Upload
others
View
0
Download
0
Embed Size (px)
Citation preview
Page1
beAWAREEnhancingdecisionsupportandmanagementservicesinextremeweatherclimate
events
700475
D7.1TechnologicalRoadmap
Disseminationlevel: Public
Contractualdateofdelivery: Month6,30June2017
Actualdateofdelivery: Month6,30June2017
Workpackage: WP7Systemdevelopment,integrationandevaluation
Task: T7.1SystemRequirementsandArchitecture
Type: Report
ApprovalStatus: FinalDraft
Version: 1.0
Numberofpages: 52
Filename: d7.1_beaware_technological_roadmap_2017-6-
30_v1.0.docx
Abstract
Theobjectiveofthisdocumentistodefinetheoutlineofthetimeplanforthedevelopment
ofthebeAWAREplatform.Inthiscontext,thedeliverableprovidesahighlevelviewofthe
beAWAREplatformarchitectureandaspecificationoftheinfrastructurelayout.Inaddition
the deliverable includes an initial functional description of each of the technicalmodules,
describing the supporting technologies, the increasing functionalities over time and the
development timeline. Finally, the deliverable includes a summary of the use cases and a
global project timeline, describing the platform’s scheduled iterations and the levels of
functionalityattheprojectmilestones.
The information in thisdocumentreflectsonly theauthor’sviewsandtheEuropeanCommunity isnot liable foranyuse
that may be made of the information contained therein. The information in this document is provided as is and no
guaranteeorwarrantyisgiventhattheinformationisfitforanyparticularpurpose.Theuserthereofusestheinformation
Ref. Ares(2017)3305579 - 30/06/2017
Page2
atitssoleriskandliability.
Co-fundedbytheEuropeanUnion
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
History
Version Date Reason Revisedby0.1 05.06.2017 Deliverablestructure Allpartners
0.2 22.06.2017 Contributionsbyallpartners Allpartners
0.3 23.06.2017 Integrateddocument CERTH
0.4 24.06.2017 Internalreviewofthedocument B.Mandler(IBM)
1.0 30.06.2017 Finalversion CERTH
Authorlist
Organisation Name ContactInformationCERTH YiannisKompatsiaris [email protected]
CERTH AnastasiosKarakostas [email protected]
CERTH KonstantinosAvgerinakis [email protected]
CERTH EfstratiosKontopoulos [email protected]
IBM BenjaminMandler [email protected]
IBM EvgeniyHvostenko [email protected]
MSIL IsraelAltar [email protected]
MSIL YanivMordecai [email protected]
IOSB HylkevanderSchaaf [email protected]
UPF StamatiaDasiopoulou [email protected]
UPF JensGrivolla [email protected]
UPF GerardCasamayor [email protected]
UPF SimonMille [email protected]
UPF LeoWanner [email protected]
AAWA DanieleNorbiato [email protected]
AAWA MichelleFerri [email protected]
PLV CarmenCastro [email protected]
HRT IosifVourvachis [email protected]
FBBR AmalieJanniche [email protected]
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
ExecutiveSummary
This deliverable presents the technological roadmap towards the implementation of the
beAWAREplatform.
First, this roadmap presents a high-level view of the envisioned architecture for the
beAWARE platform, illustrating the conceptual architecture and a draft of the complete
technical architecture. Then, the deliverable describes themodules that are developed in
eachWork Package and comprise the beAWARE platform. For eachmodule, a functional
description is provided including a summary of its scientific and technical objectives and
supportingtechnologies,input/outputspecifications,theincreasingfunctionalityovertime,
the development timeline, as well as the detailing schedule and resource allocation. In
addition, D7.1 provides a summarised vision of the proposed use cases and their
implementation strategy. Finally, a global project timeline is presented, describing the
platform’sschedulediterationsandthelevelsoffunctionalityattheprojectmilestones.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
AbbreviationsandAcronyms
ASR Automaticspeechrecognition
CCTV CloseCircuitTV
DTr Dynamictexturerecognition
GIS GeographicalInformationSystem
HTTP HypertextTransferProtocol
JSON JavaScriptObjectNotation
KB KnowledgeBase
ObjD Objectdetection
OWL WebOntologyLanguage
PSAP Public-safetyansweringpoint
RDF ResourceDescriptionFramework
REST RepresentationalStateTransfer
STL Spatio-temporallocalization
TLc Trafficlevelclassification
UC UseCase
WP WorkPackage
XML ExtensibleMark-upLanguage
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
TableofContents
1 INTRODUCTION......................................................ERROR!BOOKMARKNOTDEFINED.
2 ARCHITECTURE.........................................................................................................10
2.1 Description...........................................................................................................112.1.1 Platformcomponents..........................................................................................................11
2.2 Technologystack...................................................................................................122.2.1 Programminglanguages......................................................................................................13
2.2.2 Databases/Repositories.......................................................................................................13
2.2.3 Othertechnologies..............................................................................................................13
2.2.4 Exchangeformats................................................................................................................14
3 FUNCTIONALDESCRIPTIONOFMODULES...............ERROR!BOOKMARKNOTDEFINED.
3.1 Earlywarninggeneration(WP3)............................................................................153.1.1 Crisisclassificationmodule..................................................................................................15
3.1.2 Conceptandconceptualrelationextractionfromtextualinformationmodule.................15
3.1.3 Conceptandeventdetectionfrommultimediamodule.....................................................16
3.1.4 AutomaticSpeechRecognition(ASR)module.....................................................................18
3.1.5 Activitytableandworkload.................................................................................................19
3.1.6 Timelineanddependencyfromothermodules...................................................................21
3.2 Aggregationandsemanticintegrationofemergencyinformationfordecisionsupportandearlywarningsgeneration(WP4)..................................................................22
3.2.1 SocialMediaMonitoringmodule.........................................................................................22
3.2.2 MonitoringmachinesourcinginformationfromIoTandM2Mplatformsmodule.............24
3.2.3 Semanticrepresentationandreasoningmodule.................................................................25
3.2.4 Activitytableandworkload.................................................................................................27
3.2.5 Timelineanddependencyfromothermodules...................................................................29
3.3 Multilingualreportgeneration(WP5)...................................................................303.3.1 Textplanningmodule..........................................................................................................30
3.3.2 Multilinguallinguisticgenerationmodule...........................................................................30
3.3.3 Activitytableandworkload.................................................................................................31
3.3.4 Timelineanddependencyfromothermodules...................................................................32
3.4 MainPublicSafetyAnsweringPointforemergencymultimediaenrichedcalls(WP6) 33
3.4.1 PSAPcapabilities..................................................................................................................33
3.4.2 Activitytableandworkload.................................................................................................36
3.4.3 Timelineanddependencyfromothermodules...................................................................38
3.5 Systemdevelopment,integrationandevaluation(WP7).......................................393.5.1 Twelve-FactorApplications..................................................................................................39
3.5.2 Systemarchitecture.............................................................................................................40
3.5.3 Technicalinfrastructure.......................................................................................................41
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.5.4 Systemdevelopment...........................................................................................................41
3.5.5 Communicationbus.............................................................................................................42
3.5.6 End-usersapplications.........................................................................................................43
3.5.7 Activitytableandworkload.................................................................................................43
3.5.8 Timelineanddependenciesfromothermodules................................................................45
4 DEVELOPMENTCYCLEANDUSECASES......................................................................46
4.1 Scenario1:Flood...................................................................................................46
4.2 Scenario2:Fires....................................................................................................47
4.3 Scenario3:Heatwave............................................................................................48
5 PROJECTTIMELINEANDMILESTONES.......................................................................51
6 SUMMARY................................................................................................................52
ListofFiguresFigure1:Architecturalhigh-levelview....................................................................................10
Figure2:AllocationofTwitterpoststoitsproperdatacollection..........................................22
Figure3:Interfaceforclassifyingpostsasrelevant/irrelevant...............................................23
Figure4:beAWAREontologynetwork....................................................................................25
Figure5:PSAPTechnologicalArchitecture.............................................................................33
Figure6:beAWAREwalkingskeleton......................................................................................51
ListofTablesTable1:Programminglanguages............................................................................................13
Table2:Databaseandrepositorypackages............................................................................13
Table3:Othertechnologies....................................................................................................14
Table4:Crisisclassificationmodulesummary........................................................................15
Table5:Conceptextractioncomponentsummary.................................................................16
Table6:Relationextractioncomponentsummary.................................................................16
Table7:Dynamictexturerecognitioncomponentsummary..................................................17
Table8:Objectdetectioninvideoframesandimagescomponentsummary........................17
Table9:Trafficlevelclassificationcomponentsummary.......................................................18
Table 10: Spatio-temporal localization of fire, smoke and flood incidents component
summary.................................................................................................................................18
Table11:Automaticspeechrecognitionmodulesummary...................................................19
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Table12:WP3activitytable....................................................................................................20
Table13:WP3timeline...........................................................................................................21
Table14:Socialmediamonitoringmodulesummary.............................................................24
Table 15:Monitoringmachine sourcing information from IoT andM2Mplatformsmodule
summary.................................................................................................................................25
Table16:SemanticKBcomponentsummary..........................................................................26
Table17:KBservicecomponentsummary.............................................................................27
Table18:Semanticreasoningcomponentsummary..............................................................27
Table19:WP4activitytable....................................................................................................28
Table20:WP4timeline...........................................................................................................29
Table21:Textplanningmodulesummary..............................................................................30
Table22:Multilinguallinguisticgenerationmodulesummary...............................................31
Table23:WP5activitytable....................................................................................................31
Table24:WP5timeline...........................................................................................................32
Table25:Pre-EmergencyDecision-SupportingRiskVisualizationsummary..........................34
Table26:EmergencyIncidentCollectionandDisplaysummary.............................................34
Table27:FirstResponderPositionCollectionandDisplaysummary.....................................35
Table28:IncidentAssignmenttoFirstRespondersummary..................................................35
Table29:PublicAlertsummary..............................................................................................35
Table30:IncidentManagementsummary.............................................................................36
Table31:WP6activitytable....................................................................................................37
Table32:WP6timeline...........................................................................................................38
Table33:Architecturedefinitionsummary............................................................................41
Table34:Infrastructuredefinitionsummary..........................................................................41
Table35:Systemdevelopmentsummary...............................................................................42
Table36:Communicationbussummary.................................................................................42
Table37:End-usersapplicationssummary.............................................................................43
Table38:WP7activitytable....................................................................................................44
Table39:WP7timeline...........................................................................................................45
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
1 Introduction
ThisdocumentpresentsaroadmapofhowtheConsortiumplanstodevelopthebeAWARE
platform. The objective of the deliverable is to specify in detail: (i) the progressively
increasingfunctionality(inparticularatthetimepointsofthemilestones)oftheindividual
modules as well as of the platform as a whole, (ii) the temporal and functional
synchronisationoftheindividualmodulestoensurethisfunctionality;(iii)theresourcesthat
willbeneededtoachievethisfunctionality;(iv)thetechnicalinfrastructurespecifications.
