Soheil Zabihi

Papers

Total Citations

H-Index

About

Soheil Zabihi is a leading researcher in the intersection of artificial intelligence, deep learning, and neurorobotics, with a primary focus on advancing myoelectric control for prosthetic devices. His work centers on developing novel neural network architectures to decode surface electromyography (sEMG) signals for hand gesture recognition, directly improving the functionality and responsiveness of neuroprosthetic limbs. Zabihi’s major contributions include pioneering the use of dilated convolutional neural networks (CNNs) and hybrid deep architectures, such as the DCNN and HDNN models, which significantly enhance the accuracy and robustness of gesture classification from sEMG data. His most-cited paper (2019, 35 citations) introduced a dilated CNN framework that outperformed traditional methods, while his 2020 follow-up (27 citations) expanded on this with hybrid designs, demonstrating the potential of deep learning to revolutionize assistive robotic systems. With over 60 combined citations for these key works, Zabihi’s research is shaping the future of neurorobotic prostheses, offering hope for more intuitive and natural control for amputees. His innovative architectures are widely recognized as foundational steps toward seamless human-machine interaction in rehabilitation technology.