Publications

This study investigates how blood flow restriction affects motoneuron characteristics and sensorimotor input, providing insights into neural adaptations under restricted blood flow conditions.

This research examines the effects of blood flow restriction on motoneuron synchronization, with implications for understanding neuromuscular adaptations and neural control mechanisms.

This study explores how noise affects deep learning-based gesture recognition systems using high-density EMG, with implications for improving robustness in neural interfaces and prosthetic control.

This paper presents a novel approach to motor unit clustering based on muscle synergies, with applications in human-machine interfacing and neural control of movement.

This research investigates how arm muscle synergies vary during drawing tasks, with potential applications in understanding motor learning and skill acquisition.

This study examines how training affects muscle synergies and kinematics during spiral tracking tasks, providing insights into motor learning and adaptation.

High-density EMG decomposition accurately extracts motor unit activity, but global white Gaussian noise severely disrupts both yield and neural drive estimation. In contrast, channel loss, electrode shift, and localized noise have minimal impact. These findings emphasize the need for high signal quality and algorithmic robustness in real-world applications.

This research examines how signal degradation affects motor unit-driven motion classification accuracy, with implications for improving robustness in neural interfaces and prosthetic control.