BIG DATA SOURCES FOR/FROM INTELLIGENT ROAD TRANSPORT: AN OVERVIEW

Dr. Evangelos Mitsakis, CERTH-HIT

Data? What is it actually?

A small sized data set

One vehicle transmits its GPS data to a central server The GPS data logger contains info about:

o Position (x, y, z coordinates)

o Speed

o Heading o Unique ID

Description Type Size

Position (coordinates) Integer 24

Speed Integer 4

Heading Integer 4

Unique ID Integer 4

36 bytes

A slightly bigger sized data set

40000 vehicles transmitting their GPS data every second: 36 bytes x 40000 vehicles = 1440000 bytes = ~ 1 MB/sec = 60 MB/min

= 3600 MB/hour = ~ 3 GB/hour = ~ 72 GB/day = ~ 25 TB/year

An even bigger dataset

Google Maps has over 20 petabytes of data = ~ 21 million GB = ~ 20500 TB

Source: mashable.com

Why so much data?

Digitization of everyday activities, including travel, shopping, billing, ticketing etc.

Increasing dependence on electronic devices, all of which leave digital footprints every time they are used.

Connected devices & vehicles (Internet of Things)

Connected travelers

Progress in Big data technologies: software and hardware

Jeffrey Dean, Sanjay Ghemawat (Google) (2004) MapReduce

Google’s BigTable

Apache Hbase

Apache Hadoop

NOSQL databases, eg MongoDB

Graph databases, eg. Neo4j

SPARQL (linked data)

Big - Open - Linked

While Big Data is defined by its size, Open Data is defined by its use

Linked Data is about using the Web to connect related data that wasn't previously linked, or using the Web to lower the barriers to linking data currently linked using other methods.

Sources: http://www.opendataenterprise.org/ http://linkeddata.org/

Big data for traffic management

Big data is providing new insights into traffic patterns. E.g. several technologies are used in UK’s ‘smart motorways’ to

monitor driving conditions and to allow variable speed limits to be set to improve traffic flow performance.

Traffic Information Services collect data through FCD in addition to CCTV, traffic cameras and traffic sensors to give a real-time view of traffic conditions.

Big data is processed to provide real-time traffic data to information service providers.

Private companies use FCD collected through vehicle fleets to gather information on traffic flows and delays.

In freight and logistics, big data is used to optimize delivery, which can reduce carbon emissions and mileage.

Source: Parliamentary Office of Science & Technology

Big data for public transport

Help to understand travelers’ journey patterns, in terms of where they travel, what mode they choose, how frequently they travel and how reliable their journeys are.

These insights can be used o by transport operators to inform decisions around the planning of services. For

example, smart card data. o understand better the end-to-end journeys that customers make for network

planning and for operations management. Inform transport agencies and operators of how people from different

groups (students, children, seniors, regular commuters and infrequent travellers) use the public transport system

Gain a deeper understanding of travelers’ needs. Big data visualisation is an additional tool for transport organisations

o Improved planning and operational decisions about services. o Provide travelers with improved “transparency” of the network and the services.

Source: Parliamentary Office of Science & Technology

Big and open data for traveler information

Opening up (big) transport data to software developers can allow users to receive personalized information, such as delays on their local roads or public transport routes.

It can also generate economic benefit if reduced travelling times mean that employees spend more time working, or other benefits if it increases time available for non-work activities.

E.g TfL data has been valued at approx. 80 million € per year and has resulted in over 200 travel apps being developed by private companies.

Source: Parliamentary Office of Science & Technology

Big data for asset maintenance

Big data offer new opportunities to identify problems more quickly and to reduce costs.

For example, Network Rail uses smartphones and GPS co-ordinates to increase the accuracy of locating track defects to within 5 metres (previously it had been 1 mile).

On road networks, mobile sensors, such as Floating Car Data (FCD) are used to overcome the limitations of fixed sensors, such as the expense of installing and maintaining sensors embedded in the road.

In the USA, smartphones have been used to crowd-source information about the state of assets, such as roads.

Source: Parliamentary Office of Science & Technology

Big & open data use in the transport sector

Governments

• Traffic Control • Transport Planning and Modeling • Route Planning • Congestion Management • Intelligent Transport Systems

Private sector

• Travel Industry • Route Planning and Logistics • Competitive Advantages • Technological Enhancements

Individuals • Route Planning (save time/increase fuel-

efficiency) • Travel (tourism)

Source: International Transport Forum

Big and open data, transportation and smart cities

Source: Smart Cities Readiness Guide

Big data in research

Size, not sample: Allows focusing on size, not sample, improving accuracy of studies and responses to needs of governments, companies and people.

New big data technology means studies will not have to rely on o Sample sizes, because the amount of data collected will be vast. o Models, because the measurements themselves will be able to

replicate reality

Big ITS data in Thessaloniki: FCD

Big ITS data in Thessaloniki: C2X

Big ITS data in Thessaloniki: BT

Big data in Thessaloniki: Social networking services

Big data in transport: what to expect?

Improved multi-source traffic and travel data availability and processing.

Tools to enhance multi-source traffic and travel data fusion (for improved data quality) for: o Improved traffic and mobility management o Improved (better informed) decision support for all related entities o Improved insights into multimodal traffic and travel patterns,

collectively and at individual traveller level o Improved understanding of travellers’ needs o Improved traveller information and traveller assistance services

Combine big, open and linked data to leverage innovation and economic benefits

Thank you for your attention

Dr. Evangelos Mitsakis

Associate Researcher Centre for Research and Technology Hellas Hellenic Institute of Transport e: emit@certh.gr