Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings

Research Article

Detecting Elderly Behavior Shift via Smart Devices and Stigmergic Receptive Fields

Download
258 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-58877-3_50,
        author={Marco Avvenuti and Cinzia Bernardeschi and Mario Cimino and Guglielmo Cola and Andrea Domenici and Gigliola Vaglini},
        title={Detecting Elderly Behavior Shift via Smart Devices and Stigmergic Receptive Fields},
        proceedings={Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings},
        proceedings_a={MOBIHEALTH},
        year={2017},
        month={6},
        keywords={Elderly monitoring Smart sensing Stigmergy Neural receptive field User’s behavior shift},
        doi={10.1007/978-3-319-58877-3_50}
    }
    
  • Marco Avvenuti
    Cinzia Bernardeschi
    Mario Cimino
    Guglielmo Cola
    Andrea Domenici
    Gigliola Vaglini
    Year: 2017
    Detecting Elderly Behavior Shift via Smart Devices and Stigmergic Receptive Fields
    MOBIHEALTH
    Springer
    DOI: 10.1007/978-3-319-58877-3_50
Marco Avvenuti1,*, Cinzia Bernardeschi1,*, Mario Cimino1,*, Guglielmo Cola1,*, Andrea Domenici1,*, Gigliola Vaglini1,*
  • 1: University of Pisa
*Contact email: m.avvenuti@iet.unipi.it, c.bernardeschi@iet.unipi.it, m.cimino@iet.unipi.it, g.cola@iet.unipi.it, a.domenici@iet.unipi.it, g.vaglini@iet.unipi.it

Abstract

Smart devices are increasingly used for health monitoring. We present a novel connectionist architecture to detect elderly from data gathered by wearable or ambient sensing technology. Behavior shift is a pattern used in many applications: it may indicate initial signs of disease or deviations in performance. In the proposed architecture, the input samples are aggregated by functional structures called . The trailing process is inspired by , an insects’ coordination mechanism, and is managed by computational units called (SRFs), which provide a (dis-)similarity measure between sample streams. This paper presents the architectural view, and summarizes the achievements related to three application case studies, i.e., indoor mobility behavior, sleep behavior, and physical activity behavior.