6th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

Research Article

Mining Emerging Patterns for recognizing activities of multiple users in pervasive computing

Download671 downloads
  • @INPROCEEDINGS{10.4108/ICST.MOBIQUITOUS2009.7013,
        author={Tao Zhu and Zhanqing Wu and Liang  Wang and Xianping  Tao and Jian  Lu},
        title={Mining Emerging Patterns for recognizing activities of multiple users in pervasive computing},
        proceedings={6th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services},
        publisher={IEEE},
        proceedings_a={MOBIQUITOUS},
        year={2009},
        month={11},
        keywords={Acoustic noise Acoustic sensors Computer science Feedback loop Humans Laboratories Mathematics Pattern recognition Pervasive computing Testing},
        doi={10.4108/ICST.MOBIQUITOUS2009.7013}
    }
    
  • Tao Zhu
    Zhanqing Wu
    Liang Wang
    Xianping Tao
    Jian Lu
    Year: 2009
    Mining Emerging Patterns for recognizing activities of multiple users in pervasive computing
    MOBIQUITOUS
    IEEE
    DOI: 10.4108/ICST.MOBIQUITOUS2009.7013
Tao Zhu1,*, Zhanqing Wu2,*, Liang Wang2,*, Xianping Tao2,*, Jian Lu2,*
  • 1: Department of Mathematics and Computer Science, University of Southern Denmark
  • 2: State Key Laboratory for Novel Software Technology, Nanjing University, China
*Contact email: gu@imada.sdu.dk, wzq@ics.nju.edu.cn, wangliang@ics.nju.edu.cn, txp@ics.nju.edu.cn, lj@nju.edu.cn

Abstract

Understanding and recognizing human activities from sensor readings is an important task in pervasive computing. In this paper, we investigate the fundamental problem of recognizing activities for multiple users from sensor readings in a home environment, and propose a novel pattern mining approach to recognize both single-user and multi-user activities in a unified solution. We exploit Emerging Pattern - a type of knowledge pattern that describes significant changes between classes of data - for constructing our activity models, and propose an Emerging Pattern based Multi-user Activity Recognizer (epMAR) to recognize both single-user and multi-user activities.