INSIGHT: Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Heterogeneous Stream Processing and Crowdsourcing for.

Slides:



Advertisements
Similar presentations
Opportunistic Reasoning for the Semantic Web: Adapting Reasoning to the Environment Carlos Pedrinaci Tim Smithers and Amaia Bernaras.
Advertisements

GIS and BIM Integration: Business Level Framework
Event detection using ontologies CSIRO LAND AND WATER Jonathan Yu 13 Feb 2013.
anywhere and everywhere. omnipresent A sensor network is an infrastructure comprised of sensing (measuring), computing, and communication elements.
Improving Transportation Systems Dan Work Civil and Environmental Engineering, UC Berkeley Center for Information Technology Research in the Interest of.
Big Data Management and Analytics Introduction Spring 2015 Dr. Latifur Khan 1.
IBM TJ Watson Research Center © 2010 IBM Corporation – All Rights Reserved AFRL 2010 Anand Ranganathan Role of Stream Processing in Ad-Hoc Networks Where.
Probabilistic Aggregation in Distributed Networks Ling Huang, Ben Zhao, Anthony Joseph and John Kubiatowicz {hling, ravenben, adj,
Networks and Distributed Systems: Project Ideas
ATSN 2009 Towards an Extensible Agent-based Middleware for Sensor Networks and RFID Systems Dirk Bade University of Hamburg, Germany.
Integration and Insight Aren’t Simple Enough Laura Haas IBM Distinguished Engineer Director, Computer Science Almaden Research Center.
1 Research Profile Guoliang Xing Assistant Professor Department of Computer Science and Engineering Michigan State University.
Dunja Mladenić Marko Grobelnik Jožef Stefan Institute, Slovenia.
Streaming Data, Continuous Queries, and Adaptive Dataflow Michael Franklin UC Berkeley NRC June 2002.
Research Directions for the Internet of Things Supervised by: Dr. Nouh Sabry Presented by: Ahmed Mohamed Sayed.
PRIVACY, TRUST, and SECURITY Bharat Bhargava (moderator)
System Integration Management (SIM)
Adaptive Traffic Light Control with Wireless Sensor Networks Presented by Khaled Mohammed Ali Hassan.
New Challenges in Cloud Datacenter Monitoring and Management
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
BPM based robust e-business application development.
Machine Learning and Optimization For Traffic and Emergency Resource Management. Milos Hauskrecht Department of Computer Science University of Pittsburgh.
Atlas Pitu Mirchandani Professor and Director, ATLAS Research Center Systems and Industrial Engineering Department The University of Arizona, Tucson, Arizona.
MPlane – Building an Intelligent Measurement Plane for the Internet Maurizio Dusi – NEC Laboratories Europe NSF Workshop on perfSONAR.
A Research Agenda for Accelerating Adoption of Emerging Technologies in Complex Edge-to-Enterprise Systems Jay Ramanathan Rajiv Ramnath Co-Directors,
What is SMART NETWORK? SMART NETWORK is a centralized system providing intelligent communications, real-time data analysis and optimized management for.
Katanosh Morovat.   This concept is a formal approach for identifying the rules that encapsulate the structure, constraint, and control of the operation.
4.x Performance Technology drivers – Exascale systems will consist of complex configurations with a huge number of potentially heterogeneous components.
Javier Gil Arenales Data, a critical resource for Smarter cities.
Opening Keynote Presentation An Architecture for Intelligent Trading  Alessandro Petroni – Senior Principal Architect, Financial Services, TIBCO Software.
An approach to Intelligent Information Fusion in Sensor Saturated Urban Environments Charalampos Doulaverakis Centre for Research and Technology Hellas.
Ontology based approach for data management Ilkka Niskanen EuroSSC 2009 One Minute Madness Poster & Demos.
Dynafloat: Dynamic urban traffic flow management using floating car, planning, and infrastructure data Topconsortia voor Kennis & Innovatie (TKI) and NWO.
