Do Chang Oh

Papers

Total Citations

H-Index

About

Do Chang Oh is a researcher advancing the field of human-machine interaction through electromyography (EMG)-based gesture recognition. His primary research areas include biomedical signal processing, deep learning for prosthetic control, and rehabilitation robotics. Oh’s major contribution lies in developing robust methods for classifying hand gestures using surface EMG signals, which are critical for active prosthetic hands, rehabilitation robots, and AI-driven systems. His most cited work, “EMG-based hand gesture classification by scale average wavelet transform and CNN” (2019, 14 citations), introduces a novel approach combining wavelet transforms with convolutional neural networks to accurately predict grasping intentions—achieving high classification success rates for gestures like grasping, pinching, and wrist flexion. In a related study (2019, 4 citations), Oh demonstrated the practical application of deep learning CNN algorithms for classifying grasp gestures, directly targeting improvements in active prosthetic functionality. These contributions have laid groundwork for more intuitive and responsive prosthetic devices, enhancing the quality of life for amputees. Oh’s work stands out for its integration of signal processing and neural networks, offering a scalable solution for real-time gesture classification in assistive technologies.