University of Southern California
TransDec: A Big-Data Framework for Decision-Making in Transportation Systems
Abstract: The vast amounts of transportation datasets (traffic flow, incidents, etc.) collected by various federal and state agencies are extremely valuable in real-time decision-making, planning, and management of the transportation systems. In this talk, I will argue that considering the large volume of the transportation data, variety of the data (different modalities and resolutions), and the velocity of the data arrival, developing a scalable system that allows for effective querying and analysis of both archived and real-time data is an intrinsically challenging BigData problem. Subsequently, I will present our end-to-end prototype systme, dubbed TransDec (short for Transportation Decision-Making), which enables real-time integration, visualization, querying, and analysis of these dynamic and archived transportation datasets. I will then discuss a GPS navigation application enabled by such a system and demonstrate its commercialization as a product called ClearPath (see http://myfastestpath.com). Motivated by ClearPath, we will look under the hood and focus on a route-planning problem where the weights on the road-network edges vary as a function of time due to the variability of traffic congestion. I will show that naïve approaches to address this problem are either inaccurate or slow, leading to our new approach to this problem: A time-dependent A* algorithm.
Bio: Cyrus Shahabi is a Professor of Computer Science and Electrical Engineering and the Director of the Information Laboratory (InfoLAB) at the Computer Science Department and also the Director of the NSF's Integrated Media Systems Center (IMSC) at the University of Southern California. He was also the CTO and co-founder of a USC spin-off and an In-Q-Tel portfolio company, Geosemble Technologies, which was acquired in July 2012. He received his B.S. in Computer Engineering from Sharif University of Technology in 1989 and then his M.S. and Ph.D. Degrees in Computer Science from the University of Southern California in May 1993 and August 1996, respectively. He authored two books and more than two hundred research papers in the areas of databases, GIS and multimedia.
Dr. Shahabi has received funding from several agencies such as NSF, NIJ, NASA, NIH, DARPA, AFRL, and DHS as well as several industries such as Chevron, Google, HP, Intel, Microsoft, NCR and NGC. He was an Associate Editor of IEEE Transactions on Parallel and Distributed Systems (TPDS) from 2004 to 2009. He is currently on the editorial board of the VLDB Journal, IEEE Transactions on Knowledge and Data Engineering (TKDE), ACM Computers in Entertainment and Journal of Spatial Information Science. He is the founding chair of IEEE NetDB workshop and also the general co-chair of ACM GIS 2007, 2008 and 2009. He chaired the nomination committee of ACM SIGSPATIAL for the 2011-2014 terms. He is a PC co-Chair of MDM 2013 and regularly serves on the program committee of major conferences such as VLDB, ACM SIGMOD, IEEE ICDE, ACM SIGKDD, and ACM Multimedia.
Dr. Shahabi is a recipient of the ACM Distinguished Scientist award in 2009, the 2003 U.S. Presidential Early Career Awards for Scientists and Engineers (PECASE), the NSF CAREER award in 2002, and the 2001 Okawa Foundation Research Grant for Information and Telecommunications. He was the recipient of US Vietnam Education Foundation (VEF) faculty fellowship award in 2011 and 2012, an organizer of the 2011 National Academy of Engineering "Japan-America Frontiers of Engineering" program, an invited speaker in the 2010 National Research Council (of the National Academies) Committee on New Research Directions for the National Geospatial-Intelligence Agency, and a participant in the 2005 National Academy of Engineering "Frontiers of Engineering" program.
Car-centric Traffic Monitoring and Management using Probe-based Community Data
Abstract: With the introduction of TomTom's historic and real-time traffic technologies IQ Routes and HD Traffic in 2007 the portfolio has been implemented in many European countries, North America, South Africa, Australia and New Zealand.
The backbone of the technology is community data from GPS enabled navigation devices, fleet management solutions as well as GSM cell phone operation. Today, the entire TomTom Traffic Community consists of more than 140 Mio. users which bring TomTom in a position to get precise travel time data for the entire road network in the underlying markets.
All the traffic content has been fully integrated into navigation software of TomTom and is also licensed to external parties for use in enterprise and government application of traffic information, traffic planning and traffic management.
The increasing community of connected navigation devices using precise traffic information is also contributing for a better utilization of the road network when drivers follow dynamic route guidance. In a Traffic Manifesto the TomTom vision has been published making TomTom's traffic information widely available. The availability of traffic information and use in dynamic navigation helps to improve the road network utilization and can contribute to travel behavior changes with positive impact for the network load and the environment. Even when only 10% of the entire driver population uses dynamic routes guidance with precise traffic as HD Traffic they can gain travel time wins of up to 15% toward a planned destination but also help non-informed users to decrease the travel time up to 5%. Connected navigation can help traffic management authorities to make the road network utilization more efficient at lower costs as installing more expensive local detection systems. In the presentation the data collection, processing, storage and distribution system will be introduced. The data fusion engine to provide travel time and jam delay information is fully based on analytics of billions of real-time GPS probe data collected in 26 markets globally. Real-time and historic traffic information can be used in a variety of classical traffic management and standard routing/navigation applications generated in high quality and more cost efficient as infrastructure based systems using local detection system as inductive loops. Infrastructure performance measures are available in the entire road network and give traffic planners and consultants great tools at hand to put the investments at the right spots. TomTom discloses every 3 months the Traffic Congestion Report where over 100 cities globally are analyzed. Traffic delays in rush hour and over the days are computed against the free flow condition measure over the night hours. In the most recent report Moscow was analyzed as the most congested city of all cities in the report. The presentation will also cover how the Index is built.
Bio: SSince January 2012 Ralf-Peter Schäfer is leading the TomTom Traffic Product Unit. He is responsible for the global product development for traffic in the TomTom Group incl. Engineering, product and program management as well as sales and marketing support.
He joined TomTom in August 2006 and started to work in a position of the Research Director of TomTom's Mobility Solution Department and the Head of the TomTom R&D Centre in Berlin. His major scope from 2006 was the development of the TomTom traffic portfolio incl. algorithms and software for the realtime traffic information service HD Traffic and the historic speed profile product IQ Routes. With his team he also developed the dynamic location referencing technology OpenLR to allow cost efficient transmission and excahnge of map location.
Ralf-Peter Schäfer studied electrical engineering the the Technical University of Ilmenau and work in several research organisations as the German Academy of Sciences, the German Centre for Computer Science, the German Aerospce Center (DLR) before he joined TomTom. Main areas of activities in the past and today include static and dynamic content generation for traffic products, probe technology development from GPS and GSM sources as well as modeling and data processing techniques for traffic systems.
Areas of activity:
- static and dynamic traffic content delivery for TomTom's Traffic portfolio
- HD Traffic service development
- Traffic data processing algorithms development based on probe technologies (GSM, GPS)
- Data aggregation and fusion
- Incident detection and predictive systems
2000-2006: Research Associate and Head of Department at the German Aerospace Center (DLR) -Institute of Transport Research, Berlin, Germany
Research activities: GPS probe technology, Taxi FCD technology development, ITS applications development based on probe data technology, traffic control and management system design
1997-1999: Research Associate at the Technical University of Berlin, Computer Science Department
Research activities: ITS applications, Traffic and emission modeling, probe technology
1992-1996 Research Associate at German Center for Computer Sciences, Institute for Computer Architecture and Software Technology, Berlin, Germany
Research activities: Environmental modeling and simulation, environmental data base design, emission modeling
1990-1991: Research Associate at the German Academy of Sciences, Institute of Cybernetics, Berlin, Germany
Diploma degree in Electrical Engineering from the Technical University of Ilmenau, Germany (1990)