Recognizing multiuser activities using wireless body sensor networks

Tao Gu, Liang Wang, Hanhua Chen, Xianping Tao, Jian Lu

Research output: Contribution to journalArticlepeer-review

26 Citations (Scopus)

Abstract

The advances of wireless networking and sensor technology open up an interesting opportunity to infer human activities in a smart home environment. Existing work in this paradigm focuses mainly on recognizing activities of single user. In this work, we focus on the fundamental problem of recognizing activities of multiple users using a wireless body sensor network, and propose a scalable pattern mining approach to recognize both single- and multiuser activities in a unified framework. We exploit Emerging Pattern-a discriminative knowledge pattern which describes significant changes among activity classes of data-for building activity models and design a scalable, noise-resistant, Emerging Pattern-based Multiuser Activity Recognizer (epMAR) to recognize both single- and multiuser activities. We develop a multimodal, wireless body sensor network for collecting real-world traces in a smart home environment, and conduct comprehensive empirical studies to evaluate our system. Results show that epMAR outperforms existing schemes in terms of accuracy, scalability, and robustness.
Original languageEnglish
Pages (from-to)1618-1631
Number of pages14
JournalIEEE Transactions on Mobile Computing
Volume10
Issue number11
DOIs
Publication statusPublished - Nov 2011
Externally publishedYes

Keywords

  • Wireless body sensor networks
  • sensor-based activity recognition
  • pattern mining

Fingerprint Dive into the research topics of 'Recognizing multiuser activities using wireless body sensor networks'. Together they form a unique fingerprint.

Cite this