Experimenting with Complex Event Processing for Large Scale Internet Services Monitoring Stephan Grell, Olivier Nano Microsoft, Ritter Strasse 23, Aachen,
Dixie Regional ITS Architecture Project Summary July 31, 2006.
COMP 410 Update. The Problems Story Time! Describe the Hurricane Problem Do this with pictures, lots of people, a hurricane, trucks, medicine all disconnected.
Linked-data and the Internet of Things Payam Barnaghi Centre for Communication Systems Research University of Surrey March 2012.
Ontology Summit 2015 Track C Report-back Summit Synthesis Session 1, 19 Feb 2015.
The Fully Networked Car Geneva, 4-5 March Ubiquitous connectivity to improve urban mobility Hermann Meyer ERTICO.
Ch. 9. The Cloud of Things 1Ch. 9. CoT.  Current M2M/IoT solutions are focusing on communications and integration. Future Web of Things (WoT) evolution.
© 2010 IBM Corporation IBM Research - Ireland © 2014 IBM Corporation xStream Data Fusion for Transport Smarter Cities Technology Centre IBM Research.
Introduction Infrastructure for pervasive computing has many challenges: 1)pervasive computing is a large aspect which includes hardware side (mobile phones,portable.
Big Data Analytics Large-Scale Data Management Big Data Analytics Data Science and Analytics How to manage very large amounts of data and extract value.
Human Interaction with Data “Meaningful Interpretations” “The Power of Crowdsourcing” &
GeoSpatial and GeoTemporal Informatics for dynamic and complex systems May Yuan.
WP2001 CPA4 Towards Dependable and Survivable Systems and Infrastructures Baton holder ANDREA SERVIDA European Commission DG Information Society C-4
A Data Stream Publish/Subscribe Architecture with Self-adapting Queries Alasdair J G Gray and Werner Nutt School of Mathematical and Computer Sciences,
Kamruddin Md. Nur *, Mahmud Hasan # and Pranab Chandra Saha * * Department of Computer Science & Engineering, Stamford University Bangladesh # Department.
DRIVE Net: A Large-Scale Online Data Platform for Performance Analysis and Decision Support Yinhai Wang PacTrans STAR Lab University of Washington
CERN openlab technical workshop
Real Time Sensor Networks – challenges and solutions Information Prioritization Proposed scheme: Design techniques for priority assignment to an information.
Big traffic data processing framework for intelligent monitoring and recording systems 學生 : 賴弘偉 教授 : 許毅然 作者 : Yingjie Xia a, JinlongChen a,b,n, XindaiLu.
Integrated Corridor Management Initiative ITS JPO Lead: Mike Freitas Technical Lead: John Harding, Office of Transportation Management.
Forum on Internet of Things: Empowering the New Urban Agenda Geneva, Switzerland, 19 October 2015 Requirements and Architecture of Integrated Sensing and.
Slide no 1 Cognitive Systems in FP6 scope and focus Colette Maloney DG Information Society.
SOA & Event Driven Architecture Steve Else, Ph.D., Certified Enterprise Architect, SOA COP Srinidhi Boray, Certified Enterprise Architect, Ingine, Inc.
Cognitive & Organizational Challenges of Big Data in Cyber Defence. YALAVARTHI ANUSHA 1.
Cyberinfrastructure Overview of Demos Townsville, AU 28 – 31 March 2006 CREON/GLEON.
Internet of Things. Creating Our Future Together.
Efficient Opportunistic Sensing using Mobile Collaborative Platform MOSDEN.
Time Series Data Repository #ODSummit - The Generic, Extensible, and Elastic Data Repository in OpenDaylight for Advanced Analytics.
Big Data Quality Challenges for the Internet of Things (IoT) Vassilis Christophides INRIA Paris (MUSE team)
Real Time Event Processing Using Distributed Machine Learning in Urban Environments Nikos Stefanos Kostagiolas Computer Science Student at National Kapodistrian.
IoT Week, 2 nd June 2016Ralf Tönjes1 University of Applied Sciences Osnabrück Satelliten- und MobilfunkProf. Dr.-Ing. Ralf Tönjes1 Ralf Tönjes University.
Connected Infrastructure
Themes in Geosciences.
Connected Infrastructure
Big Data Young Lee BUS 550.
Big DATA.
Presentation transcript:

