Activity recognition exploiting classifier level fusion of acceleration and physiological signals

Abstract

We investigate how to effectively combine physiological signals with acceleration signals to conduct activity recognition task. Firstly, features are extracted from acceleration and physiological signals, including heart rate variability (HRV). Secondly, classifier level fusion is utilized to combine the models built by acceleration and physiological features separately. Experiment results show that activity recognition task can benefit from HRV features, and classifier level fusion has its superiority over feature level fusion.

DOI: 10.1145/2638728.2638777

Extracted Key Phrases

2 Figures and Tables

Cite this paper

@inproceedings{Guo2014ActivityRE, title={Activity recognition exploiting classifier level fusion of acceleration and physiological signals}, author={Haodong Guo and Gencai Chen and Ling Chen and Yanbin Shen}, booktitle={UbiComp Adjunct}, year={2014} }