Behaviour Profiling with Ambient and Wearable Sensing

  • Louis Atallah
  • M. ElHelw
  • J. Pansiot
  • D. Stoyanov
  • L. Wang
  • B. Lo
  • G. Z. Yang
Conference paper

DOI: 10.1007/978-3-540-70994-7_23

Part of the IFMBE Proceedings book series (IFMBE, volume 13)
Cite this paper as:
Atallah L. et al. (2007) Behaviour Profiling with Ambient and Wearable Sensing. In: Leonhardt S., Falck T., Mähönen P. (eds) 4th International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2007). IFMBE Proceedings, vol 13. Springer, Berlin, Heidelberg

Abstract

This paper investigates the combined use of ambient and wearable sensing for inferring changes in patient behaviour patterns. It has been demonstrated that with the use of wearable and blob based ambient sensors, it is possible to develop an effective visualization framework allowing the observation of daily activities in a homecare environment. An effective behaviour modelling method based on Hidden Markov Models (HMMs) has been proposed for highlighting changes in activity patterns. This allows for the representation of sequences in a similarity space that can be used for clustering or data-exploration.

Keywords

body sensor networks similarity based clustering blob sensors behaviour profiling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  • Louis Atallah
    • 2
  • M. ElHelw
    • 2
  • J. Pansiot
    • 2
  • D. Stoyanov
    • 2
  • L. Wang
    • 2
  • B. Lo
    • 2
  • G. Z. Yang
    • 2
  1. 1.Dept of ComputingImperial College LondonLondonUK
  2. 2.Dept of ComputingImperial College LondonLondonUK

Personalised recommendations