TransDec: Big Data for Transportation

TransDec (short for Transportation Decision-Making) is a real-world system  which enables real-time traffic sensor data collection, analysis and visualization of dynamic transportation systems.

With TransDec, we particularly address the fundamental data management and visualization challenges in effective management of dynamic and large-scale transportation data, and efficient processing of real-time and historical spatio-temporal queries on transportation.

The latest developments in wireless technologies as well as the widespread usage of sensors have led to the recent prevalence of Intelligent Transportation Systems (ITS) for realistic and effective monitoring, decision-making, and management of the transportation systems. Considering the large size of the transportation data, variety of the data (different modality and resolutions), and frequent changes of the data, the integration, visualization, querying and analysis of such data for large-scale real-time systems are intrinsically challenging data management tasks. Due to these challenges, current ITS applications only support limited data monitoring and analysis capabilities.


At IMSC we developed a real-world datadriven Intelligent Transportation framework, dubbed TransDec (short for Transportation Decision Making), which enables real-time visualization, querying, and analysis of dynamic transportation systems. We build TransDec with a three-tier architecture (presentation tier, query-interface tier, and data tier) that allows users to create customized spatiotemporal queries through an interactive webbased map interface. With this architecture, we particularly address the fundamental data management and visualization challenges in 1) effective management of dynamic and largescale transportation data, and 2) efficient processing of real-time and historical spatiotemporal queries on transportation networks.

TransDec fuses a rich set of real transportation data obtained from RIITS (Regional Integration of Intelligent Transportation Systems) and NAVTEQ. The RIITS dataset is collected by various organizations based in Los Angeles County including Caltrans D7, Metro, LADOT, and CHP. This dataset includes both inventory and real-time data (with update rate as high as every 1 minute) for freeway and arterial congestion, bus location, events, and CCTV snapshots. Moreover, in order to support diverse ITS applications, TransDec contains the transportation network of the entire US, as well as a wide variety of point-of-interest data provided by NAVTEQ.

 

Subprojects


Year 2013 - 2014

Task Allocation in Dynamic Environments

  • Lead by Prof. Ketan Savla
  • Develop task allocation algorithms for groups of autonomous or human supervised mobile agents which operate in uncertain and dynamically changing environments
Time-dependent Vehicle Routing for Fleets
  • Lead by Dr. Jayant Sharma, Oracle   
  • Develop efficient algorithms for next-generation route planning of delivery vehicles based on real-time and predictive traffic information in transportation networks. 
Traffic Sensor Data Analysis and Regional Monitoring
  • Lead by Prof. Genevieve Giuliano 
  • Mine historical and real-time traffic sensor data to monitor and analyze most congested regions in Los Angeles county towards improving traffic flow. 


Year 2012 - 2013

Archived Traffic Data Management System

  • Faculty lead: Prof. Genevieve Giuliano
  • Description: Implement Online Analytical Processing (OLAP) techniques to analyze archived traffic sensor data towards transportation decision making and planning.

Study of Congested Corridors in Los Angeles

  • Faculty lead: Prof. James Elliott Moore, II
  • Description: Study the most congested corridors of Los Angeles County using historical traffic sensor data, and make before and after analysis of Carmegedons.

Analysis of Mobility Data Using Spatiotemporal Graph-based Techniques

  • Faculty lead: Prof. Antonio Ortega (Electrical Engineering)
  • We consider the scenario where multiple body-attached sensors are used and assume that the data provided by these sensors will be noisy. We will start by analyzing the data captured by real sensors in order to develop a better understanding of noise sources and characteristics. We will then study several de-noising approaches. The first one will be purely time based and will seek to develop techniques (e.g., based on Wavelets) to smooth the temporal trajectories of data at each sensor without removing information that will be important for evaluation and diagnostic. Then, we will also consider graph-based techniques to improve data quality by taking into consideration constraints on the sensor position due to the fact that they are attached to the body. As an example, two sensors attached to an individual's arm will be limited in the extent of their relative motions. We will develop methods were the system is initially calibrated under controlled circumstances, and then data acquired regarding relative sensor positions is used for de-noising. We further plan to explore the potential benefits of recently introduced graph wavelets which can capture all relevant information about body movement as either vertex data (sensor information) or edge data (distance between sensors). In addition to considering the de-noising problem, we will also study lossless and lossy techniques to compress the information generated by the sensors in order to make it easier to store complete records of sensor motion during extended periods of time. The compression techniques will be application-specific, with the goal of preserving key information for signal analysis.


Year 2011 - 2012

Urban Goods Movement

  • Lead by Prof. James Elliott Moore, II (Civil and Environmental Eng.)
  • Develop efficient methods to optimize delivery of goods in urban areas and evaluate impacts across the supply chain.

Traffic Sensor Data Analysis and Corridor Monitoring

  • Lead by Prof. Genevieve Giuliano and Prof. Lisa Schweitzer
  • Analyze real-time and historical traffic sensor data to develop new policies towards enhancing the efficacy of the transportation systems, with emphasis on corridor management and congestion pricing.

Realtime Traffic Video Analysis

  • Joint work with Prof. Jonathan Taplin (Annenberg Innovation Lab) and Intel Corp.
  • Develop vision-based algorithms to extract traffic flow data from traffic monitoring video streams using Intel's coprocessor.
  • Detailed slides can be found here.
  • General introductory presentation.

  • Technical demo presentation.