INSIGHT: Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management Alexander Artikis, Matthias Weidlich, Francois Schnitzler, Ioannis Boutsis, Thomas Liebig, Nico Piatkowski, Christian Bockermann, Katharina Morik, Vana Kalogeraki, Jakub Marecek, Avigdor Gal, Shie Mannor, Dermot Kinane and Dimitrios Gunopulos 1

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data  New technologies are creating a data revolution: – Sensor network deployments at large-scale. – Smart-phones as tools for data sensing, sharing and processing. – Social networks for disseminating news, advertisements and organizing social actions.  These technologies bring problems and challenges: – Heterogeneous data, different scales, noisy data, imperfect knowledge, massive data. – User centered focus, event understanding. – Specific Problem: Urban Traffic Management Big Data Challenge Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data INSIGHT  Objective 1: develop an adaptive, scalable and dependable, real-time infrastructure for improving our ability of coping with emergencies.  Objective 2: develop new methods for monitoring and analysing in real-time massive streams of heterogeneous data.  Objective 3: ensure reusability and facilitate faster adaptation of the proposed methodology. 3 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data INSIGHT Architecture 4 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Urban Traffic Management 5 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Complex Event Processing  Data variety problem: heterogeneous event sources  Buses: position, direction, route, congestion.  SCATS sensors: traffic flow, traffic density.  Solution: complex event processing  Compute bus punctuality, bus driving quality, traffic congestion (trends).  Event Calculus for Run-Time reasoning (RTEC)  Formal, declarative semantics.  Interval-based reasoning.  Highly efficient (for event hierarchies).  Machine learning support for automated construction of complex event patterns. 6 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Complex Event Processing Buses reporting congestion at some location (Lon, Lat) of interest: busCongestion(Lon, Lat) initiated iff move(Bus, Lon B, Lat B, 1) happens, close(Lon B, Lat B, Lon, Lat) busCongestion(Lon, Lat) terminated iff move(Bus, Lon B, Lat B, 0) happens, close(Lon B, Lat B, Lon, Lat) 7 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Complex Event Processing Identifying mismatches among different streams: disagree(Bus, Lon I, Lat I, 1) happens if move(Bus, Lon B, Lat B, 1) happens, close(Lon B, Lat B, Lon I, Lat I ), not (scatsCongestion(Lon I, Lat I )=true holds) disagree(Bus, Lon I, Lat I, 0) happens if move(Bus, Lon B, Lat B, 0) happens, close(Lon B, Lat B, Lon I, Lat I ), scatsCongestion(Lon I, Lat I )=true holds 8 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Complex Event Processing Dealing with event source disagreement: noisy(Bus)=true initiatedAt T iff disagree(Bus, Lon I, Lat I, BusVal) happensAt T, crowd(Lon I, Lat I, CrowdVal) happensAt T', BusVal <> CrowdVal, 0 < T'-T < threshold noisy(Bus)=true terminated if agree(Bus) happens noisy(Bus)=true terminatedAt T if disagree(Bus, Lon I, Lat I, BusVal) happensAt T, crowd(Lon I, Lat I, CrowdVal) happensAt T', BusVal=CrowdVal, 0 < T'-T < threshold 9 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Self-Adaptive Complex Event Processing Discarding temporarily unreliable event sources: busCongestion(Lon, Lat) initiated iff move(Bus, Lon B, Lat B, 1) happens, not (noisy(Bus) holds), close(Lon B, Lat B, Lon, Lat) busCongestion(Lon, Lat) terminated iff move(Bus, Lon B, Lat B, 0) happens, not (noisy(Bus) holds), close(Lon B, Lat B, Lon, Lat) 10 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Complex Event Processing in Dublin 11 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Crowdsourcing  Data veracity problem: Inaccurate measurements, network failures, interference of mediators.  Solution: Query human volunteers (imperfect experts) close to the location of event source disagreement.  Crowdsourced information  Can also be directly sent to operators  Can also be used in the case of sensor unavailability  Model the reliability of each participant  Online Expectation-Maximisation.  Use participant reliability to improve the aggregation of answers. 12 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Crowdsourcing 13 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Crowdsourcing 14 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Traffic Modelling  Data sparsity problem: Several parts of the city are never/infrequently monitored.  Solution: Generalise observations of monitored locations to produce estimates for locations without sensors.  Scalability to city-sized areas is achieved by modelling the usual case.  Traffic network is represented with a Gaussian Process regression framework  SCATS intersections: observed traffic flow values.  Variables are highly correlated if they are adjacent in the traffic network. 15 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Traffic Modelling: Map of Dublin 16 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Traffic Modelling: Street Network & SCATS Locations 17 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Traffic Modelling: Traffic Flow Estimates 18 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data Summary Insight solution to Urban Traffic Management:  Variety  Complex event processing.  Veracity  Crowdsourcing.  Sparsity  Traffic modelling. 19 Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management

Intelligent Synthesis and Real Time Response using Massive Streaming of Heterogeneous Data  New technologies are creating a data revolution:  These technologies bring problems and challenges: – Heterogeneous data, different scales, noisy data, imperfect knowledge, massive data. – User centered focus, event understanding. – Focused on Urban Traffic Management Insight solution to Urban Traffic Management:  Variety: Complex event processing.  Veracity: Crowdsourcing.  Sparsity: Traffic modelling.  Volume: Stream Processing Active research on several technical fronts, Integrating solutions into one system Come to the MUD 2014 workshop Big Data Challenge Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management