49

Barga ACM DEBS 2013 Keynote

Embed Size (px)

Citation preview

Page 1: Barga ACM DEBS 2013 Keynote

Streaming Data Processing

Over the next few years well see the adoption of

scalable frameworks and platforms for handling

streaming or near real-time analysis and processing In

the same way that Hadoop has been borne out of

large-scale web applications these platforms will be

driven by the needs of large-scale location-aware

mobile social and sensor use ndash

Edd Dumbill OrsquoREILLY

Gatheramp

Distribute

Data

Gartner on Analytics Big Data and Internet of Things

Forecasts of over 50 billion intelligent devices by 2015 and 275 Exabytes per day of data being sent across the Internet by 2020 are indicators of looming challenges

bull Gartners Analytics Key Initiative focus is on two analytical styles predictive and real-time

bull Information of extreme size and need for rapid processing

bull Analytics help uncover root causes support decisions and make predictions in real time

The value of timely analytics on demand if necessaryhellip

The value of timely analytics on demand if necessaryhellip

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 2: Barga ACM DEBS 2013 Keynote

Gatheramp

Distribute

Data

Gartner on Analytics Big Data and Internet of Things

Forecasts of over 50 billion intelligent devices by 2015 and 275 Exabytes per day of data being sent across the Internet by 2020 are indicators of looming challenges

bull Gartners Analytics Key Initiative focus is on two analytical styles predictive and real-time

bull Information of extreme size and need for rapid processing

bull Analytics help uncover root causes support decisions and make predictions in real time

The value of timely analytics on demand if necessaryhellip

The value of timely analytics on demand if necessaryhellip

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 3: Barga ACM DEBS 2013 Keynote

Gartner on Analytics Big Data and Internet of Things

Forecasts of over 50 billion intelligent devices by 2015 and 275 Exabytes per day of data being sent across the Internet by 2020 are indicators of looming challenges

bull Gartners Analytics Key Initiative focus is on two analytical styles predictive and real-time

bull Information of extreme size and need for rapid processing

bull Analytics help uncover root causes support decisions and make predictions in real time

The value of timely analytics on demand if necessaryhellip

The value of timely analytics on demand if necessaryhellip

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 4: Barga ACM DEBS 2013 Keynote

The value of timely analytics on demand if necessaryhellip

The value of timely analytics on demand if necessaryhellip

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 5: Barga ACM DEBS 2013 Keynote

The value of timely analytics on demand if necessaryhellip

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 6: Barga ACM DEBS 2013 Keynote

Velocity Pipeline

20

30

TRADITIONAL

ANALYTICSbull Primarily descriptive

analytics amp reporting

bull Internally sourced

relatively small

structured data

bull ldquoBack Roomrdquo teams

of business analysts

BIG DATAbull Complex large

unstructured data sources

bull New analytical and

computational capabilities

bull Data Scientists emerge

RAPID INSIGHTS

PROVIDING

BUSINESS IMPACTbull Analytics integral to running the

business considered strategic

competitive asset CEP thinkinghellip

bull Rapid and agile insight delivery by

analytical models at point of decision

making in data streamshellip

bull Able to author and manage data

pipelines and predictive models

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 7: Barga ACM DEBS 2013 Keynote

Startups first round of funding

Early adopters investigate

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 8: Barga ACM DEBS 2013 Keynote

Mass media hype begins

Activity beyond early adopters

Negative press begins

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 9: Barga ACM DEBS 2013 Keynote

Supplier consolidation amp failures

Second third round funding

Less than 5 of potential audience

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 10: Barga ACM DEBS 2013 Keynote

Methodologies and best practices emerge

Third generation products out of the box

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 11: Barga ACM DEBS 2013 Keynote

High-growth adoption begins 20 to 30 of

the potential audience begins to adopthellip

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 12: Barga ACM DEBS 2013 Keynote

Quantum

Computing

Internet of

Things

CEP

Intelligent

Devices

Predictive

AnalyticsConsumer

Telematics

Cloud

Computing

M2M

Communications

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 13: Barga ACM DEBS 2013 Keynote

Engines to Airtime

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 14: Barga ACM DEBS 2013 Keynote

Telematics reactive to predictive

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 15: Barga ACM DEBS 2013 Keynote