Tothisend,andbasedonamodelofiterativedevelopment,theroadmapincludes:
1. Ahigh-levelviewoftheenvisionedPlatformarchitecture,illustratingtheconceptual
architectureandadraftofthecompletetechnicalarchitecture.Aspecificationofthe
infrastructurelayoutandtopologyisalsoprovided.
2. Afunctionaldescriptionofeachofthetechnicalmodules,describing:
a. A summary of its scientific and technical objectives, and supporting
technologies;
b. Itsprogressivelyincreasingfunctionalityovertime;
c. Itstimeline,detailingscheduleandresourceallocation;
3. Asummarisedvisionoftheproposedusecasesandtheirimplementationstrategy;
4. A global project timeline, describing the platform’s scheduled iterations and the
levelsoffunctionalityattheprojectmilestones;
Therefore, this deliverable is structured as follows. Section 2 presents the architecture.
Section3providesthefunctionaldescriptionofthemodulesinvolvedinalignmentwiththe
project Work Packages (WPs). Section 4 presents the development cycle and briefly
discusses the use cases. Finally, Section 5 provides the overall project timeline and the
milestones,whileSection6concludesthedeliverable.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
2 Architecture
The forming architecture is formulated with the ultimate goal of providing accuracy and
functionality for decision support systems to be able to respondwell to weather related
disasterscenarios.
Thearchitectureisroughlymadeupofthefollowinglayers:
1. Ingestionlayer,containingmechanismsandchannelsthroughwhichdataisbrought
intotheplatform;
2. Internal services, genericdata repositoriesandcommunicationservicesbeingused
bythedifferentcomponents;
3. Businesslayer,containingthecomponentsthatperformtheactualplatform-specific
capabilities;
4. External facing layer, including the end-users’ applications and PSAP (Public-safetyansweringpoint)modules,interactingwithpeopleandentitiesoutsidetheplatform
(end-usersoftheplatform).
Figure1:Architecturalhigh-levelview
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
2.1 DescriptionAscanbederivedfromFigure1,thefirststepinagenericflowoftheplatformconsistsof
new data being pushed into the platform. The new data can originate from specific
beAWARE applications used by civilians (end-users) or first responders. Note that these
applicationsmay be bi-directional as they can serve to communicate backwith the users
uponneed.Moreover, incomingdata to theplatformcanoriginate fromother sources as
well,suchasIoTdevices,socialmediapotsgrabbedbycrawlers,andweatherdata,toname
afew.
Once a newpieceof data is successfully ingested into the system, thedata is stored in a
temporaryrawdatastoreandtheavailabilityofthenewpieceofdataisbroadcastedtoall
interested components using a specific topic of the messaging service. There shall be a
separate topic for each kind of information flowing into the system, such that only
componentswhich are interested in that specific kind of datawill bemade aware of the
arrivalofanewrelevantpieceofdata.
All interested parties will receive the information, which includes a pointer enabling to
access the data, and shall perform their specific analysis on the newdata.Note, that the
resultofsuchananalysismayinturncreateanewpieceofdatawhichisofinteresttoother
components,thatonceagainwillbemadeawareandaccessthedatainthesamemanner
explainedabove,providingservicesforcrisisclassificationandearlywarning.
The final results of the analysis canbe added to the knowledgebase, and if requiredwill
notifyPSAPrelatedcomponentsoftheidentificationofanewstate.
ThePSAP in turnmayusebeAWAREcomponents, includingapps tomanageandalert the
differentstakeholders(citizens,firstresponders,andauthorities).
2.1.1 Platformcomponents
Ingestion layer – Serves as the input mechanism into the platform. Different kinds of
informationcanserveasinputtothesystem.Forexample,IoTdevicesandadditionalinput
mechanisms, such as dedicated applications, can produce different kinds of data such as
measurements (time series), pictures, videos, audio, and more. An additional source of
incominginformationisweatherrelateddata.Typically,onceanewpieceofdatahasbeen
ingested into theplatform, it is stored temporarily in a raw storage system, andaproper
notificationissentviatheservicebustotheinterestedparties.
Internal services – These services are used internally for the proper functioning of thecapabilities provided by the various components. These services are usedmostly for data
storage and communication. Some generic data analytics and processing servicesmay be
used as well. Examples of this layer include a central (raw) data repository, a central
messagebus,andagenericknowledgebase.Theseserviceswillbeaccessibletoallplatform
components.
Businesslayer–This layerencompassesthecomponentsthatperformtheactualplatform
specificcapabilities.Thebulkoftheplatformisconcentratedatthislayer,whichinteractsin
turnwithalladditionallayers.Aparticulargroupofcomponentsinthislayertacklestheanalysisofdifferentkindsofdata
flowingintotheplatform.Amainaspectofthecomponentsinthiscategoryisextractionof
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
semanticdata flowing into theplatform fromvariousdifferent sources.Among this group
wecanfindthefollowingcomponents:
• SocialMediaAnalysisServices
• Imageanalysis
• Videoanalysis
• Multimediaanalysis
• Automaticspeechrecognition
• Sensoranalysis
These components help to determine the crisis classification and drive the detection of
eventswhichleadsinturntomeaningfuldecisionsupport.
Asecondgroupofcomponentsdealmorespecificallywiththeanalysisofweather-related
data.Amongthesecomponentsare:
• ClimateEmergencyModelingandPredictionServices
• WeatherForecastServices
• FloodPredictionServices
Bothsub-categorieslistedabovecontributetotheproperwarninggenerationcapabilitiesof
theplatform,includingmeasuresofcrisisclassification.
A third groupof related components dealmostlywith text, both at the input andoutput
aspects.Namely, incomingtextmessages,possibly inavarietyof languages,areprocessed
and analyzed, and outgoing textmessages that need to be delivered by the platform are
prepared:
• MultilingualReportGenerator
• MultilingualTextAnalyzer
External layer – This layer handles the interaction of the platformwith external entities,
bothas inputprovidersandoutput recipients. Thereare twomaingroupsof components
makingupthislayer,namely:
• Mobileapplications
o CiviliansMobileApplication
o FirstResponderMobileApplication
• Controlcenters
o PublicSafetyAnsweringPoint(PSAP)
o ValenciaLocalPoliceControlCenter
The REST architectural pattern will be used to model the services used by the different
services. REST proposes a very lightweight, HTTP-based method of stateless operations
betweenresourcesintheWeb.
2.2 TechnologystackIn order to keep the architecture coherent and manageable, and simplify hosting and
maintenance, a controlled set of technologies will be used to implement the shared
componentsoftheplatform.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
As a general principle, open source technologies will be used to implement the platform
(“opensource”definedassoftwarelicensedunderanOSI1-approvedlicensethatisincluded
in the list of EUPL-compatible licenses2). Exceptions will be proprietary or non EUPL-
compatible licenses for software belonging to a partner in the beAWARE consortium, or
specificproducts,wherenoEUPL-compatiblealternativesexist.
2.2.1 Programminglanguages
A preliminary list of the selected programming languages for module implementation is
providedinTable1.
Language/framework Versions
allowed
Notes
Python 2.7 Forcomponentdevelopment
Java JSE7,JSE8,JEE7 Forcomponentdevelopment
C/C++ ANSI-C99/ISO
C++
Forcomponentdevelopment
R 3.2 Forcomponentdevelopment
JavaScript Any Node.js0.10.x
Table1:Programminglanguages
2.2.2 Databases/Repositories
Apreliminarylistofselecteddatabase/storagesolutionsisprovidedinTable2.
Datastore Versions
allowed
Notes
GraphDB 8.1 RDFrepository–accessviaSPARQLandHTTP
MongoDB 3.4.2 Socialmediaandmultimediastorage
PostgreSQL 9.x RelationalDB(Time-seriessensordataandmetadata)
ObjectStorage - IBM®ObjectStorageforBluemix(rawdatastore)
Table2:Databaseandrepositorypackages
2.2.3 Othertechnologies
A preliminary list of miscellaneous technological packages (application servers, special
purposestacks,etc.)isprovidedinTable3.
Product Versions
allowed
Notes
Kafka 0.8.x Messagingservice
1 Open Source Initiative, see http://opensource.org/. 2 See https://joinup.ec.europa.eu/software/page/eupl/eupl-compatible-open-source-licences for complete list of EUPL-compatible open source licences.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
(MessageHub)
Jetty 9.x J2EEapplicationserver(preferred)
Tomcat 7.x J2EEapplicationserver
Node.js 0.10+ JavaScriptapplicationserver
ApacheJena 3.x SemanticWebframeworkforJava
Table3:Othertechnologies
2.2.4 Exchangeformats
The preferred exchange format for structured datawill be JSON3.UTF-8 encodingwill be
usedinordertoensurecorrectandconsistenthandlingofmultilingualcontent.
For semantic data representation and serialisation, theOWL2/XML format4 will be used.
JSON-LD5willbeusedwhereappropriatetorepresentLinkedData.
Finally,forannotationsofmultimediacontent,theMPEG-7standard6willbeused.
3 http://json.org/ 4 https://www.w3.org/TR/owl2-xml-serialization/ 5 http://json-ld.org/ 6 http://mpeg.chiariglione.org/standards/mpeg-7
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3 FunctionalDescriptionofModules
3.1 Earlywarninggeneration(WP3)WP3 addresses the provision of the necessary technological solutions that will allow the
beAWARE framework to provide early warning and decision support to the PSAP. This is
accomplished through: i) the crisis classification module, ii) the module that deals with
concept and conceptual relation extraction from textual information, iii) the multimedia
concept/eventdetectionmodule,andiv)theautomaticspeechrecognition(ASR)module.
