A Human Body Posture Recognition Algorithm Based on BP Neural Network for Wireless Body Area Networks

• Published in: China communications Vol. 13; no. 8; pp. 198 - 208
• Main Authors: Hu, Fengye, Wang, Lu, Wang, Shanshan, Liu, Xiaolan, He, Gengxin
• Format: Journal Article
• Language: English
• Published: China Institute of Communications 01.08.2016; College of Communication Engineering, Jilin University, Changchun, Jilin, 130025, China%The North West China Research Institute of Electronic Equipment, Xi'an, Shanxi, 710065, China
• Subjects: Acceleration; Algorithm design and analysis; Biological neural networks; Body area networks; BP neural network; Hardware; posture recognition rate; signal vector magnitude; wireless body area networks; Wireless communication; posture recognition rate; BP neural network; wireless body area networks; signal vector magnitude
• ISSN: 1673-5447
• DOI: 10.1109/CC.2016.7563723

Human body posture recognition has attracted considerable attention in recent years in wireless body area networks （WBAN）. In or- der to precisely recognize human body posture, many recognition algorithms have been proposed. However, the recognition rate is relatively low. In this paper, we apply back propagation （BP） neural network as a classifier to recognizing human body posture, where signals are collected from VG350 acceleration sensor and a posture signal collec- tion system based on WBAN is designed. Human body signal vector magnitude （SVM） and tri-axial acceleration sensor data are used to describe the human body postures. We are able to recognize 4 postures： Walk, Run, Squat and Sit. Our posture recognition rate is up to 91.67%. Furthermore, we find an implied relationship between hidden layer neurons and the posture recognition rate. The proposed human body posture recognition algorithm lays the foundation for the subsequent applications.