Fleet Focus

ECU Connectivity

Remote

DiagnosticsUpgrades

Cost SavingsAvoidance

ProductivityOperational

Guidance

Regulatory Compliance

Telematics Serving Two Worlds

Consumer Telematics

DriverPassenger FocusConnectivity to Content

Mobility

Safety and Security Apps

Navigation

Infotainment amp Tracking

Asset Centric Person Centric

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 16: Barga ACM DEBS 2013 Keynote

Edge Supplying Data

Analyzing in realtime

Known data

patternsAdditional

Context

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 17: Barga ACM DEBS 2013 Keynote

Evolving from Reactive to Proactive

NotifyUse preferred channels to notify and insure receipt of information

PlanAssess risk options amp decide on course of action

ValidateValidate performance document actions retrain models if warranted

PredictProvide early warning of degradation with priority assessment and fault indication

ActCollaborate to secure resources amp execute work

DiagnoseFacilitate Collaboration between analyst subject matter experts amp service personnel

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 18: Barga ACM DEBS 2013 Keynote

Provides analysis on driving stylebehavior and predictive model for vehicle maintenance

Application Driver Style Impact

Sources Inputs Analytic Components Outputs

Onboard Measurements bull Speed

bull Acceleration

bull Deceleration

bull Gear Changes

bull Brake Pressure

bull Steering

bull Brake pressure

bull Accelerometer

bull Gear shift position

bull Fuel

bull Miles Driven

bull Fuel Used

bull CO2 Emissions

Aggregate Driver Behavior bull Driving Techniques

bull Agegender locality

experience of Driver

bull Speeding violations data

bull Accelerationdeceleration

bull Brake pressure

bull Accelerometer

bull Steering

bull Eco Index

bull Driving Behavior rating

bull Projected savings if driving

behavior improves

Environment ConditionsFactors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Impact on environment

Vehicle study data bull Driver behaviour

bull Vehicle study data on driver

behaviourrsquos impact on vehicle

bull Brake

bull Accelerometer

bull Gear

bull Fuel

bull Impact on vehicle and

maintenance (ie you will have

to change brakes earlier than

scheduled due to poor driving)

- - DRAFT - -

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 19: Barga ACM DEBS 2013 Keynote

Application Preventive Alerts

Sources Inputs Analytic Components Outputs

OBU bull Tire pressure

bull Battery voltage

bull Brake Pressure

bull Vehicle acceleration

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine data

bull Lights amp exhaust

bull Sensor data

bull Tire

bull Battery

bull Brake Disc

bull Accelerometer

bull Brake Fluid

bull Oil amp other fluid levels

bull Suspension

bull Steering

bull Air conditioning

bull Engine

bull Lights amp exhaust

bull Sensors

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Problem Description

Historical aggregate vehicle data bull Age of components( battery tire

etc)

bull Age at which each component was

changed service history

bull Condition of the component

bull Battery

bull Tire

bull Brake disc

bull Component Name (Battery Radio

Tire Pressure etc)

bull Status (Red Yellow Green)

bull Display(will require replacement in 2

months)

Vehicle research data bull Tire pressure effect on fuel

consumption and tire life

bull Tire pressure bull Display(2 increase in fuel

consumption due to under inflated

tire)

Environmental factors bull Emission data

bull Emission standard

bull CO2 emissions

bull CO HC NOx emission

bull Display(warning)

- - DRAFT - -

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 20: Barga ACM DEBS 2013 Keynote

Application Predictive Maintenance

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 21: Barga ACM DEBS 2013 Keynote

o A regression model was built to analyze

relationship between telematics data and

diagnostic outcome

o More specifically the model predicts the

probability that a vehicle component will

fail to function properly

o Precise error detection The model makes

use of several predictor variables (ie

telematic signals non telematic data) that

may be either numerical or categorical

o The model also determines which factors

(vehicle speed brake velocity etc) influence

more the probability of component failure

Failure Estimation Model

Pro

bab

ilit

y

Medium-Probability of

component failure

Low-Probability of

component failure

High-Probability

component failure

Signal Data

Application Preventive AlertsReal Time Diagnostic Model

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 22: Barga ACM DEBS 2013 Keynote