3.1.1 Crisisclassificationmodule
ThebeAWAREcrisisclassificationmoduledealswith the identificationandclassificationof
crisis events, based on 1) weather forecasting data (provided by FMI), 2) data from
heterogeneoussources(e.g.photos,writtentext,socialmedia,etc.)and3)rulesthatwillbe
definedwith the help and guidance of user experts. Themodule serves as a two-layered
crisisclassificationsystem(firstlayer:earlywarningofupcomingcrisisevents,secondlayer:
real-timemonitoringofanidentifiedcrisisevent’sseveritylevel).
Input • Weatherforecastingdata(earlywarninglayer)
• OutputsfromWP3-WP5modules(monitoringlayer)
Output • Identificationofupcomingcrisisevent(earlywarninglayer)
• Levelofseverityforidentifiedcrisisevent(monitoringlayer)
Programminglanguages Java,R
Dependencies • WP2weatherforecastingdata
• WP2userrequirements
• OutputfromWP3-WP5modules
CriticalFactors • DifficultiesinutilizingtheoutputsofsomeWP3-WP5modules
inthemonitoringlayerofthemodule
• Insufficientintegrationoftheuserpartners’domainexpertise
intothemonitoringlayer
Table4:Crisisclassificationmodulesummary
3.1.2 Conceptandconceptualrelationextractionfromtextualinformationmodule
Theconceptandconceptualrelationextractioncomponentsimplementthemultilingualtext
analysis functionalities of beAWARE, enabling to process textual inputs in the targeted
languages and abstract them into structured representations that faithfully capture their
meaning,andcanbesubsequentlyreasoneduponforintelligentdecisionmakinginWP4.
ConceptextractioncomponentThe concept extraction component tackles the recognitionof namedandnominal entities
(objects,locations,etc.)andeventsfromthepertinenttobeAWAREtextualinputs(i.e.social
media posts, SMS messages, transcribed language, etc.), their disambiguation, and their
mapping to existing structured lexical and knowledge resources such as BabelNet7 and
7 http://babelnet.org/
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
DBpedia8. ItservesasthefirststepofthebeAWAREsemantic,multilingualtextanalysis. It
involvesseveralsteps,includingthenormalisationofthetextualinputs.
Input Rawtext,pluspertinentmetadata(e.g.geolocation)
Output RDFrepresentations,fedtotheKBviaUPDATEqueries
Programminglanguages/tools
Java,UIMA/DKProsoftwarearchitecture,JenaAPI
Dependencies • Componentsaffording(viatheBUS)textualinputs,namely:
socialmediamonitoring,automaticspeechrecognition,and
mobileapplicationbackend
• Semanticrepresentationandreasoning:theextractedRDF
representationsareusedtopopulatetheKB
CriticalFactors Poorcontextduetobrevityandnatureofinputtexts
Table5:Conceptextractioncomponentsummary
RelationextractioncomponentThe relation extraction component deals with the identification of semantic frames, i.e.
relationalcontextsthatdenoteeventsandsituationsbetweenentities(frameparticipants)
andthesemanticroles(frameroles)oftheparticipatingentities.Itservesasthesecondstep
ofthebeAWAREsemantictextanalysis.
Input Raw text plus annotations extracted by the concept extraction
module
Output RDFrepresentations,fedtotheKBviaUPDATEqueries
Programminglanguages/tools
Java,UIMA/DKProsoftwarearchitecture,Matetools,JenaAPI
Dependencies • Conceptextractionperformance
• Semantic representation and reasoning: the extracted RDF
representationsareusedtopopulatetheKB
CriticalFactors • Poorcontextduetobrevityandnatureofinputtexts
• Incompleteand/orpartiallyungrammaticalinputs
Table6:Relationextractioncomponentsummary
3.1.3 Conceptandeventdetectionfrommultimediamodule
Thismoduleconsistsof severalcomponents thatdealwithseveralaspectsofconceptand
event detection. More specifically, the concept and event detection from multimedia
modulecomprisesthefollowingcomponents:(a)Thedynamictexturerecognition(DTr),(b)
the object detection (ObjD) in video frames and images, (c) the traffic level classification
(TLc)and(d)theSpatio-Temporallocalization(STL)offire,smokeandfloodincidents.More
informationforeachcomponentisprovidedinthefollowingsubsections.
8 http://wiki.dbpedia.org/
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Dynamictexturerecognition(DTr)componentThedynamictexturerecognitioncomponentisresponsibleforanalysingvideosamplesand
determining whether they contain a fire, smoke, flood or traffic incident. It is used as a
prerequisitebeforerunningobjectdetectionandtrafficclassificationcomponents.
Input Videofile(.avi,.mp4)fromstaticormobilecamera.
Output .xmlwiththepredictionscoreoftheclassificationtask
Programminglanguages/tools
C/C++,Python,openCV,vlfeat
Dependencies • WP2userrequirements
• WP4modulesthatwillprovidetheinputvideosfromtweets
• WP4modules (KB service) that will retrieve information from
theDTr
CriticalFactors It is essential that the input files have been acquired from video
samples that do not contain a lot of camera motion, and good
lightingcondition.
Table7:Dynamictexturerecognitioncomponentsummary
Objectdetection(ObjD)componentObjectdetectionwilltakeplaceonvideosamplesthathavebeenindicatedbythedynamic
texturecomponenttoincludeafire,smoke,floodortraffic incidents.Objectdetectionwill
alsotakeplaceon imagesthatthetextretrievalmodulewhichanalysestweeterpostshas
indicatedthattheycontainfire,smokeoffloodincident.
Input Video(.avi, .mp4)fromstaticofmobilecameraor imagefile(.png,
.jpg)frommobilecamera
Output .xmlwiththepredictionscoresforeachobjectthatexistsinsidetheimageframeanditsboundingbox(i.e.wherethisobject is located
insidetheimage)
Programminglanguages/tools
C/C++,python,openCV,vlfeat,caffe
Dependencies • WP2userrequirements
• DTrcomponent
• WP4 modules (KB service) that will provide the input images
andvideosfromtweets
• WP4modulesthatwillretrieveinformationfromtheObjD
CriticalFactors Theobjectsthatweexpecttoidentifyshouldnotbeoccludedmore
than50%bywater,smokeorfloodregions.
Table8:Objectdetectioninvideoframesandimagescomponentsummary
Trafficlevelclassification(TLc)componentThe traffic level classification component will be responsible for classifying the traffic
incidentsthathavebeendetectedbythedynamictexturecomponent.Trafficlevelincidents
couldbeclassifiedaslight,mediumorhighdensityones.Thealgorithmcouldworktwofold
sothatitcanclassifybothimagesandvideoinputfiles.Ontheonehand,thecomponentwill
count thenumberofcarsbyusing theobjectdetectioncomponent toclassify image files,
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
while on theother hand itwill use dynamic texture representation features to clarify the
motionpatternthatthecarsexhibitanddistinguishthetrafficlevelinvideos.
Input Video (.avi, .mp4)or image file (.png, .jpg) from static surveillance
cameraorCloseCircuitTV(CCTV)
Output .xmlwiththetrafficlevelofanimageorvideofile
Programminglanguages/tools
C/C++,python,openCV,vlfeat,caffe
Dependencies • WP2userrequirements
• DTrandObjDcomponents
• WP4modules (KB service) that will retrieve information from
theTLc
CriticalFactors Wewould need long duration videos to classify appropriately the
trafficlevelclassificationmodel.
Table9:Trafficlevelclassificationcomponentsummary
Spatio-temporallocalization(STL)offire,smokeandfloodincidentscomponentThespatio-temporallocalizationcomponentwillanalysevideofilessoastoidentifythestart
andendboundarydetectionframeswhereacriticaleventoccurs(dynamictexturetemporal
detection).Afterwards,spatiallocalizationwilltakeplacetoidentifythisincidentspecifically
in each frame (dynamic texture frame-based spatial localization). This component will
produceamoredetailedanalysisofwhereacriticaleventoccurs insidea longhourvideo
sample.
Input Video(.avi,.mp4)fromstaticormobilecamera
Output .xmlwiththeboundarytimestampsofacriticalevent(startandend
frame) and corresponding bounding boxes for each video frame
inside
Programminglanguages/tools
C/C++,python,openCV,vlfeat,caffe
Dependencies • WP2userrequirements
• WP3component:DTr
• WP4modules (KB service) that will retrieve information from
theSTL
CriticalFactors This module will work only for long duration videos with critical
events
Table10:Spatio-temporallocalizationoffire,smokeandfloodincidentscomponent
summary
3.1.4 AutomaticSpeechRecognition(ASR)module
The automatic speech recognition module provides a channel for analysis of spoken
language in audio and video files. Themodule considers both audio extraction and audio
transcriptionfunctionalities.Theformerdealswiththeextractionofaudio,inthecasethat
the input to themodule is a video file. The latter dealswith the conversion of the audio
input into written texts. The module is able to accept audio and video input in various
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
formatsandencodings.WithinbeAWARE,ASR isperformed for three languages regarding
thepilotusecases,namelyItalian,SpanishandGreek.ASRisalsoperformedforEnglish(for
presentation/demonstrationpurposes).
Input Audioorvideofile,languageparameter(English,Italian,Spanishor
Greek)
Output Theoutputisretrievedasynchronously:
• Inthefirststepafile-ID
• Inthesecondstep,eithertherecognisedtextasaplainUTF-8
textortheCTMfilewithtimestepsforeachrecognisedword
Programminglanguages C++,Python
Dependencies • InordertobeabletoadapttheASRfortheusecasedomains,
there will be a need to collect (monolingual) corpora for the
defined domains. Thus, the ASR quality will depend on the
quality and the use-case closeness of the data which will be
usedforthetraining.
CriticalFactors • Therecognitionqualitymightbe lowfortheselecteddomains,
ifthetrainingdatadiffersfromthetestingdata.
