Jaehwan Ryu

Papers

Total Citations

H-Index

About

Jaehwan Ryu is a researcher specializing in human motion recognition, wearable sensing technologies, and assistive robotics, with a particular focus on developing intelligent systems for lower-limb rehabilitation and power-assist devices. His work centers on leveraging surface electromyogram (sEMG) signals and inertial measurement unit (IMU) sensors to enable accurate, real-time detection and prediction of human gait patterns — a critical challenge in the field of exoskeleton and gait-assist robot control. Ryu's most impactful contribution, his 2019 paper on gait sub-phase detection and prediction using a user-adaptive classifier (35 citations), addresses longstanding limitations of EMG-based pattern recognition systems, including signal variability across users and sessions. By integrating sEMG, pressure sensors, and knee angle data with adaptive machine learning models, he advanced the practical viability of personalized assistive robotics. His earlier 2016 work introduced a novel gait phase recognition framework using a GPES library and integrated spectral matching filter, laying foundational groundwork for more robust EMG-based control systems. Together, these contributions reflect Ryu's sustained commitment to bridging the gap between biomechanical sensing and intelligent robotic assistance, making his research highly relevant to students and engineers working at the intersection of rehabilitation engineering and human-robot interaction.