Comparing metabolic energy expenditure estimation using wearable multi-sensor network and single accelerometer

Author

Bo Dong ; Biswas, Santosh ; Montoye, Alexander ; Pfeiffer, Klaus

Author_Institution

Dept. of Electr. & Comput. Eng., Michigan State Univ., East Lansing, MI, USA

fYear

2013

fDate

3-7 July 2013

Firstpage

2866

Lastpage

2869

Abstract

This paper presents the implementation details, system architecture and performance of a wearable sensor network that was designed for human activity recognition and energy expenditure estimation. We also included ActiGraph GT3X+ as a popular single sensor solution for detailed comparison with the proposed wearable sensor network. Linear regression and Artificial Neural Network are implemented and tested. Through a rigorous system study and experiment, it is shown that the wearable multi-sensor network outperforms the single sensor solution in terms of energy expenditure estimation.

Keywords

accelerometers; biochemistry; biomedical measurement; body sensor networks; neural nets; pattern recognition; regression analysis; wearable computers; ActiGraph GT3X+; Artificial Neural Network; Linear regression; human activity recognition; metabolic energy expenditure estimation; single accelerometer; single sensor solution; system architecture; wearable sensor network performance; Accelerometers; Artificial neural networks; Biomedical monitoring; Estimation; Feature extraction; Linear regression; Wearable sensors; Activity Recognition; Energy Expenditure Estimation; Wearable Sensor Network;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE

Conference_Location

Osaka

ISSN

1557-170X

Type

conf

DOI

10.1109/EMBC.2013.6610138

Filename

6610138