Table11:Automaticspeechrecognitionmodulesummary
3.1.5 ActivitytableandworkloadActivity Subactivity Description Dependencies
Crisisclassification Earlywarning Identification and
early warning of
upcoming crisis
events
WP2 weather
forecastingdata
Severity level
monitoring
Real-time
monitoring of an
identified crisis
event’s severity
level
• WP2user
requirements
• Outputfrom
WP3-WP5
modules
• Userpartners’
domain
expertise
Concept and
conceptual relation
extraction from
textualinformation
Conceptextraction Textualinputs
normalization;
identificationand
disambiguationof
named(locations,
temporal,etc.)and
nominalentities
(events,objects)
• Feedoftextual
inputsfrom
socialmedia
monitoring,
mobile
application&
ASR
components
• KBmodeling
andpopulation
requirements
Relationextraction Distilleventsand
situationsalong
with-centric
• Concept
extraction
• KBmodeling
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
representations
thatcapturethe
participating
entitiesandtheir
relations
andpopulation
requirements
Concept and event
detection from
multimedia
Dynamic texture
recognition
Classify video
samples as critical
ornot
• WP2user
requirements
• WP4modules
• KBservice
Object detection in
video frames and
images
Detect persons and
cars within video
andimagefiles
• WP2user
requirements
• Dynamic
texture
recognition
component
• WP4modules
• KBservice
Traffic level
classification
Determine the
traffic level of a
videoorimagefile
• WP2user
requirements
• Dynamic
texture
recognitionand
object
detection
components
• WP4modules
Spatio-temporal
localization of fire,
smoke and flood
incidents
Localize the
existence of critical
event in a spatio-
temporal manner
insidevideofiles
• WP2user
requirements
• Dynamic
texture
recognition
component
• KBservice
Automatic speech
recognition
Baselinesystem ASRtrainedon
general-domain
data
N/A
Domain-adapted
system
ASRadaptedforthe
use-casedomains
andtunedbyin-
domaindata
Collectedcorpora
forthedefineduse-
casedomains
Table12:WP3activitytable
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.1.6 Timelineanddependencyfromothermodules
ACTIVITY Y1 Y2 Y3
WP3 D3.2
D3.3D3.1 D3.4
Crisisclassification Earlywarning Severitylevelmonitoring Multilingualtextanalysis Conceptandconceptualrelationextractionv1 Conceptandconceptualrelationextractionv2 Conceptandeventdetectionfrommultimedia Dynamictexturerecognitionv1 Dynamictexturerecognitionv2 Objectdetectionv1 Objectdetectionv2 Trafficlevelclassificationv1 Trafficlevelclassificationv2 Spatio-temporallocalizationv1 Spatio-temporallocalizationv2 Automaticspeechrecognition Baselinesystem Domain-adaptedsystem
Table13:WP3timeline
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.2 Aggregation and semantic integration of emergency information fordecisionsupportandearlywarningsgeneration(WP4)
WP4addressesthecollection,aggregationandsemantic integrationofcontentrelevanttoemergencyinformationinordertofacilitatedecisionsupportandearlywarningsgeneration.This is accomplished through: i) the social media monitoring module, ii) the moduleresponsibleformonitoringmachinesourcinginformationfromIoTandM2Mplatforms,andiii)thesemanticrepresentationandreasoningmodule.
3.2.1 SocialMediaMonitoringmodule
TheaimofthesocialmediamonitoringmoduleistocollectpostsfromTwitterthatappeartoberelevanttothethreemainpilots,i.e.floods,fire,andheatwave.Thecrawlingprocessneeds tobe real-timeandefficient, able tohandle large streamsofdata, especiallywhenkeywords such as “fire” have multiple meanings. The module collects tweets in English,Greek, Italian, Spanish, and Danish, that are published by any citizen, civil protectionorganisationoronlinenewswebsites.
InordertogainaccesstoTwitter’sglobalstreamofdata,wehaveexploitedtheStreamingAPIs9, a streaming client that receives tweets themoment that they occur. Compared toTwitter’sRESTAPIs10 ,thisoptionoffersareal-timestreamoftweets insteadofconstantlymakingrequestsandthusoverridesanyratelimiting,i.e.maximumnumberofrequests.TheonlylimitationwhenusingtheStreamingAPIsisthateachaccountisallowedtocreateonlyonestandingconnection.
There are various streaming endpoints that can be divided into the following categories:Public streams, User streams, and Site streams. In our case, the “POST statuses/filter”endpoint of public streams is the most suitable, since it focuses on public data flowingthroughTwitterthatmatchesoneormorefilterpredicates.Specifically,the“track”fieldcanbeusedtodefineupto400searchkeywords,combinedwithanORoperator,sothattheAPIwillreturntweetsmatchinganyofthesekeywords.
Figure2:AllocationofTwitterpoststoitsproperdatacollection
9 https://dev.twitter.com/streaming/overview 10 https://dev.twitter.com/rest/public
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
To consume Twitter’s Streaming API, we chose to adopt the Hosebird Client (hbc)11, anopen-sourceandeasy-to-use JavaHTTPclient.A requiredparameter is theuseraccount’scredentials, while an optional parameter is the track keywords. For each pilot and eachlanguage we sustain separate collections in a MongoDB database, not only to store thecrawledtweets,butalsotokeepacollectionofrelevantkeywords.Bycommunicatingwiththesecollectionsweareable todefinea setofwordsanduse themas track terms.Afterconnection with the Twitter API is established, every time a new tweet is retrieved, weexaminewhich of the keywords exists in the tweet’s text. In this waywe canmatch thetweet to the corresponding languageandpilot (e.g. “inundación”matches to Spanishandfloods),andtheninsertittotherespectivedatabase,maintainingthestructureprovidedbytheAPI,sincetheJSONformatfitswellforMongoDBdatabasesstructures.
Aservice iscreatedtoclassifyallpostsasrelevantor irrelevant,soonlytherelevantonesproceed to the beAWARE analysis component, aiming mainly to extract locations and todetect key events. The training of the classificationmodel is based on user feedback, ascollected from our dedicated interface that demonstrates all social media collections,offeringtheannotationoptionasrelevant/irrelevant,whichisstoredasabinaryattributeinMongoDB.
Figure3:Interfaceforclassifyingpostsasrelevant/irrelevant
11 https://github.com/twitter/hbc
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Theclassificationservicecollectsthestoredannotatedpostseverymidnight(00:00GMT+2)toupdatethetrainingset.TheupdatedtrainingsetisusedtoassignanestimatedrelevancescoretosendonlytherelevantTwitterpostsforfurtheranalysis.Theclassificationisbasedonopen-sourcecode,whichisalsoavailableasalibraryinR(RTextTools12),incombinationwiththetm13library.
OnceanewTwitterpost is collectedand identified as relevant, amessage is createdandpublishedtothecommunicationbusandallsubscriberscanaccessthemarkedTwitterpostsdirectlyfromtheMongoDBdatabase.
Theoverallinput,output,dependenciesandcriticalfactorsarelistedinTable14.
Input Twitter API, Streaming API, relevant keywords for each languageanduse-casescenario
Output RelevantTwitterposts
Programminglanguages Java,R
Dependencies ConceptextractionmoduleandmainlyTask3.2.
CriticalFactors The percentage of relevant to irrelevant Twitter posts; the totalamountofcollectedposts
Table14:Socialmediamonitoringmodulesummary
3.2.2 MonitoringmachinesourcinginformationfromIoTandM2Mplatformsmodule
Sensordataiscrucialfortrackingtheonsetandprogressofacrisis.Thereisalargevariationinsensorsandanalmostequallylargevariationininterfacestoaccessthedatafromthosesensors. The aimof thismodule is to collect time-series sensor data from various on-linesensors and make this sensor data, and the sensor metadata, available through astandardisedinterface.
Amodern, RESTful interface for accessing time-series sensor data and sensormetadata isTheOGCSensorThingsAPI14. Itspecifiesadatamodel,a JSONdataformatfortransferringthe data, and a RESTful interface for accessing the data. The datamodel is based on theISO/OGC Observation and Measurement (O&M) model. The data format and RESTfulinterfaceisbasedontheOASISODataVersion4.0specification.SeveralimplementationsoftheSensorThingsAPIexist,bothopen-andclosed-source.
Thesensordatawillbe fed into thesystemthroughdatawrappers thatmediatebetweenthe (oftenproprietary) interfaceof the sensor and the SensorThingsAPI. Themodulewillcontain an extension for setting thresholds and for sending notifications through thecommunicationbus(WP7)whenthresholdsarepassed.
12 https://cran.r-project.org/web/packages/RTextTools/index.html 13 https://cran.r-project.org/web/packages/tm/index.html 14 http://docs.opengeospatial.org/is/15-078r6/15-078r6.html
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Input Time-seriessensordatainvariousformats
Output Time-series sensordataandmetadata in JSON format, conformingtotheOGCSensorThingsAPIspecifications
Programminglanguages Java,PLSQL
Dependencies • Modulessupplyingsensordata(WP2,WP7)• Modulesaccessingsensordata(WP3,WP6,WP7)• Communicationbus(WP7)
CriticalFactors Accesstoon-linesensordata
Table15:MonitoringmachinesourcinginformationfromIoTandM2Mplatformsmodulesummary
3.2.3 Semanticrepresentationandreasoningmodule
The semantic representationand reasoningmodule consistsof the followingcomponents:(a)thebeAWAREKnowledgeBase (KB),alsoreferredtoas“ontology”,(b)theKBService,(c) the semantic enrichment and reasoning framework. More information on thesecomponentsisgiveninthefollowingsubsections.
SemanticKBcomponent
ThesemanticKB,orontology,constitutesthecoremeansforsemanticallyrepresentingthepertinentknowledgeandforsupportingdecision-making.Basedonawell-definedformalism(OWL–WebOntologyLanguage),thebeAWAREontologywillencompass,amongstothers,information regarding domain knowledge (types of crises, risks and impacts), multimodalinput (image, video, text and speech) and contextual information, climate andenvironmentalconditions,geolocations,aspectsrelevanttoeventsandtime.
