Sensor-based Human Activity Recognition in a Multi-user Scenario

Liang Wang, Tao Gu, Xianping Tao, Jian Lu

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstrakt

Existing work on sensor-based activity recognition focuses mainly on
single-user activities. However, in real life, activities are often performed by multiple
users involving interactions between them. In this paper, we propose Coupled
Hidden Markov Models (CHMMs) to recognize multi-user activities from
sensor readings in a smart home environment. We develop a multimodal sensing
platform and present a theoretical framework to recognize both single-user and
multi-user activities. We conduct our trace collection done in a smart home, and
evaluate our framework through experimental studies. Our experimental result
shows that we achieve an average accuracy of 85.46% with CHMMs.
OriginalsprogEngelsk
TitelIn Proc. of the European Conference on Ambient Intelligence (AmI '09), Salzburg, Austria, Nov 18-21, 2009.
RedaktørerManfred Tscheligi, Boris de Ruyter, Panos Markopoulus, Reiner Wichert, Thomas Mirlacher, Alexander Meschterjakov, Wolfgang Reitberger
ForlagSpringer
Publikationsdato2009
ISBN (Trykt)978-3-642-05407-5
ISBN (Elektronisk)978-3-642-05408-2
DOI
StatusUdgivet - 2009
Begivenhed3rd European Conference on Ambient Intelligence, AmI 09 - Salzburg, Østrig
Varighed: 18. nov. 200921. nov. 2009

Konference

Konference3rd European Conference on Ambient Intelligence, AmI 09
LandØstrig
BySalzburg
Periode18/11/200921/11/2009

    Fingerprint

Citationsformater

Wang, L., Gu, T., Tao, X., & Lu, J. (2009). Sensor-based Human Activity Recognition in a Multi-user Scenario. I M. Tscheligi, B. de Ruyter, P. Markopoulus, R. Wichert, T. Mirlacher, A. Meschterjakov, & W. Reitberger (red.), In Proc. of the European Conference on Ambient Intelligence (AmI '09), Salzburg, Austria, Nov 18-21, 2009. Springer. https://doi.org/10.1007/978-3-642-05408-2_10