Mobile and Ubiquitous Systems: Computing, Networking, and Services. 8th International ICST Conference, MobiQuitous 2011, Copenhagen, Denmark, December 6-9, 2011, Revised Selected Papers

Research Article

Recognizing Group Activities Using Wearable Sensors

Download244 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-30973-1_34,
        author={Dawud Gordon and Jan-Hendrik Hanne and Martin Berchtold and Takashi Miyaki and Michael Beigl},
        title={Recognizing Group Activities Using Wearable Sensors},
        proceedings={Mobile and Ubiquitous Systems: Computing, Networking, and Services. 8th International ICST Conference, MobiQuitous 2011, Copenhagen, Denmark, December 6-9, 2011, Revised Selected Papers},
        proceedings_a={MOBIQUITOUS},
        year={2012},
        month={10},
        keywords={group activity recognition context recognition distributed systems multi-user wearable},
        doi={10.1007/978-3-642-30973-1_34}
    }
    
  • Dawud Gordon
    Jan-Hendrik Hanne
    Martin Berchtold
    Takashi Miyaki
    Michael Beigl
    Year: 2012
    Recognizing Group Activities Using Wearable Sensors
    MOBIQUITOUS
    Springer
    DOI: 10.1007/978-3-642-30973-1_34
Dawud Gordon1,*, Jan-Hendrik Hanne2,*, Martin Berchtold2,*, Takashi Miyaki1,*, Michael Beigl1,*
  • 1: Karlsruhe Institute of Technology
  • 2: Technische Universität Braunschweig
*Contact email: Dawud.Gordon@kit.edu, j-h.hanne@tu-bs.de, m.berchtold@tu-bs.de, Takashi.Miyaki@kit.edu, Michael.Beigl@kit.edu

Abstract

Pervasive computing envisions implicit interaction between people and their intelligent environments instead of between individuals and their devices, inevitably leading to groups of individuals interacting with the same intelligent environment. These environments must be aware of user contexts and activities, as well as the contexts and activities of groups of users. Here an application for in-network group activity recognition using only mobile devices and their sensors is presented. Different data abstraction levels for recognition were investigated in terms of recognition rates, power consumption and wireless communication volumes for the devices involved. The results indicate that using locally extracted features for global, multi-user activity recognition is advantageous (10% reduction in energy consumption, theoretically no loss in recognition rates). Using locally classified single-user activities incurred a 47% loss in recognition capabilities, making it unattractive. Local clustering of sensor data indicates potential for group activity recognition with room for improvement (40% reduction in energy consumed, though 20% loss of recognition abilities).