EAI Endorsed Transactions on Energy Web 15(7): e4

Research Article

Sensor-Based Activity Recognition with Dynamically Added Context

Download67 downloads
  • @ARTICLE{10.4108/eai.22-7-2015.2260164,
        author={Jiahui Wen and Seng Loke and Jadwiga Indulska and Mingyang Zhong},
        title={Sensor-Based Activity Recognition with Dynamically Added Context},
        journal={EAI Endorsed Transactions on Energy Web},
        volume={15},
        number={7},
        publisher={EAI},
        journal_a={EW},
        year={2015},
        month={8},
        keywords={activity recognition, extra context, activity adaptation},
        doi={10.4108/eai.22-7-2015.2260164}
    }
    
  • Jiahui Wen
    Seng Loke
    Jadwiga Indulska
    Mingyang Zhong
    Year: 2015
    Sensor-Based Activity Recognition with Dynamically Added Context
    EW
    EAI
    DOI: 10.4108/eai.22-7-2015.2260164
Jiahui Wen1,*, Seng Loke2, Jadwiga Indulska1, Mingyang Zhong1
  • 1: The University of Queensland, School of Information Technology and Electrical Engineering, Australia
  • 2: Department of Computer Science and Computer Engineering, La Trobe University, Australia
*Contact email: j.wen@uq.edu.au

Abstract

An activity recognition system essentially processes raw sensor data and maps them into latent activity classes. Most of the previous systems are built with supervised learning techniques and pre-defined data sources, and result in static models. However, in realistic and dynamic environments, original data sources may fail and new data sources become available, a robust activity recognition system should be able to perform evolution automatically with dynamic sensor availability in dynamic environments. In this paper, we propose methods that automatically incorporate dynamically available data sources to adapt and refine the recognition system at run-time. The system is built upon ensemble classifiers which can automatically choose the features with the most discriminative power. Extensive experimental results with publicly available datasets demonstrate the effectiveness of our methods.