Mobile and Ubiquitous Systems: Computing, Networking, and Services. 9th International Conference, MobiQuitous 2012, Beijing, China, December 12-14, 2012. Revised Selected Papers

Research Article

Fine-Grained Transportation Mode Recognition Using Mobile Phones and Foot Force Sensors

Download11 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-40238-8_9,
        author={Zelun Zhang and Stefan Poslad},
        title={Fine-Grained Transportation Mode Recognition Using Mobile Phones and Foot Force Sensors},
        proceedings={Mobile and Ubiquitous Systems: Computing, Networking, and Services. 9th International Conference, MobiQuitous 2012, Beijing, China, December 12-14, 2012. Revised Selected Papers},
        proceedings_a={MOBIQUITOUS},
        year={2013},
        month={9},
        keywords={Transportation Mode Recognition Foot force sensor GPS Accelerometer},
        doi={10.1007/978-3-642-40238-8_9}
    }
    
  • Zelun Zhang
    Stefan Poslad
    Year: 2013
    Fine-Grained Transportation Mode Recognition Using Mobile Phones and Foot Force Sensors
    MOBIQUITOUS
    Springer
    DOI: 10.1007/978-3-642-40238-8_9
Zelun Zhang1,*, Stefan Poslad1,*
  • 1: Queen Mary University of London
*Contact email: zelun.zhang@eecs.qmul.ac.uk, stefan@eecs.qmul.ac.uk

Abstract

Transportation or travel mode recognition plays an important role in enabling us to derive transportation profiles, e.g., to assess how eco-friendly our travel is, and to adapt travel information services such as maps to the travel mode. However, current methods have two key limitations: low transportation mode recognition accuracy and coarse-grained transportation mode recognition capability. In this paper, we propose a new method which leverages a set of wearable foot force sensors in combination with the use of a mobile phone’s GPS (FF+GPS) to address these limitations. The transportation modes recognised include walking, cycling, bus passenger, car passenger, and car driver. The novelty of our approach is that it provides a more fine-grained transportation mode recognition capability in terms of reliably differentiating bus passenger, car passenger and car driver for the first time. Result shows that compared to a typical accelerometer-based method with an average accuracy of 70%, the FF+GPS based method achieves a substantial improvement with an average accuracy of 95% when evaluated using ten individuals.