Typicalconstructsstoredinanontologycontaintheclassesrepresentingthemainentitiesinthedomain,the instantiationsoftheseclasses(i.e.objects)andtherelationsbetweentheentities. Specifically, for thebeAWAREontology, the storednotions and interrelationshipswill depend on the output of the requirements analysis activities within WP2, and mostnotablyonD2.1,deliveredinM5.Thecontentoftheontologywillbeupdatedinlaterstagesin the project lifetime, according to more up-to-date needs arising from the pilotdeployments.
The design and development of theontologywillfollowawell-knownontologyengineering methodology, called “NeOnmethodology”,whichisextremelysuitablefor collaborative ontology design andauthoring (i.e. twobeAWAREpartnersareinvolved in developing the ontology,CERTH and IOSB). The actual deploymentof the ontology will rely on open-sourceestablished software tools: Protégé (v.5+) ontology editor for authoring the ontology,GraphDBorWebGenesistriplestoreservingastheontologyrepository.
Inordertoconformtoamoremodularapproach, thebeAWAREontologywillconsistofaset of interconnected sub-ontologies, one per class of crises (flood, fire, heatwave).
Figure4:beAWAREontologynetwork
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Additionally, existing standards and ontologies will be adapted or extended according tobeAWAREneeds.
Afterthebasicschemaoftheontology is finalised,the inputtotheontologywillcome(inthe formof instances) fromvariousotherbeAWAREcomponents, likee.g. thecomponentextractingconceptsandconceptualrelationsfromtext(T3.2),orthecomponentretrievingconcepts and events frommultimedia (T3.3). Sincewe are expectingmassive volumes ofinstancestobeaddedintotheontologyinthecaseofacrisisevent,thechoiceofascalableontologyrepositoryisofutmostimportance.
Input TheKBsimplystoresinformation–inputandoutputarehandledbytheKBservice(seenextsubsection).Output
Ontologylanguage OWL2
Dependencies Ontologyhasdependencieswith:
• WP2userrequirements;• KnowledgeextractedfromWP3andWP4modules;• WP5modules,whichwillretrieveinformationfromtheKB.
CriticalFactors • Inefficient communicationwith use case partners on themostrelevantnotionstobestoredintheKB.
• Scalabilityoftheontologyrepository.
Table16:SemanticKBcomponentsummary
KBServicecomponent
TheKBServiceisresponsibleforaccessingandupdatingtheontologycontent,byprovidingaRESTFulAPIservice.CallstotheAPIfromend-userswillbetranslatedtoappropriateSPARQL1.1 queries, which will then be submitted to the GraphDB triple store maintaining theontology.Thus, thiscomponent is responsible for theontology’ssemantic integration, i.e.semantically integrating information that is the output from other modules into theontology.
Other aspects thatwill be investigated (and potentially added to the KB Service) include:ontologypopulationandontologyenrichment.Theformerprocessinvolvestheadditionofobjects/instances into the ontology, while semantic enrichment refers to the process ofaugmenting the semantics of anontologyby establishing links to external sources andbyappendingnewknowledge retrieved fromthosesources. It is imperative that theexternalthird-partyknowledgesourcesservedatainanappropriateformat(i.e.asRDFLinkedData),thuswewillconsiderknowledgesourcessuchasDBpedia,GeonamesandFreebase.
Input Select/Updatequeriesfromothercomponents.
Output Responsecontainingtheresultsetofthe‘Select’query.Inthecaseof ‘Update’ queries, the response will be the number of triplesaddedto/removedfromtheontology.
Programminglanguages Any(RESTfulAPIsarelanguage-independent).
Dependencies • CommunicationBus(WP7);• ModulesaccessingtheKBService(throughtheBus):WP3,WP4,
WP5modules.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
CriticalFactors • Concurrencyoftransactionstotriplestore.• Scalabilityoftheontologyrepository.
Table17:KBservicecomponentsummary
SemanticReasoningcomponent
This component is responsible for performing semantic reasoning on the ontology,whichrefers to the process of inferring implicit knowledge from the explicitly asserted factsresidingintheontology.Thereasoningmechanismswillsupportsophisticatedinterpretationtasksrelevanttothemanagementofmultimodalincominginformationandtotheretrievalofinformationpertinenttotheusers’needs.
AcriticalissueforbeAWAREinvolveshandlinguncertaininformation.Forthispoint,wewillrelyonfuzzyand/ornon-monotonicreasoningapproaches,inordertocopewithincompleteand inconsistent information and to resolve conflicts and prioritize the proposed actions.Existingreasoningengineswillbethebaselineforthesemanticreasoningactivityandwillbeeffectivelyextended,inordertomitigatetheircurrentlimitations,likee.g.scalabilityissues,non-seamlessintegrationwithontologies(inthecaseofuncertaintyreasoningengines)andmoreimplementation-specificlimitations.
Input Asetoffacts(inRDF)relevanttothequeryfromtheuser.
Output A graph of query-relevant facts extracted from the triple store.Relevantinformationwillbeencodedinthegraph.
Programminglanguages Javaand/orPython
Dependencies • OntologyandKBServicefromWP4;• Use case needs and requirements from WP2 with respect to
datatypesandreasoning.
CriticalFactors • The accuracy of this service is crucial to the quality of usersupporting information. Flaws/errors in the reasoning andinferenceproceduresmightproducesub-optimalresults.
• The size of the knowledge base might be too large for thereasonertohandleefficiently.
• The lack of specificity can lead to poor results with thiscomponent.
• Uncertaintyhandlingshouldbemeaningfulandnottrivial.
Table18:Semanticreasoningcomponentsummary
3.2.4 ActivitytableandworkloadActivity Subactivity Description Dependencies
SocialMedia
SocialmediacrawlingCollect social mediainformation from socialmedia(real-time)
• TwitterStreamingAPI
Classification of socialmediaposts
Classify the collectedsocial media posts asrelevantorirrelevant
• WP2 user requirementsfor annotating a trainingsetofTwitterposts
Event detection andlocalisation
Detect locations in rawtextfromsocialmediaandclusterpostsbylocation
• Task 3.2 (conceptdetection from textualinformation)
Sensordata Sensordataintegration Mediatingbetweensensor • WP2Userrequirements
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
interfaceandtheSensorThingsAPI
andSensordatasources
Thresholddetection Implementingthresholddetectionandnotification • WP7Communicationbus
SemanticKB
Ontology specification&conceptualization
Designtheontology,usingrequirements extractionand conceptualizationtechniques(e.g.diagrams)
• WP2userrequirements• WP5modules,whichwill
retrieveinformationfromtheKB
Ontology formalization&implementation
Formalize the ontologyusing an appropriateontologylanguage
• WP2userrequirements• WP5modules,whichwill
retrieveinformationfromtheKB
Ontology mapping andalignment
Establish links to othervocabularies/ontologies
• Knowledge extractedfrom WP3 and WP4modules
KBService
Investigate semanticintegrationtechniques
Examine approaches forsemanticintegration N/A
KBServicev1 Integrateinv1operationalprototype
• Communication Bus(WP7)
• ModulesaccessingtheKBService:WP3,WP4,WP5modules
KBServicev2 Integrateinv2operationalprototype
SemanticReasoning
Investigate uncertainty&scalablereasoning
Examine relevantapproaches N/A
Implement uncertaintyreasoningv1
Integrateinv1operationalprototype
• Ontology and KB ServicefromWP4
• Use case needs andrequirementsfromWP2
Implement uncertaintyreasoningv2
Integrateinv2operationalprototype
Integrate scalablereasoningv1
Integrateinv1operationalprototype
• Ontology and KB ServicefromWP4
• Use case needs andrequirementsfromWP2
Integrate scalablereasoningv2
Integrateinv2operationalprototype
Table19:WP4activitytable
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.2.5 Timelineanddependencyfromothermodules
ACTIVITY Y1 Y2 Y3
WP4
D4.1
D4.2 D4.3
Socialmediamonitoring Socialmediacrawling Classificationofsocialmediaposts Eventdetectionandlocalisation Sensordataintegration SemanticKB(ontology) Ontologyspecification&conceptualization Ontologyformalization&implementation Ontology mapping and alignment with othervocabularies
KBService Investigate semantic integration techniques formultimodalinput
ImplementKBServicev1 ImplementKBServicev2 SemanticReasoning Investigateuncertainty&scalablereasoning Implementuncertaintyreasoningframeworkv1 Implementuncertaintyreasoningframeworkv2 Integratescalablereasoningtechniquesv1 Integratescalablereasoningtechniquesv2
Table20:WP4timeline
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.3 Multilingualreportgeneration(WP5)WP5 addresses the generation of the emergency reports andmessages that need to (orshould) be communicated to the different types of stakeholders that beAWARE considers(authorities, first responders, citizens,etc.)duringanemergency inorder toprovide themwithtailoredsupport.Itaccomplishesthisthroughthefollowingtwomodules.
3.3.1 Textplanningmodule
Thetextplanningmoduledealswiththeselectionofcontentfromthesemanticrepository(KB) and the creation of a discourse plan for the reports and messages that are to begenerated. It serves as the first step in the beAWARE emergency report and messagegenerationpipeline,anditisresponsiblefortailoringcontentsselectionandtheirstructuringtotheinformationneedspertinenttothespecifictargetusergroupandcontext.
Input • RDFtriplesobtainedviaSELECTqueriesfromtheKB• Targetedusergroup (e.g.authorities, first responders,citizens,
etc.), with the possibility for further potentially relevantinformation(e.g. filters) fromthetriggeringmodules (semanticreasoningandPSAP)
Output PartiallyorderedsequenceoftheselectedRDFtriples
Programminglanguages/tools
Java,BabelNetsynsetannotatedWikipediadump
Dependencies • Modules triggering report generation, namely semanticreasoningandPSAP
• Domain knowledge modelling, as it affects the selection anddiscoursestructuringcriteria
• Specification of the information needs of the different usergroupsaddressed
CriticalFactors • Scalabilityofcontentselectionalgorithm• Update effectively with respect to what has been
communicatedpreviously• The richer the semantic domainmodel, themore changes for
coherentcontentselectionanddiscourseplanning
Table21:Textplanningmodulesummary
3.3.2 Multilinguallinguisticgenerationmodule
The multilingual linguistic generation module deals with the verbalization of emergencyreportsinthelanguageofendusergroupstargetedinthebeAWAREpilots.Ittakesasinputthe abstract (conceptual) representations produced by the text planning module andsuccessivelyproducesallthelayersforeseenbytheMeaning-TextTheorythroughapipelineofgraphtransducersandclassifiers.
Input RDFtriplesasselectedbythetextplanningmodule
Output Naturallanguagereportsandmessagestobeshowntotheinvolvedstakeholders(authorities,firstresponders,citizens,etc.)
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Programminglanguages/tools
Java,JenaAPI,Matetools
Dependencies • Textplanningmoduleperformance• User partner’s specifications about the desired/appropriate
language style for the different types of generatedreports/messagesintheconsideredpilotcontexts
CriticalFactors Flexible projection of RDF constructs to predicate-argumentstructuresthataresuitableforlinguisticgeneration
Table22:Multilinguallinguisticgenerationmodulesummary
3.3.3 ActivitytableandworkloadActivity Subactivity Description DependenciesTextplanning Contentselection Selectrelevant
contentsformtheKB,uponpertinentsystem/userrequest
• Semanticreasoning/PSAPtriggersforcontentselection
• Expressivityofreferencedomainontology
• Userpartnerdelineatedcriteriaforassessingrelevance/importanceofthecontentstobeincluded
Discoursestructure Arrange selectedcontents in acoherentway
• Contentselectionperformance
• Expressivityofreferencedomainontology
Multilinguallinguisticgeneration
Mappingfromconceptualrepresentationstolinguisticsemanticstructures
Projectionofontologicalrepresentationstolinguisticsemanticstructures
• Textplanningcompleteness• Underlyingsemanticsof
referencedomainontology
Mapping fromlinguistic semanticrepresentations tosurface-syntacticones
Projection oflinguistic semanticstructures tosyntacticones
N/A
Linearisation &morphologicalrealisation
Projection oflinguistic syntacticstructures tonatural languagetext
N/A
Table23:WP5activitytable
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.3.4 Timelineanddependencyfromothermodules
ACTIVITY Y1 Y2 Y3
WP5
D5.1
D5.2 D5.3
Emergencyreportgenerationspecificationsandrequirements
Textplanning
Contentselection&discourseplanningv1
Contentselection&discourseplanningv2
Multilinguallinguisticgeneration
ProjectionofconceptualreprensetationstoNLtextv1
ProjectionofconceptualrepresentationtoNLtextv2
Table24:WP5timeline
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.4 Main Public Safety Answering Point for emergency multimediaenrichedcalls(WP6)
TheobjectivesofWP6aretodevelopaunifiedplatformdeployedinpublicsafetyanswering
points (PSAP) for efficient emergency incidents management through the provision of a
commonoperationalpictureandimprovedsituationalawareness,basedon4mainpillars:
1. Collectingandcorrelatingmultimodaleventscomingfromdisparatedatasources;
2. Videomanagement;
3. GeographicalInformationSystem(GIS)analysis;
4. Incidentandresourcemanagement.
One of the main objectives of this WP is the design and development of an advanced
presentationlayerbasedoncuttingedgeGIS,analyticandvisualizationtechniques.Thiswill
include research on novel interaction techniques and investigation of new presentation
conceptsindataanalysis.
PSAPhasathree-tiertechnologicalarchitectureasshowninFigure5:
• FrontEnd–DesktopandWebClients,endpointsecurity.
• BackEnd–DesktopandWebServices,Inbound/OutboundCommunicationServices,
ServerSecurity(includingClientAuthenticationServices).
• Infrastructure–ArcGISGeographicalInformationServices,IBMmessagingservices.
Figure5:PSAPTechnologicalArchitecture
3.4.1 PSAPcapabilities
ThefollowingcapabilitiesareplannedaspartofthePSAPfunctionality:
Pre-EmergencyDecision-SupportingRiskVisualizationPSAP shall display pre-emergency risk assessment and crisis classification to the decision
makers.
Input Risk assessment, Crisis Classification, Alerts,
Position-based metrics, Analyzed video and
images,analyzedsensorreadingreports
Sources: Flood Risk Analysis
Services, Crisis Classification
Services, Video Analytics,
Social Media Analytics,
SensorAnalytics
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Output Risk display, decision supporting information
display,geo-basedinformationlayerdisplay
Videoplayback,Imagedisplay
Riskindicatorandmetriccharts
Recipients: Decision Makers,
Emergency Managers,
EmergencyAnalyst
Programminglanguages/tools
N/A
Components DSS,Front-End,Back-EndServices,GIS
Dependencies Flood Risk Analysis Services, Crisis Classification Services, Video Analytics,
SocialMediaAnalytics,SensorAnalytics,MessageBus
CriticalFactors FloodRiskAnalysisServices,CrisisClassificationServices,OutcomesofD6.1
Table25:Pre-EmergencyDecision-SupportingRiskVisualizationsummary
EmergencyIncidentCollectionandDisplayPSAP shall collect and display emergency incident information to the emergency control
centeroperators.
Input Incident Sources:VideoAnalytics,
SocialMediaAnalytics,
Generalpublic,First
responders,LocalPolice/
Calltakingservice
Output Geo-basedincidentdisplay
Incidentrecorddisplay
Recipients:
EmergencyManagers,
ControlCenterOperators
Programminglanguages/tools
N/A
Components Front-End,Back-End,GIS
Dependencies VideoAnalytics,SocialMediaAnalytics,FirstResponder(FR)MobileApp,Public
MobileApp,Calltakingservice,ExternalIncidentDataProvider,MessageBus
CriticalFactors N/A
Table26:EmergencyIncidentCollectionandDisplaysummary
FirstResponderPositionCollectionandDisplayPSAPshallcollectanddisplay first responderteampositionsandstatus informationtothe
emergencycontrolcenteroperators.
Input FirstResponderPosition Sources:FRMobileApp
Output Geo-basedworkforcepositiondisplay
Workforceinformationdisplay
Recipients:
EmergencyManagers,
ControlCenterOperators
Programminglanguages/tools
N/A
Components Front-End,Back-End,GIS
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Dependencies FRMobileApp,MessageBus
CriticalFactors FRMobileApppositionsending
Table27:FirstResponderPositionCollectionandDisplaysummary
IncidentAssignmenttoFirstResponderPSAP shall allow assigning incidents to first responder teams and incident information
distributiontothefirstrespondersbytheemergencycontrolcenteroperators.
Input Incidentassignmenttoworkforce Sources:ControlCenter
Operator
Output Incidentinformation(positionanddetails) Recipients:
Firstresponders(withFR
MobileApp)
Programminglanguages/tools
N/A
Components Front-End,Back-End
Dependencies FRMobileApp,MessageBus
CriticalFactors FRMobileAppTaskReceptionInterface
Table28:IncidentAssignmenttoFirstRespondersummary
PublicAlertPSAP shall allow sendingpublic alerts regarding incidents and general risk assessments to
citizenswhohavethePublicAppontheirmobiledevice.
Input PublicAlert,incidentcue Sources:ControlCenter
Operator
Output PublicAlertMessage Recipients:
Citizen(withPublicMobile
App)
Programminglanguages/tools
N/A
Components Front-End,Back-End
Dependencies PublicMobileApp,MessageBus,AlertTranscripts
CriticalFactors N/A
Table29:PublicAlertsummary
IncidentManagementPSAP shall receive and display incident information, status, and footage from first
respondersinthefieldorbystanders(citizens)whowillprovidetheinformationandfootage
fromtheirmobiledeviceandFRMobileapp.
Input Incidentinformation,IncidentFootage(video,
stills)
Sources:FRMobileApp,Public
MobileApp
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
Output Incidentinformationdisplay
Incidentlifecyclemanagement
On-mapincidentinformationdisplay
Videoplayback,Imagedisplay
Recipients:
ControlCenterOperator
Programminglanguages/tools
N/A
Components Front-End,Back-End,GIS
Dependencies PublicMobileApp,FRMobileApp,MessageBus
CriticalFactors N/A
Table30:IncidentManagementsummary
3.4.2 ActivitytableandworkloadActivity Subactivity Description Dependencies
Main Public
SafetyAnswering
Point for
emergency
multimedia
enrichedcalls
Pre-Emergency
Decision-
SupportingRisk
Visualization
Display pre-emergency risk
assessment and crisis
classification to the
decisionmakers
FloodRiskAnalysis Services, Crisis
Classification Services, Video
Analytics, Social Media Analytics,
SensorAnalytics,MessageBus
Emergency
Incident
Collection and
Display
Collect and display
emergency incident
information to the
emergency control center
operators
Video Analytics, Social Media
Analytics, FR Mobile App, Public
Mobile App, Calltaking service,
External Incident Data Provider,
MessageBus
FirstResponder
Position
Collection and
Display
Collect and display first
responder team positions
and status information to
the emergency control
centeroperators
FRMobileApp,MessageBus
Incident
Assignment to
FirstResponder
Assign incidents to first
responder teams and
incident information
distribution to the first
responders by the
emergency control center
operators
FRMobileApp,MessageBus
PublicAlert Sendpublicalertsregarding
incidents and general risk
assessments to citizens
whohavethePublicMobile
Appontheirmobiledevice
Public Mobile App, Message Bus,
AlertTranscripts
Incident
Management
Receive and display
incidentinformation,status
and footage from first
responders in the field or
bystanders (citizen) who
will provide the
information and footage
from their mobile device
PublicMobileApp,FRMobileApp,
MessageBus
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
andFRMobileapp
Table31:WP6activitytable
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.4.3 Timelineanddependencyfromothermodules
ACTIVITY Y1 Y2 Y3
WP6
D6.1
D6.2
D6.3 D6.4
Pre-emergency decision-supporting riskvisualization
Researchandspecification Designanddevelopment Deployment,integration,demonstration Emergencyincidentcollectionanddisplay Designanddevelopment Deployment,integration,demonstration Firstresponderpositioncollectionanddisplay Designanddevelopment Deployment,integration,demonstration IncidentAssignmenttoFirstResponder Designanddevelopment Deployment,integration,demonstration PublicAlert Designanddevelopment Deployment,integration,demonstration IncidentManagement Designanddevelopment Deployment,integration,demonstration
Table32:WP6timeline
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.5 Systemdevelopment,integrationandevaluation(WP7)Due to the distributed approach of the design and implementation of the beAWAREplatform,inwhichdifferentpartnersmaintainownershipoverdifferentcomponentsofthesystem,combinedwiththecomplexityoftheplatform,whichiscomprisedofmanydifferentcomponentswe opted to follow amicro-services approach tomake the entire process ofdesign,implementation,andintegrationmoremanageable,inadistributedmanner
Using thisapproach,wemaintain the independenceof thedifferentcomponents,and theintegrationfocusisontheexposedcapabilitiesofeachcomponent.Theintegrationbetweencomponents isbeingrealizedvia twomainmechanisms, first, inter-communicationvia theplatformcommunicationservicebus,andsecondthroughexposedRESTinterfacesofvariouscomponents,potentiallyaidedbyadiscoveryservice.
