Author(s)

Lingfei Mo, Shaopeng Liu, Robert X. Gao, Patty S. Freedson

Department of Kinesiology, University of Massachusetts, Amherst, MA, USA.
Department of Mechanical Engineering, University of Connecticut, Storrs, CT, USA.
School of Instrument Science and Engineering, Southeast University, Nanjing, China.

This paper presents a multi-sensor ensemble classifier (MSEC) for physical activity (PA) pattern recognition of human subjects. The MSEC, developed for a wearable multi-sensor integrate measurement system (IMS),combines multiple classifiers based on different sensor feature sets to improve the accuracy of PA type identification.Experimental evaluation of 56 subjects has shown that the MSECis more effectivein assessing activities of varying intensitiesthan the traditional homogeneous classifiers. It is able to correctly recognize 6 PA types with an accuracy of 93.50%, which is 7% higher than the non-ensemble support vector machine method. Furthermore, the MSECis effective in reducing the subject-to-subject variabilityin activity recognition.

Physical Activity Assessment;Multi-Sensor Ensemble;Support Vector Machine

L. Mo, S. Liu, R. Gao and P. Freedson, "Multi-Sensor Ensemble Classifier for Activity Recognition," Journal of Software Engineering and Applications, Vol. 5 No. 12B, 2012, pp. 113-116. doi: 10.4236/jsea.2012.512B022.