Sheng-Bin Cao

Papers

Total Citations

H-Index

About

Sheng-Bin Cao is a leading researcher in human-robot interaction and rehabilitation robotics, specializing in surface electromyography (sEMG)-based control systems. His work focuses on developing intelligent algorithms for lower limb exoskeletons, enabling seamless communication between humans and machines. Cao’s major contributions include real-time knee joint angle estimation using Back Propagation Neural Networks (BPNN), achieving 13 citations for his 2021 study that improved continuous motion control in rehabilitation devices. He further advanced the field with a domain-adaptive convolutional neural network (CNN) for gait phase recognition, published in 2022 (12 citations), which overcomes speed-dependent recalibration challenges—a critical step toward practical, user-friendly prosthetics and exoskeletons. By addressing the need for robust, adaptive human–robot interfaces, Cao’s work reduces the data burden for training deep learning models, enhancing accessibility for patients and clinicians. His research has been recognized for its potential to transform rehabilitation therapy, offering more natural and responsive assistive technologies. With a growing citation impact, Cao continues to push boundaries in sEMG signal processing and neural network applications, positioning him as a key innovator in the field of biomechatronics.