Vehicles Connected through Cloud ComputingCloud infrastructure provides virtualization routing and storage management

hosts the analytical models

PDA

Tolling

EV

Hybrid

Charging

V2R

Dealer

iCOM

bull DCAN

bull Ethernet

bull Flexray

ECUVCU

Satellite

GPS

Network

GSM IP

GPRS Network

PLMN

V2V

Dealer

Cellular

(WAN)

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 23: Barga ACM DEBS 2013 Keynote

Common Application Pattern

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 24: Barga ACM DEBS 2013 Keynote

Monitor act on amp log real-time

data

Analyze and model logged

data

Mind the gap between investigate and operational analyticshellip

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 25: Barga ACM DEBS 2013 Keynote

Event Stream both stored

and processed

1

Analysis produces models2

Model can be installed directly to the event

processing service for operational analytics

3

Produce real time alerts

and actions based on

predictive models

4

Event Stream

Analysis

Model

Event Processing

Engine

Alerts amp Action

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 26: Barga ACM DEBS 2013 Keynote

Velocity Pipeline enables data to flow across

an enterprise infrastructure and Internet spanning the

devices where valuable data is gathered from employees and

customers to the back-end systems where that data can be

translated into insights and action

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 27: Barga ACM DEBS 2013 Keynote

Perspective is worth 80 IQ pointshellip

Alan Kay

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 28: Barga ACM DEBS 2013 Keynote

bull Beecham Research M2M World of Connected Things Sector Map

bull ABI Research Internet of Things M2M Wireless Sensor Networks

bull Forrester

bull Internet of Things Reports

bull Search for Internet of Things M2M Sensor

bull Frost amp Sullivan Internet of Things M2M Sensor

bull Gartner

bull Internet of Things and Internet of Things Blog Posts

bull M2M and M2M Blog Posts

bull Sensor and Sensor Blog Posts

bull IDC Search for Internet of Things M2M

ldquoKey elements of the IoT which are being embedded in a variety of mobile devices include embedded

sensors image recognition technologies and NFC paymentrdquo ndash Gartner (link)

ldquoAs billions of devices connect via the

Internet exchanging information and

taking autonomous actions based on

continuous input we will face a

paradigm change that will transform

our personal lives and revolutionize

business These radical transformations

will pose unprecedented data privacy

and security challenges to security and

risk (SampR) professionalsrdquo ndash Forrester (link)

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 29: Barga ACM DEBS 2013 Keynote

bull BusinessWeek Internet of Things M2M

bull CIOcom Internet of Things M2M

bull Computer World Internet of Things M2M

bull Forbes Internet of Things M2M

bull InformationWeek Internet of Things M2M

bull InfoWorld Internet of Things M2M

bull Venture Beat Internet of Things M2M

bull Wall Street Journal Internet of Things M2M

bull Wiredcom Internet of Things M2M

bull ZDNet Tapping M2M The Internet of Things M2M

Tapping M2M The Internet of Things by ZDNet

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 30: Barga ACM DEBS 2013 Keynote

bull Accenture Toasters refrigerators and Internet of Things

bull Ericsson Labs Internet of Things

bull Harbor Research Website

bull HP Implementing ldquoThe Internet of Thingsrdquo in Your Business and

bull IBM The Internet of Things (video) and Internet of Things (IBM Academy of Technology paper)

bull Information Builders Internet of Things

bull Infosys Internet of Things Endless Opportunities

bull Intel Simplifying the Internet of Things

bull Microsoft Building the Internet of Things

bull Oracle M2M Solutions The Move to Value Creation and the Internet of Things

bull SAP The Ubiquitous Internet of Things Managing Cities the Smart Way and Making The Internet

Of Things A Reality With Mobile Management

bull Siemens The Next Network

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 31: Barga ACM DEBS 2013 Keynote

bull Google Blog Search Internet of Things M2M Sensors

bull Google+ Communities Search Internet of Things M2M

bull LinkedIn Group Search Internet of Things M2M and

Group Sensor Networks

bull Pinterest Search Internet of Things Machine to Machine

bull Twitter hashtag searches IoT M2M sensors

bull Tumblr Search Internet of Things

bull YouTube Internet of Things Playlists and Internet of Things

Channel

bull YouTube M2M Playlists and Machine to Machine Channel

bull Wikipedia Internet of Things M2M

Internet of Things Playlists on YouTube

Page 32: Barga ACM DEBS 2013 Keynote