Cheikh Latyr Fall
Papers
5
Total Citations
407
H-Index
5
About
Cheikh Latyr Fall is a researcher at the intersection of biomedical engineering, machine learning, and assistive robotics, whose work has significantly advanced the development of intelligent human-machine interfaces for individuals living with disabilities. His research focuses on surface electromyography (sEMG) signal processing, deep learning-based gesture recognition, and adaptive wireless control systems for robotic prosthetics. Fall's most influential contribution, his 2017 paper on transfer learning for sEMG hand gesture recognition using convolutional neural networks (174 citations), tackled a critical bottleneck in the field — the impracticality of collecting large training datasets from individual users — by demonstrating how transfer learning could dramatically reduce this burden. Building on this, his 2016 work applying CNNs with frequency-domain features to robotic arm guidance (138 citations) established a robust framework for real-time prosthetic control. Beyond neural signal decoding, Fall has championed accessible, user-centered design through his multimodal body-machine interfaces, which leverage wearable wireless sensor networks to accommodate varying levels of residual motor function. Together, these contributions represent a coherent and impactful research vision: making intelligent assistive robotics genuinely practical and personalized for amputees and individuals with upper-body disabilities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5