Spinal-inspired spiking neural network improves finger movement decoding
A spinal-inspired spiking neural network for continuous finger-joint kinematics estimation from high-density surface EMG
Human-Computer Interaction
Summary
Figuring out finger movements from muscle signals is tricky, especially when tracking multiple joints at once. The authors created a special kind of artificial neural network inspired by how the spine processes signals naturally, using precise spike-like patterns. This new network does better than standard methods in predicting finger positions from muscle activity, and it also helps explain how the brain might control these movements. Such models can someday help build better devices to assist people recovering motor abilities.
What this means in practice
- •For rehabilitation engineers: Design neural prosthetics that decode finger joint movements more accurately from muscle signals for motor rehabilitation devices.
- •For biomedical device developers: Create control systems for assistive hand exoskeletons using physiologically inspired neural models predicting finger motion from EMG data.$Commercial implications: Enables more natural and precise control of hand orthotics by linking EMG signals to finger joint movement patterns.
Authors
Cristian David Guerrero-Mendez, Leonardo Abdala Elias
Abstract
Decoding simultaneous and proportional finger kinematics from high-density surface electromyography (HD sEMG) remains challenging. Although data-driven methods have shown promising performance for finger movement decoding, their limited physiological interpretability remains a relevant limitation. This study proposes and evaluates a spiking neural network (SNN) that incorporates spinal-inspired structures and mechanisms to predict multi-joint finger kinematics from HD sEMG signals. The spinal-inspired SNN includes a spike-encoding computational model with input-noise variability, a phenomenological representation of Henneman's size principle, and excitation/inhibition (E/I) balance. HD sEMG and kinematic data were collected from 23 healthy participants performing grasping tasks under different elbow and wrist postures. Performance was assessed using six prediction metrics and compared against six baseline machine learning and deep learning methods. The proposed method showed a large and significant ($p<0.05$, rank-biserial correlation $r_{rb}>0.7$) improvement over all baseline methods across all accuracy metrics. Performance improved significantly with increasing spike encoder firing rates up to approximately 128 Hz, and with more regular input spike trains compared with a Poisson-like encoder. In contrast, the E/I balance did not significantly affect the decoding performance of the algorithm. The firing rate and inter-spike interval statistics of the SNN differed significantly across motor tasks. These results demonstrate that incorporating neurophysiological principles into SNNs improves prediction performance while providing additional physiological interpretability for simultaneous and proportional finger-kinematics decoding. This approach represents a promising step toward physiology-informed neural networks, with potential applications in motor rehabilitation.