4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming healthcare through innovations in mobile and wireless technologies"

Research Article

Real-time Indoor Patient Movement Pattern Telemonitoring with One-meter Precision

Download503 downloads
  • @INPROCEEDINGS{10.4108/icst.mobihealth.2014.257401,
        author={Po-Chou Liang and Paul Krause},
        title={Real-time Indoor Patient Movement Pattern Telemonitoring with One-meter Precision},
        proceedings={4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming healthcare through innovations in mobile and wireless technologies"},
        publisher={IEEE},
        proceedings_a={MOBIHEALTH},
        year={2014},
        month={12},
        keywords={telemonitoring movement pattern localization location tracking received signal strength kalman filter step detection sensor fusion},
        doi={10.4108/icst.mobihealth.2014.257401}
    }
    
  • Po-Chou Liang
    Paul Krause
    Year: 2014
    Real-time Indoor Patient Movement Pattern Telemonitoring with One-meter Precision
    MOBIHEALTH
    IEEE
    DOI: 10.4108/icst.mobihealth.2014.257401
Po-Chou Liang1,*, Paul Krause1
  • 1: University of Surrey
*Contact email: p.liang@surrey.ac.uk

Abstract

Monitoring of the activities of daily living of the elderly at home is widely recognized as useful for detection of new or deteriorated health conditions. However, the accuracy of existing indoor location tracking systems remains unsatisfactory. The aim of this study was therefore to develop a localization system that can identify a patient’s real-time location in a home environment with maximum estimation error of two meters at a 95% confidence level. A prototype based on a sensor fusion approach was built. This involved the development of both a step detector using the accelerometer and compass of an iPhone 5, and a radio-based localization subsystem using Kalman filter and received signal strength indication (RSSI). The results of our experiments were promising with average estimation error of 0.55 meters. We are confident that with more work our design can be adapted to a home-like environment with a more robust localization solution.