Micro-servicesisanarchitectureformandmethodologyforbreakingupalargeandcomplexsystemintosmallunits,eachfulfillingauniquewell-definedtask,inanindependentmanner.Eachsuchmicro-serviceisdeployedseparatelyandcaninteractwithitspeermicro-servicesusing standard communication protocols. Such an approach eases the task of long termmaintenanceandevolutionofalargesystem,comparedtoamonolithicsystem.Inaddition,internal changeswithin amicro-service do not influence any other system component aslongastheexternalcontractofthemicro-serviceisadheredto.Moreover,eachcomponentcanbeimplementedinadifferentprogramminglanguage,usingdifferentmiddleware.
Asmentionedearlier,therearetwomainmechanismsformicro-servicestointeract,namely,thecommunicationservicebusandaREST interface(possiblywiththehelpofadiscoveryservice).Forcommunicatingthroughthecommunicationbusthecomponentsneedonlytoagree on the topic via which they will be interacting and the format of the messagespublishedonthattopic.ForcommunicatingviaaRESTinterface,thereneedstobeawayforone micro-service to find another micro-service it wishes to invoke. For that purpose, aservice discovery component may be deployed. Such a component serves as a centralregistry of availablemicro-services, responding to queries about the location of a certainmicro-service. In actual deployments, this capability can be provided by packages such asNetflixEureka,amalgam8,orConsul.
Additional helping capabilities that may be employed in our environment consists of agateway,healthmonitoring,andlogging(ELKstack).
3.5.1 Twelve-FactorApplications15
Theplatformwillbecomposedofmultiplemicro-servicesandaspirestoseamlesslydeliverservicestoitsusers,thusweareencouragedtousethefollowingguidelines:
1. Codebase
Maintainaone-to-onerelationshipbetweencodebaseandtheapplication(onecodebasemultipledeploys).
15 https://12factor.net/
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
2. Dependencies
Theyshouldnotrelyonsystem-widepackagesorfunctions.Dependenciesmustbedeclaredinsidethescopeoftheapplication
3. Configuration
Separationbetweenconfigurationandcode,asconfigurationvariesacrossdeployments.
4. Back-endServices
Amicro-serviceshouldmakenodistinctionbetweenlocalandthirdpartyservices.
5. Build,release,run
Separatebetweenbuild,release,andrunstages.
6. Processes
Stateless.Anypersistentdataisstoredusingexternalservices.
7. Portbinding
Applicationshouldbestandalone,ratherthanrelyingonarunninginstanceofanapplicationserver.Servicesareprovidedtoexternalsviaacertainportboundtotheapplication.
8. Concurrency
Shouldeasilybescaledhorizontallyandhavingtheworkloaddistributedamongstmultipleinstancesofthesamemicro-service.
9. Disposability
Supportfailuresbyeasilybeingstartedandstopped.
10. Development/productionparity
Designedforcontinuousdeployment.Therefore,thedifferencebetweendevelopmentandproductionenvironmentsshouldalwaysbeminimal.
11. LogsProvideacontinuousstreamoflogginginformation,whichisretrievedbyaseparatelyconfiguredservice.
12. Adminprocesses
Runadmin/managementtasksasone-offprocesses,onanenvironmentsimilartoproduction.
3.5.2 Systemarchitecture
ThiswillinvolvethedefinitionoftheglobalarchitectureforthebeAWAREplatform,fromitshigh-levelcomponentdesigntotheserverlayoutdefinition.Aroadmapwillalsobedefined,todrivetheprocessofimplementation.
Dependencies User requirements, specification of pilot use cases and validationplan: the Use Cases will drive the processes and ultimately thearchitecture will be built to service those use cases, so a cleardefinitionisessential.
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
CriticalFactors • IncompleteUseCasedefinition:UCsmustbeclearlydefinedandwell understood to ensure the appropriate systems, processesand capabilities are put in place in the architecture.UCsmustincludecomprehensivescenariosandvalidationplanstoensurethearchitectureisbuiltcorrectlytospecifications.
• Incomplete service definition: each of the technicaldevelopmentWP is responsible fordefiningtheserviceAPI forcomponents related to its research. Failure to provide theAPIspecification in a timely and thorough manner can lead todelaysorerrorsindefinitionofthearchitecture.
Table33:Architecturedefinitionsummary
3.5.3 Technicalinfrastructure
This implies the provisioning and operation of the infrastructure, onwhich the beAWAREsystemwillrun.Thisincludestheinternalservices,businessservices,associatedrepositoriesandexternalentities(mobileapplications,controlcenters).
IteasilyfollowsthatsomesubsystemsofthebeAWAREplatformcannotbedeployedtotheplatform, due to licensing reasons. Othersmay be dependent on secondary systems thatcannot be easily replicated in a different environment, or may require concentratedcomputingpowerthat isprovidedbyahighlyspecializedexpertsysteminapartner’sdatacentre.Insuchcases,proxyserviceswillbebuiltbypartnersandexposedtotherestoftheplatform.Proxyserviceswilldelegateworktotheactualservicesanddoanyextraworkasrequiredinatransparentway.
Dependencies Systemarchitecture:technicalinfrastructurewillbeprovisionedtoimplementthesystemarchitecture.
CriticalFactors • Distributed infrastructure: parts of the infrastructure areforeseentobedistributedandincludesystemswhicharerunin-house by some partners. Issues with firewalls, authentication,etc.aretobeexpected,andacteduponasneeded.
• Performance: the scope and complexity of the beAWAREprocesses and the size of the data to be handled is not yetknown and is likely to evolve as research progresses.Performance problems may arise, and resizing and/orprovisioningofextracapacitymayberequired.
Table34:Infrastructuredefinitionsummary
3.5.4 Systemdevelopment
ThisisthetaskforalldevelopmentactivitiesrelatedtothetechnicalimplementationoftheUseCasesandanyotherworkrequiredforthecompletionoftheobjectives.
The system development will be iterative, from an initial dummy prototype to the finalversion,withthefollowingcycleplanned:
OperationalPrototype
Dummyend-to-endarchitecture;allservicedummiesinplace,operatingontest/mockdata.
FirstPrototype
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
UsingrealservicesfromWP3-WP6;FirstPrototypemilestone(MS3).
SecondPrototype
UsingrealservicesfromWP3-WP6;SecondPrototypemilestone(MS4).
FinalSystem
CompletebeAWAREplatform;FinalSystemmilestone(MS5).Dependencies • AlltechnicalWPservices
• WP2UseCasesandEvaluation
CriticalFactors • Changingrequirements:UseCasesshouldremainstableduringthe project. While minor changes are always to be expected,major breaking changes may cause throwing away work thathasalreadybeendoneandimpactondeliverycapabilities.
Table35:Systemdevelopmentsummary
3.5.5 Communicationbus
The communication bus serves as a central point of communication between differentsystem components. Its main mode of operation is that of publish / subscribe, whichsupports different parts of a composite application to be unaware of each other but stillmanagetocommunicateuponneed.Theonlyitemsthatneedtobeagreeduponbetweenapublisher and a subscriber is the name of the topic (channel) throughwhich theywill becommunicatingandtheformatofthemessagesflowingthroughthattopic.
Theproposedbusisinchargeofnotifyinginterestedandregisteredcomponentswhennewitems which are of interest to them have been received or calculated by anothercomponent. In addition, the bus may perform some light transformations on incominginformation,uponneed.
The communication bus will be configured, upon deployment, with the necessary set oftopics as agreed upon between the different components. In addition, the messagestructure of each message in each topic will be agreed upon and documented by thecooperatingcomponents.Thecommunicationbusneedstosupportthenumberofdifferenttopics required for a beAWARE installation, along with the associated aggregatedthroughputinalltopics.
ThecommunicationbusisrealizedbyusinganinstanceofaMessageHubservice,deployedin IBM’sBlueMixcloud.Theback-end isbasedonaKafkacluster,andthe interactionwiththeserviceisrealizedusingstandardKafkaclients.
Dependencies • Kafka–apopularopensourcemessagingplatform• MessageHub–aclouddeploymentbasedonKafka
CriticalFactors • Needstosupportthenumberoftopicsrequiredalongwiththeaggregated throughput. Requires cooperating components toagreeuponmessagesformatandabidebythem.
Table36:Communicationbussummary
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.5.6 End-usersapplications
Therearetwoend-userapplicationsformobiledevices(smartphonesortablets):oneusedby the first responders and one used by the public. These mobile applications willcommunicatewithabackendthatwillconnecttotherestofthebeAWAREsystem.
With these applications, the first responders can communicate with the PSAP, sendinformationabouttheemergencyevent, receivetasksandreportonthoseassignedtasks.Thepublicwillbeabletoreceiveinformationaboutemergencyeventsandsendinformationabout theevent to thePSAPusing the communicationbus.Both first responders and thepublicwillbeabletosendtext,image,videoandvocalinformation.
