Event-Driven Implementation of a Physical Reservoir Computing Framework for superficial EMG-based Gesture Recognition

2025-03-10

AI Summary

To address high latency and power consumption in cloud-dependent surface electromyography (sEMG) gesture recognition for wearable health devices, this paper proposes a near-sensor, event-driven edge inference framework. Methodologically, it introduces the first integration of event-driven sEMG spike encoding with a hardware-efficient spiking Rotational Neuron-based Physical Reservoir (sRNR), supporting a fully spike-based delta learning rule for low-overhead spatiotemporal feature extraction and online training. Key contributions include: (i) the first spike-based physical reservoir architecture tailored for sEMG; (ii) a co-optimized event-encoding and sRNR design aligned with sEMG signal characteristics; and (iii) end-to-end learning entirely within the spike domain. Evaluated on a large-scale public sEMG dataset, the system achieves 80.3% accuracy—5.7% higher than conventional classifiers—while significantly reducing inference latency and energy consumption, thereby demonstrating feasibility for embedded real-time deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Wearable health devices have a strong demand in real-time biomedical signal processing. However traditional methods often require data transmission to centralized processing unit with substantial computational resources after collecting it from edge devices. Neuromorphic computing is an emerging field that seeks to design specialized hardware for computing systems inspired by the structure, function, and dynamics of the human brain, offering significant advantages in latency and power consumption. This paper explores a novel neuromorphic implementation approach for gesture recognition by extracting spatiotemporal spiking information from surface electromyography (sEMG) data in an event-driven manner. At the same time, the network was designed by implementing a simple-structured and hardware-friendly Physical Reservoir Computing (PRC) framework called Rotating Neuron Reservoir (RNR) within the domain of Spiking neural network (SNN). The spiking RNR (sRNR) is promising to pipeline an innovative solution to compact embedded wearable systems, enabling low-latency, real-time processing directly at the sensor level. The proposed system was validated by an open-access large-scale sEMG database and achieved an average classification accuracy of 74.6% and 80.3% using a classical machine learning classifier and a delta learning rule algorithm respectively. While the delta learning rule could be fully spiking and implementable on neuromorphic chips, the proposed gesture recognition system demonstrates the potential for near-sensor low-latency processing.

Problem

• Real-time gesture recognition using sEMG data
• Low-latency processing for wearable health devices
• Neuromorphic computing for efficient biomedical signal processing

Innovation

• Event-driven sEMG spiking data processing
• Rotating Neuron Reservoir in Spiking Neural Network
• Low-latency, real-time wearable system processing