2nd International ICST Conference on Body Area Networks

Research Article

On-body activity recognition in a dynamic sensor network

Download628 downloads
  • @INPROCEEDINGS{10.4108/bodynets.2007.114,
        author={Clemens Lombriser and Nagendra B. Bharatula and Daniel Roggen and Gerhard Tr\o{}ster},
        title={On-body activity recognition in a dynamic sensor network},
        proceedings={2nd International ICST Conference on Body Area Networks},
        publisher={ICST},
        proceedings_a={BODYNETS},
        year={2007},
        month={6},
        keywords={Titan Activity Recognition Context awareness},
        doi={10.4108/bodynets.2007.114}
    }
    
  • Clemens Lombriser
    Nagendra B. Bharatula
    Daniel Roggen
    Gerhard Tröster
    Year: 2007
    On-body activity recognition in a dynamic sensor network
    BODYNETS
    ICST
    DOI: 10.4108/bodynets.2007.114
Clemens Lombriser1,*, Nagendra B. Bharatula1,*, Daniel Roggen1,*, Gerhard Tröster1,*
  • 1: Wearable Computing Lab ETH Zürich Zürich, Switzerland
*Contact email: lombriser@ife.ee.ethz.ch, bharatula@ife.ee.ethz.ch, droggen@ife.ee.ethz.ch, troester@ife.ee.ethz.ch

Abstract

Recognizing user activities using body-worn, miniaturized sensor nodes enables wearable computers to act context-aware. This paper describes how online activity recognition algorithms can be run on the SensorButton, our miniaturized wireless sensor platform. We present how the activity recognition algorithms have been optimized to be run online on our sensor platform, and how the execution can be distributed to the wireless sensor network. The resulting algorithm has been implemented as a custom, platform-specific executable as well as integrated into TinyOS. A comparison shows that the TinyOS executable is using about 7kB more code memory, while both implementations classify the activity in up to 18 classifications per second.