Activity recognition using dynamic multiple sensor fusion in body sensor networks

Lei Gao, Alan K. Bourke, John Nelson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Multiple sensor fusion is a main research direction for activity recognition. However, there are two challenges in those systems: the energy consumption due to the wireless transmission and the classifier design because of the dynamic feature vector. This paper proposes a multi-sensor fusion framework, which consists of the sensor selection module and the hierarchical classifier. The sensor selection module adopts the convex optimization to select the sensor subset in real time. The hierarchical classifier combines the Decision Tree classifier with the Naïve Bayes classifier. The dataset collected from 8 subjects, who performed 8 scenario activities, was used to evaluate the proposed system. The results show that the proposed system can obviously reduce the energy consumption while guaranteeing the recognition accuracy.

Original languageEnglish
Title of host publication2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012
Pages1077-1080
Number of pages4
DOIs
Publication statusPublished - 2012
Event34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012 - San Diego, CA, United States
Duration: 28 Aug 20121 Sep 2012

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012
Country/TerritoryUnited States
CitySan Diego, CA
Period28/08/121/09/12

Fingerprint

Dive into the research topics of 'Activity recognition using dynamic multiple sensor fusion in body sensor networks'. Together they form a unique fingerprint.

Cite this