Spiking Neural Network Decoders of Finger Forces from High-Density Intramuscular Microelectrode Arrays

2025-09-04

AI Summary

This study addresses natural finger control via high-density intramuscular microelectrode arrays by proposing a lightweight spiking neural network (SNN) decoding framework for continuous, isometric single-finger force estimation directly from motor unit spike trains (MUPs). Departing from conventional preprocessing and buffering requirements, the method employs a shallow SNN architecture with two input modalities: raw MUPs and spike-encoded intramuscular EMG. A systematic evaluation quantifies the accuracy–efficiency trade-off. During 15% maximum voluntary contraction tasks, the framework achieves synchronous proportional multi-finger force decoding with accuracy comparable to state-of-the-art methods, while reducing memory footprint by 62% and achieving a mean latency of 32 ms. The core contributions are: (i) the first end-to-end SNN decoding paradigm specifically designed for intramuscular MUPs; and (ii) a solution that simultaneously delivers high decoding accuracy, ultra-low latency, robustness to signal variability, and feasibility for embedded deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Restoring naturalistic finger control in assistive technologies requires the continuous decoding of motor intent with high accuracy, efficiency, and robustness. Here, we present a spike-based decoding framework that integrates spiking neural networks (SNNs) with motor unit activity extracted from high-density intramuscular microelectrode arrays. We demonstrate simultaneous and proportional decoding of individual finger forces from motor unit spike trains during isometric contractions at 15% of maximum voluntary contraction using SNNs. We systematically evaluated alternative SNN decoder configurations and compared two possible input modalities: physiologically grounded motor unit spike trains and spike-encoded intramuscular EMG signals. Through this comparison, we quantified trade-offs between decoding accuracy, memory footprint, and robustness to input errors. The results showed that shallow SNNs can reliably decode finger-level motor intent with competitive accuracy and minimal latency, while operating with reduced memory requirements and without the need for external preprocessing buffers. This work provides a practical blueprint for integrating SNNs into finger-level force decoding systems, demonstrating how the choice of input representation can be strategically tailored to meet application-specific requirements for accuracy, robustness, and memory efficiency.

Problem

• Decoding finger forces from motor unit activity
• Evaluating SNN configurations for accuracy and efficiency
• Comparing input modalities for tailored application requirements

Innovation

• Spiking neural networks decode finger forces
• Motor unit spike trains from microelectrode arrays
• Minimal latency decoding with reduced memory requirements