Alessio Burrello
Papers
4
Total Citations
81
H-Index
4
About
Alessio Burrello is a researcher specializing in embedded machine learning, edge computing, and human-machine interfaces, with a particular focus on deploying sophisticated neural networks on ultra-low-power hardware. His most impactful contributions center on surface electromyography (sEMG)-based gesture recognition and hand kinematics regression, addressing the critical challenge of running advanced deep learning models on resource-constrained microcontrollers for prosthetics and rehabilitation applications. His 2022 paper introducing Bioformers — a transformer architecture optimized for ultra-low-power sEMG gesture recognition — has garnered 30 citations, demonstrating the field's strong interest in bridging state-of-the-art AI with practical wearable deployment. Complementing this, his work on Temporal Convolutional Networks for hand kinematics regression on edge devices (29 citations) further establishes his expertise in efficient neural architecture design. Notably, Burrello has also tackled the real-world problem of sEMG signal time-variability through on-device incremental learning, addressing a key barrier to clinical adoption. More recently, he has extended his edge AI expertise to nano-UAV pose estimation through neural architecture search, signaling a broader impact across robotics and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4