TRAC-IT is an innovative mobile phone app that is able to collect high-resolution travel behavior data that are instantly transferred to a server for analysis by transportation professionals and automated software systems. A mobile phone with TRAC-IT installed easily fits in a person’s pocket and can record true multimodal travel using car, bus, bike, and walk.
TRAC-IT implements several patented and patent-pending, battery-smart technologies that enable the phone battery to last more than an entire day, even when GPS is being sampled as frequently as every second while the user is moving. Since data is transferred to the TRAC-IT server as it is being collected, TRAC-IT can be deployed into the field indefinitely to record behavior without needing to collect the devices to retrieve data. For more information on the smart battery-saving technology underlying TRAC-IT, see our “Technology” page. There are also several data processing modules that produce information from raw tracking data about points-of-interest (via clustering), mode of transportation (via artifical neural networks), and trip purpose (via geographic information systems).

Green and yellow clusters represent Points-of-interest where the user frequently visits, while the red and orange clusters indicate areas of frequent traffic congestion
Since TRAC-IT sends GPS data from the phone to a server in real-time, TRAC-IT also can provide personalized, predictive real-time location-based services (e.g., traffic alerts, location-based advertising) that benefits the end-user and gives the user a direct incentive for continuing to participate in long-term travel surveys. Read more about TRAC-IT’s real-time location-based services in the Dynamic Travel Info research project.
TRAC-IT also integrates Personal Travel Coach technology, which can provide personalizes suggestions to users that may help them save time and money by streamlining their travel behavior. The Personal Travel Coach was designed to support Transportation Demand Management strategies and policies to seek to increase transportation system efficiency and achieve specific objectives such as reduced traffic congestion, road and parking cost savings, increased safety, improved mobility for non-drivers, energy conservation, and pollution emission reductions. Read more about the Personal Travel Coach in a TRAC-IT report.
For TRAC-IT Users:
Tutorial – Using TRAC-IT for a Travel Behavior Survey – Sanyo Pro 200 w/ Java ME
TRAC-IT users can now log into our participant website.
TRAC-IT Papers and Publications
- Philip Winters. “Using Mobile Phones to Track Multimodal Travel Behavior”, 2013 UTC Southeast Conference, Orlando, FL, April 4th, 2013.
- Concas, Barbeau, Winters, Georggi, Bond. “Using Mobile Apps to Measure Spatial Travel Behavior Changes of Carsharing Users,” Proceedings of 2013 Transportation Research Board Conference, Washington, D.C., January 13-17, 2013. Powerpoint Presentation.
- Concas, Barbeau, Winters, Georggi, Bond. “Do Variable-Pricing Strategies Influence Activity-Travel Patterns of Carsharing Users? – A Case Study,” Proceedings of 2013 Transportation Research Board Conference, Washington, D.C., January 13-17, 2013. Powerpoint Presentation.
- Sean J. Barbeau, Nevine L. Georggi, Philip L. Winters, Miguel Labrador. “Participatory Sensing: Smart Phones as Sensors in a Connected World (P11-1654),” SensingTechnologies for Transportation Applications Workshop, Information Systems and Technology (ABJ50) & Geographic Information Science and Applications (ABJ60) Committee Meetings, National Academy of Sciences’ Transportation Research Board 90th Annual Meeting. Washington, D.C., January 23th, 2011.
- Paola A. Gonzalez, Jeremy S. Weinstein, Sean J. Barbeau, Miguel A. Labrador, Philip L. Winters, Nevine L. Georggi, Rafael A. Perez. “Automating Mode Detection for Travel Behavior Analysis by Using GPS-enabled Mobile Phones and Neural Networks,”Institution of Engineering and Technology (IET) Intelligent Transportation Systems, 2010, Vol. 4, Iss. 1, pp. 37–49. doi: 10.1049/iet-its.2009.0029. © The Institution of Engineering and Technology 2010.
- Sean J. Barbeau, Nevine L. Georggi, Philip L. Winters. “TRAC-IT: Travel Behavior Data Mining using GPS-enabled Mobile Phones,” U.S Department of Transportation Federal Highway Administration Travel Model Improvement Program (TMIP) National Webinar on Data Transferability and Data Mining, January 25, 2010.
- Sean J. Barbeau, Miguel A. Labrador, Nevine L. Georggi, Philip L. Winters, Rafael A. Perez. “TRAC-IT: A Software Architecture Supporting Simultaneous Travel Behavior Data Collection and Real-Time Location-Based Services for GPS-Enabled Mobile Phones,” Proceedings of the National Academy of Sciences’ Transportation Research Board 88th Annual Meeting, Paper #09-3175, January, 2009.
