Fang Yang

Fang Yang

Auto-generated profile, based on publicly available information

Fang Yang

College of Nursing and Rehabilitation, North China University of Science and Technology, Tangshan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 May 2024 in IEEE Access
Verified
Journal Article
Open access
FYFang Yang
Fang Yang
QZQianqian Zheng
Qianqian Zheng
LCLianqing Chen
Lianqing Chen
XTXiong Tan
Xiong Tan
HSHong Sun
Hong Sun
With the increasing aging of the population, exoskeleton robots, gait assistance in the medical field, and condition monitoring in the rehabilitation field have been widely concerned by scholars. Accurate recognition of human gait and the perception of behavioral intention are essential for understanding the human motion state. Addressing issues of intricate sensor layout, low resolution of the plantar pressure sensor, and inaccurate gait classification, this paper presents a wearable sensor-based method for perceiving human behavior intentions. Firstly, a foot motion data acquisition system is built, and the foot motion feature data are obtained by combining the self-designed tactile pressure sensor and the Inertial Measurement Unit. Secondly, the rule of human movement is analyzed and the phase of gait in different motion modes is divided. Then, considering the temporal characteristics of human motion, the behavior pattern recognition algorithm is constructed by combining a Convolutional Neural Network and a Long Short-Term Memory network. Simultaneously, a Convolutional Neural network is established to recognize gait information and enhance the recognition accuracy of human behavior. Finally, the experiment of human motion intention recognition is carried out. The experimental results show that the proposed method has an average recognition accuracy of 96% for human motion patterns, and an average recognition accuracy of 93.38%, 94.57%, and 92.57% for the gait phase in various modes, respectively. The experimental results show that this method can meet the requirements of common human behavior recognition.