Dependencies • Communicationbus• Mobiledevicehardware(camera,voice,gps,gsm)
CriticalFactors • Badreceptiononthemobilenetwork• BadGPSreception
Table37:End-usersapplicationssummary
3.5.7 ActivitytableandworkloadActivity Subactivity Description Dependencies
Systemarchitecture
Technologicalroadmap
Currentdocument N/A
Systemrequirementsandarchitecture
DescriptionoftechnicalrequirementsderivedfromUseCasesanddetaileddesignofplatformarchitecture
WP2userrequirements
Technicalinfrastructure
N/A Provisioningandoperationoftheinfrastructure,onwhichthebeAWAREsystemwillrun
Systemarchitecture
Systemdevelopment
OperationalPrototype
Initialdummyprototype
WPs3-6
FirstPrototype FirstiterationofbeAWAREplatform
WPs3-6
SecondPrototype SeconditerationofbeAWAREplatform
WPs3-6
Finalsystem FinalversionofbeAWAREplatform
WPs3-6
Communicationbus
N/A Centralpointofcommunicationbetweendifferentsystem
• Kafka• MessageHub
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
components
End-usersapplications
N/A Mobileapplicationusedbyfirstrespondersandthegeneralpublic
• WP2userrequirements• Integratedsystembackend
(T7.2)• Communication
infrastructure(T7.4)
Table38:WP7activitytable
D7.1–V1.0
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 700475
3.5.8 Timelineanddependenciesfromothermodules
ACTIVITY Y1 Y2 Y3
WP7
D7.1
D7.2
D7.3 D7.4 D7.5
D7.6
D7.7
D7.8 D7.9
Systemarchitecture Technologicalroadmap Systemrequirementsandarchitecture Technicalinfrastructure Systemdevelopment OperationalPrototype FirstPrototype SecondPrototype Finalsystem Communicationbus End-usersapplications
Table39:WP7timeline
D7.1–V1.0
Page46
4 DevelopmentCycleandUseCases
Theoverall strategy for thedevelopmentof thebeAWAREplatform is tostartwithsimplescenarios and proceed stepwise towards the final system. The detailedwork plans of theindividualmodulespresentedinSection3willfollowthegeneralcycle:afterthecompletionofeachprototypeversion(timingdefinedbyMilestones),thefunctioningoftheprototypeisassessed, the needs for further development are identified and agreed upon, a detailedworkplanforthenextprototypeversionisfinalizedandthedevelopmentcycletowardsthenextprototypeisinitiated.Oneimportantpredefinedconceptforthedifferentprototypesisthedefinitionofthepracticalusecaseseachprototypeisserving.
4.1 Scenario1:FloodTargetgroup:
In each development cycle different user groups (target groups)will be involved in pilot-testinginareal-worldenvironmentandwithreal-worlddata:
• AAWApersonnel
• Decisionmakersinvolvedduringthefloodemergencies:intheC.O.C(theMunicipal
operativecentre):
o TheMayor
o TheheadoftheMunicipalgroupofVicenzaCivilProtection
o TheheadoftheNationalAssociationofCarabinieri
o TheheadoftheNationalAlpineTrooperAssociation
o ThecoordinatorofVoluntaryAssociationsofCivilProtection,ProvinceofVicenza
o TheheadoftheLocalItalianRedCross
o TheheadoftheVicenzaFireBrigades
o TheheadoftheVicenzaLocalPolice
• Citizens
• Firstresponders
• Researchcommunity
• SMEs
• FloodRiskManagementauthorityatnationalandinternationalscale
Objectives:beAWAREshould:
• Support the collection and visualization of spatially distributed and multi-sourcedinformationrelatedtoafloodemergency(floodreports,weatherforecasts, floodearlywarningsystemresults,elementsatrisk,extensionoffloodedareas,crisisclassificationbasedonallavailabledata).
D7.1–V1.0
Page47
• Enable the automatic detection of flood hazardous situations, such as river levelovertopping/breaking.
• Provideauthoritieswiththeabilitytomanagefirstresponderassignments.• Facilitate the communication between authorities and citizens, also in different
languages.Morespecifically,beAWAREshould:o Provideauthoritieswiththeabilitytowarnpeoplewithmessages,oncetheyare
approachingafloodedarea.o Allowcitizenstosendfloodreportswithtext,images,audioandvideo.
4.2 Scenario2:FiresTargetgroup:
Τhe target groups listed below are those who will use and interact with the beAWAREplatforminthephaseofpreparednessandresponseduringaforestfireemergency:
UsersInvolvedinFireUsecases
• Localentities
o CivilProtection-ValenciaCityCouncil:Volunteers
o LocalPolice-ValenciaCityCouncil
o LocalFirefighters:Professionalbody
o Devesa-AlbuferaService
• Localauthorities
o Mayor
o CityCouncilors
ProvincialEnd-UserInvolvedinFireUsecases
• Provincialentities:ValenciaProvincialFireConsortium
• Provincialauthorities:PresidentoftheProvincialCouncil
RegionalUsersInvolvedinFireUsecases
• EmergenciesRuralBrigades
• AirborneandHeliborneBrigades
• ForestFirePreventionServiceoftheDepartmentofAgriculture,Environment,Climate
changeandRuraldevelopment
• NaturalParkGuards
Healthservices
• CenterofCoordinationforEmergencyInformationandCoordination(CICU)
• UrgentMedicalAssistanceServiceUnits(SAMU)
D7.1–V1.0
Page48
• BasicLifeSupportUnits(SVB)
• NotAssistedTransport(TNA)
RegionalAuthorityinFireUsecases
• RegionalAuthority
• RegionalDirectorforPrevention,FireExtinctionandEmergencies
• ValencianSafetyandEmergencyResponseAgency(112-regionalPSAP)
NationalUsersInvolvedinFireUsecases
• GuardiaCivilTrafficGroup
• GuardiaCivilNatureProtectionService(SEPRONA)
• NationalPolice
• UME(militaryemergencyunit)
NationalFirstrespondersInvolvedinFireUsecases
• AircraftsoftheMinistryofEnvironment
Objectives:beAWAREshould:
• Sendinformationregardingpeopleindanger–wherearethey,howmany,howwilltheybeaffected–inordertooptimizetheresponseandpossibleevacuation.
• Provide visualization on incoming information (mobile apps, videos, calls, textmessages,sensors,socialmedia).
• Givetheabilitytomanagethetasksassignedtothefirstrespondersandtrackthesetasks, as well as personnel and material to allow appropriate mobilization andcoordinationofresources(watersupplyetc.).
• Provide information about the fire and weather conditions (development, flameheight,winddirection,droughtindexetc.).
• Provide information to the public (safe locations, safe evacuation directions/ways,warnings,forbiddenactivities/behaviors).
4.3 Scenario3:HeatwaveTargetgroup:
The target groups listed below are those, who will use and interact with the beAWAREplatforminthephaseofpreparednessandresponseduringaheatwaveemergency.Thesegroupsarecategorizedbasedontheirgeographicallevelofinvolvement.
Usersinvolvedinheatwavecasesinlocallevel
• MunicipalCivilProtection
• MunicipalSocialServices
• Mayor
D7.1–V1.0
Page49
• LocalFirefighters:Professionalbody
• NationalEmergencyAidCentre(EKAV)
• Hospitals
• Volunteerorganizations:Firstresponders
• Localtrafficpolice(incaseofatrafficjam)
Usersinvolvedinheatwavecasesinregionallevel
• RegionalDirectorateofFireDepartment
• RegionalCivilProtection
• RegionalHealthDirectorate
• RegionalGovernor
• RegionalPSAP(112,166,199)
Usersinvolvedinheatwavecasesinnationallevel
• NationalHealthOperationsCentre
• GeneralSecretariatforCivilProtection
• MinistryofHealth
• MinistryofforCitizenProtection
• MinistryofNationalDefense
Objectives:beAWAREshouldprovidethefollowingsupporttofirstrespondersanddecisionsmakers:
• Issueanalertonanimminentheatwaveinordertoinformauthoritiestotakeproactivemeasures.
• Provideanassessmentonfirerisk,theperiodduringandafteraheatwave.• Send information of where people are in danger in order to send rescue teams or
orderingevacuations/confinement,especiallyinthecaseswhereelderorsickpeopleareconfinedinhouseswithnoA/Corpeoplearetrappedinanelevator.
• Sendinformationandcreateanestimatebasedonpastevents,onhowmanypeopleareindangerandhowmanyare/couldbeaffectedfromtheheatwave.
• Visualizationonrelevant informationprovidedviamobileapps,calls, textmessages,aswellassocialmediastreams(socialmediamonitoring).
• Assigntaskstofirstrespondersandevaluatetheirdevelopmentinrealtime.• Monitorheatwavedevelopmentandtheweatherconditions.• Keepingtrackofpersonnel,volunteersandequipment/vehicles.• Allowingtheappropriatemobilizationofresources.• Monitortrafficconditionsinordertomobilizefirstrespondersmoreeffectively.• Monitor the level of occupancy in places of relief that are offered to general public
duringaheatwave.
D7.1–V1.0
Page50
beAWAREshouldalsoprovidethefollowingsupporttocitizensaffectedbytheheatwave:
• Sendinformationonplacesforrelief,e.g.wheretheyareandwhatistheleveloftheiroccupancyinrealtime,asmuchaspossible.
• Sendwarningstocitizensinordertoavoidinterferenceswithfirstresponders.• Informcitizensofbestpractices/behavioursduringaheatwave.• Warncitizensofanimminentheatwave.
D7.1–V1.0
Page51
5 ProjectTimelineandMilestones
Theplatformwillbebuilt incrementallyand iteratively, startingwithasystemmadeupofdummy services for formal end-to-end validation and delivering increasingly enrichedfunctionalityandfurthercapabilitiesoneachmilestone.
Thefigurebelowillustratesthetimelineforthetechnicalmilestonesintheevolutionofthesystem.
Figure6:beAWAREwalkingskeleton
D7.1–V1.0
Page52
6 Summary
In this deliverable, the technical roadmap of the beAWARE platformwas presented. Thisdocumentwillguidethedevelopmentof theprojectwithaviewtoattainingthescientificandthetechnicalobjectivesenvisaged.
However, since the project is following an iterative development procedure (use cases-requirements-development-evaluation),itisexpectedthatsmalladaptationsanddeviationsfrom the initial technical specifications and the module functionalities foreseen by thisdocumentwillbeneededtosatisfy the finaluserrequirements.Suchchanges/adaptationsmightberequiredatcomponentorsubcomponentlevel.Theplatformarchitecturetogetherwith the detailed specification of the modules (including any updates required) will bereportedinD7.2(Systemrequirementsandarchitecture).