- Narin Persad-Maharaj, Sean J. Barbeau, Miguel A. Labrador, Philip L. Winters, Rafael Perez, Nevine Labib Georggi.“Real-time Travel Path Prediction using GPS-enabled Mobile Phones,” 15th World Congress on Intelligent Transportation Systems, New York, New York, November 16-20, 2008.
Research Project Reports
TRAC-IT Phase 1 Traveling Smart: Increasing Transit Ridership Through Automated Collection (TRAC) of Individual Travel Behavior Data and Personalized Feedback
Reducing vehicle trips and vehicle miles of travel (VMT) are part of a multifaceted approach that addresses the growing traffic congestion problems. Previous research analyzed household travel patterns and provided personalized advice to participants to encourage the reduction of vehicle trips and VMT. An analysis of covariance conducted on the average contributed VMT and vehicle trips used the post-advice period’s travel patterns as the dependent variable. The provision of suggestions had a statistically significant effect on VMT and trip numbers contributed. Overall, this experiment showed that the provision of feedback would reduce VMT.
However, the labor and time-intensive post-processing costs hampered widespread application. This project sought to overcome this limitation by using the expanded capabilities and falling prices of Personal Digital Assistants (PDA) and cellular phones in combination with Global Positioning Systems (GPS). This system, “TRAC-IT” offers an opportunity to improve the quality of collected data while reducing associated collection and processing costs and errors. TRAC-IT Phase 1 final report.
TRAC-IT Phase 2 Testing the Impact of Personalized Feedback on Household Travel Behavior
Making smart travel choices require understanding the operation of the transportation system and influencing the use of public transportation. This knowledge begins with collecting data to measure or monitor travel behavior. This research project is Phase II of the ongoing NCTR project “Traveling Smart: Increasing Transit Ridership by Automatic Collection (TRAC) of Individual Travel Behavior Data and Personalized Feedback” or TRAC-IT. The focus of Phase I was to design, implement and test a portable automatic activity diary system. A personal digital assistance (PDA) combined with a global positioning system (GPS) was assembled as one unit PDA/GPS and loaded with an activity diary that collects information such as travel purpose, origin, destination, travel time & path, speed, occupancy, etc. Additionally, a “GPS-Enabled” cell phone was identified as a possible cost-effective replacement for the PDA/GPS device combination and could even provide additional benefits such as extended battery-life and increased portability due to its smaller size. Also, the task of building a prototype expert system that provides customized feedback advice tailored to an individual’s travel behavior patterns was completed.
The goal of Phase II is to test and refine the data collection tool (PDA/GPS or GPS-enabled cell phone software) & Expert System created in Phase I so that TRACIT can be distributed to two groups: an experimental and a control group. The trial expert system developed for Phase 1 tested the suggestion generation rationale on a handful of households for a particular set of sample travel scenarios but did not monitor or measure travel behavior changes. Phase II will test the handheld device prototype (“GPS-Enabled” cell phone or PDA/GPS) on a larger sample of households and measure the changes in household travel behavior. After 2-4 weeks of collecting baseline travel behavior from the two groups of participants, custom travel device generated by the Expert System will be given to the experimental group but not the control group. After giving the travel advice, another round of activity-based travel data will be collected using the handheld device to see if the suggestions had an impact on the experimental group’s travel behavior. TRAC-IT Phase 2 Final Report
TRAC-IT Phase 3 Smart Phone Application to Influence Travel Behavior
In earlier phases of this project, the NCTR-funded TRAC-IT project developed and pilot tested an application to track an individual’s travel behavior using a Personal Digital Assistant (PDA) platform linked with a Global Positioning Systems (GPS). The system works across modes of transportation (i.e., not tied to a vehicle such as a car or bus). In addition, TRAC-IT automatically analyzes the data collected from the device to give personalized feedback advice, based on its server-side expert system. This project will expand the PDA-based TRAC-IT by adapting the application to cell phones and integrating the technology with other real-time information services such as traffic information systems and transit AVL systems to increase the utility and effectiveness of the application. Location-based services such as approaching transit vehicles, alternate routes and driving directions can be calculated and delivered directly to the user based on both real-time incident and traffic conditions and their past travel behavior, allowing them to alter their mode or planned route before they encounter a problem. Intelligent software will control the delivery of information to the user to assure that only relevant information is delivered to the user based on their current location and driving path, and that it is delivered in a method that is not distracting (i.e., through voice prompts). It also will examine modifications on the client side (e.g., within the phone) and server-side (e.g., hosted on a computer) to make the TRAC-IT system fully automated and scalable from small towns to large urban cities. TRAC-IT Phase 3 Final Report
3 Responses to TRAC-IT