Mobile Computing, Applications, and Services. Second International ICST Conference, MobiCASE 2010, Santa Clara, CA, USA, October 25-28, 2010, Revised Selected Papers

Research Article

SensOrchestra: Collaborative Sensing for Symbolic Location Recognition

Download208 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-29336-8_11,
        author={Heng-Tze Cheng and Feng-Tso Sun and Senaka Buthpitiya and Martin Griss},
        title={SensOrchestra: Collaborative Sensing for Symbolic Location Recognition},
        proceedings={Mobile Computing, Applications, and Services. Second International ICST Conference, MobiCASE 2010, Santa Clara, CA, USA, October 25-28, 2010, Revised Selected Papers},
        proceedings_a={MOBICASE},
        year={2012},
        month={10},
        keywords={Collaborative sensing mobile phone sensing localization context-awareness context-based advertising},
        doi={10.1007/978-3-642-29336-8_11}
    }
    
  • Heng-Tze Cheng
    Feng-Tso Sun
    Senaka Buthpitiya
    Martin Griss
    Year: 2012
    SensOrchestra: Collaborative Sensing for Symbolic Location Recognition
    MOBICASE
    Springer
    DOI: 10.1007/978-3-642-29336-8_11
Heng-Tze Cheng1,*, Feng-Tso Sun1,*, Senaka Buthpitiya1,*, Martin Griss1,*
  • 1: Carnegie Mellon University
*Contact email: hengtze.cheng@sv.cmu.edu, lucas.sun@sv.cmu.edu, senaka.buthpitiya@sv.cmu.edu, martin.griss@sv.cmu.edu

Abstract

Symbolic location of a user, like a store name in a mall, is essential for context-based mobile advertising. Existing fingerprint-based localization using only a single phone is susceptible to noise, and has a major limitation in that the phone has to be held in the hand at all times. In this paper, we present SensOrchestra, a collaborative sensing framework for symbolic location recognition that groups nearby phones to recognize ambient sounds and images of a location collaboratively. We investigated audio and image features, and designed a classifier fusion model to integrate estimates from different phones. We also evaluated the energy consumption, bandwidth, and response time of the system. Experimental results show that SensOrchestra achieved 87.7% recognition accuracy, which reduces the error rate of single-phone approach by 2X, and eliminates the limitations on how users carry their phones. We believe general location or activity recognition systems can all benefit from this collaborative framework.