SmarTrAC: A Smartphone Solution for Travel and Activity Capturing

Principal Investigator:

Yingling Fan, Assistant Professor, Humphrey School of Public Affairs

Project Summary:

SmartTrAC is an innovative smartphone application that collects highly-detailed activity and travel behavior data with high precision and minimal respondent burden. SmartTrAC brings together smartphone-based sensing, data mining, and user communication seamlessly:

  • It combines smartphone sensing with advanced data mining techniques to automatically detect and classify daily activity and travel episodes;
  • It further integrates the data mining function with effective user communication to allow users to view, correct and augment the automatically classified information, as well as to allow the use of user input data to continuously optimize the data mining function.

The development of SmarTrAC has been sponsored by the Intelligent Transportation Systems Joint Program Office at the U.S. Department of Transportation (USDOT). We anticipate to complete the first SmarTrAC prototype by July 31, 2014. The CTS seed grant will be used between August 2014 and January 2015 to support testing and refinement efforts for improving the SmarTrAC prototype.

Specially, tests will be conducted to assess the suitability of SmarTrAC for every-day work and large-scale deployment. The tests involve putting SmartTrAC to its intended use by its envisaged type of user to perform a standardized multi-day activity and travel data collection task. We will recruit 30 real-world Android phone users with diverse socio-demographic backgrounds. The participants will be asked to wear their smartphone in close contact of the body during all waking hours other than during water activities or phone use activities for seven consecutive days and respond to a set of questions on the smartphone on a daily basis at the end of each day. A smartphone-based exit survey will be conducted with participants after their trial of SmartTrAC to provide detailed feedback on their trial experience and perceived strengths and weaknesses of SmartTrAC, as well as their concerns about participation requirements and privacy issues. Testing and evaluation results will feed into the ongoing refinement and calibration of the SmarTrAC prototype. By January 2015, we expect SmarTrAC to be fully functional, tested, and ready for large-scale deployment.

Sponsors:

Project Details: