Takuto Soeda

Papers

Total Citations

H-Index

About

Dr. Takuto Soeda is a researcher at the forefront of human-machine interaction, specializing in the integration of deep learning with biomedical signal processing. His primary research focuses on gesture recognition using surface electromyography (sEMG) data, with the critical goal of advancing myoelectric prosthetic control. In his most cited work, "Deep Learning for Gesture Recognition based on Surface EMG Data" (2021, 12 citations), Soeda proposed a novel deep learning framework that maps sEMG signals to individual finger motions, addressing a key challenge in creating intuitive, everyday prosthetic hand functionality. This contribution is pivotal for developing robotic prostheses that can accurately interpret a user's muscle signals, enabling natural and precise hand gestures. By leveraging deep neural networks, Soeda's work enhances the robustness and accuracy of gesture classification, moving beyond traditional signal processing limitations. His research holds significant promise for improving the quality of life for amputees, bridging the gap between biological intent and robotic execution. With a growing citation impact, Soeda continues to be a notable contributor to the fields of rehabilitation robotics and intelligent human-machine interfaces.