AUTHOR=Yang Liman , Shi Zhijun , Jia Ruming , Kou Jiange , Du Minghua , Bian Chunrong , Wang Juncheng 

TITLE=Multi-branch deep learning neural network prediction model for the development of angular biosensors based on sEMG

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 12 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2024.1492232

DOI=10.3389/fbioe.2024.1492232

ISSN=2296-4185

ABSTRACT=Lower extremity exoskeleton robots have a very broad application prospect, covering many fields such as rescue and disaster relief, industrial production, military operations and medical rehabilitation. However, it is still a challenge to estimate the continuous motion of human joints through surface electromyography(sEMG). In this study, the collected sEMG and plantar force signal are filtered and denoised, and the time domain features and frequency domain features that can characterize human gait information are extracted. A multi-branch deep learning neural network model is built. The extracted features are used as input, and the gait cycle and joint angle are used as output to realize the accurate recognition of human walking gait and the effective estimation of joint angle. In this study, a human walking gait recognition and joint angle prediction model was designed to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.