Recognizing human motion with multiple acceleration sensors

Author

MÄntyjÄrvi, Jani ; Himberg, Johan ; SeppÄnen, Tapio

Author_Institution

Nokia Res. Center, Finland

Volume

2

fYear

2001

fDate

2001

Firstpage

747

Abstract

In this paper experiments with acceleration sensors are described for human activity recognition of a wearable device user. The use of principal component analysis and independent component analysis with a wavelet transform is tested for feature generation. Recognition of human activity is examined with a multilayer perceptron classifier. Best classification results for recognition of different human motion were 83-90%, and they were achieved by utilizing independent component analysis and principal component analysis. The difference between these methods turned out to be negligible

Keywords

accelerometers; feature extraction; multilayer perceptrons; principal component analysis; sensor fusion; signal classification; wavelet transforms; feature generation; human activity recognition; human motion recognition; independent component analysis; multilayer perceptron classifier; multiple acceleration sensors; principal component analysis; wavelet transform; wearable device user; Acceleration; Humans; Independent component analysis; Multilayer perceptrons; Principal component analysis; Sensor phenomena and characterization; Testing; Wavelet analysis; Wavelet transforms; Wearable sensors;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2001 IEEE International Conference on

Conference_Location

Tucson, AZ

ISSN

1062-922X

Print_ISBN

0-7803-7087-2

Type

conf

DOI

10.1109/ICSMC.2001.973004

Filename

973004