Shijie Fan

About

Dr. Shijie Fan is a leading researcher at the intersection of wearable sensing, rehabilitation robotics, and human–machine interaction. His work centers on decoding neuromuscular signals—particularly surface electromyography (sEMG)—to enable intuitive control of lower limb exoskeletons and advanced prosthetics. Fan’s most cited paper, “EMG-Based Dual-Branch Deep Learning Framework With Transfer Learning for Lower Limb Motion Classification and Joint Angle Estimation” (2025, 4 citations), tackles a critical challenge in the field: simultaneously classifying discrete movement types and predicting continuous joint angles from sEMG data. By introducing a dual-branch neural architecture combined with transfer learning, his framework significantly improves the accuracy and robustness of motion decoding across different users and sessions, reducing the need for extensive retraining. This work directly addresses the real-world demands of rehabilitation and assistive robotics, where seamless, adaptive control is essential. Fan’s contributions are paving the way for more responsive and personalized exoskeleton systems, with potential applications in stroke rehabilitation, spinal cord injury recovery, and augmenting human mobility. His research continues to push the boundaries of how biological signals can be harnessed for intuitive, non-invasive machine control.

Research Focus

Key Achievements

Top Papers

1. 1
   <scp>EMG</scp>‐Based Dual‐Branch Deep Learning Framework With Transfer Learning for Lower Limb Motion Classification and Joint Angle Estimation

   4 citations · 2025

Key Collaborators

Contact & Links