Mobile Computing, Applications, and Services. First International ICST Conference, MobiCASE 2009, San Diego, CA, USA, October 26-29, 2009, Revised Selected Papers

Research Article

A Mobile Application to Detect Abnormal Patterns of Activity

Download
706 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-12607-9_13,
        author={Omar Baki and Joy Zhang and Martin Griss and Tony Lin},
        title={A Mobile Application to Detect Abnormal Patterns of Activity},
        proceedings={Mobile Computing, Applications, and Services. First International ICST Conference, MobiCASE 2009, San Diego, CA, USA, October 26-29, 2009, Revised Selected Papers},
        proceedings_a={MOBICASE},
        year={2012},
        month={10},
        keywords={activity monitoring context-aware abnormality detection unsupervised learning online clustering senior care},
        doi={10.1007/978-3-642-12607-9_13}
    }
    
  • Omar Baki
    Joy Zhang
    Martin Griss
    Tony Lin
    Year: 2012
    A Mobile Application to Detect Abnormal Patterns of Activity
    MOBICASE
    Springer
    DOI: 10.1007/978-3-642-12607-9_13
Omar Baki1,*, Joy Zhang1,*, Martin Griss1,*, Tony Lin1,*
  • 1: Carnegie Mellon Silicon Valley
*Contact email: omar.abdulbaki@sv.cmu.edu, joy.zhang@sv.cmu.edu, martin.griss@sv.cmu.edu, tony.lin@sv.cmu.edu

Abstract

In this paper we introduce an unsupervised online clustering algorithm to detect abnormal activities using mobile devices. This algorithm constantly monitors a user’s daily routine and builds his/her personal behavior model through online clustering. When the system observes activities that do not belong to any known normal activities, it immediately generates alert signals so that incidents can be handled in time. In the proposed algorithm, activities are characterized by users’ postures, movements, and their indoor location. Experimental results show that the behavior models are indeed user-specific. Our current system achieves 90% precision and 40% recall for anomalous activity detection.