Irio De Feudis
Papers
2
Total Citations
41
H-Index
2
About
Irio De Feudis is a researcher at the forefront of human-machine interaction, specializing in the development of intuitive control strategies for wearable robotic systems. His primary research focuses on decoding motor intention from electromyography (EMG) signals, with a particular emphasis on extracting muscle synergies—the fundamental building blocks of movement. De Feudis has pioneered the use of autoencoder-based neural models for this purpose, a novel approach that surpasses traditional linear methods by capturing the complex, non-linear relationships within muscular activity. His most cited work, "Task-Oriented Muscle Synergy Extraction Using An Autoencoder-Based Neural Model" (2020, 23 citations), demonstrates how deep learning can enhance the naturalness and accuracy of myoelectric control for prosthetics and assistive devices. In his earlier foundational paper, "An undercomplete autoencoder to extract muscle synergies for motor intention detection" (2019, 18 citations), he established the core methodology that underpins his subsequent research. By enabling more robust and intuitive control of wearable robots, De Feudis’s contributions are directly advancing the field of rehabilitation engineering and assistive technology, bringing us closer to seamless human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2