sEMG-Based Joint Angle Estimation via Hierarchical Spiking Attentional Feature Decomposition Network

2024-04-11

IEEE Robotics and Automation Letters

AI Summary

To address high inference power consumption and poor cross-subject generalization in sEMG-driven joint angle estimation, this paper proposes a multi-subject sEMG modeling framework for lower-limb rehabilitation exoskeletons. We introduce a novel hierarchical spiking attention feature decomposition architecture that achieves the first interpretable disentanglement of kinematic features from subject-specific biophysical features. Our approach integrates a Spiking Sparse Attention Encoder (SSAE), a Spiking Attention Feature Decomposition (SAFD) module, and neuromorphic computing within a dual-task joint learning framework. Evaluated on two public datasets, our method reduces inference power consumption by 37.5%–39.1% compared to Informer and Spikformer, while significantly decreasing joint angle prediction error and improving subject identification accuracy. The framework thus simultaneously achieves high estimation accuracy, ultra-low power consumption, and strong cross-subject generalization—critical for practical deployment of adaptive, energy-efficient neuroprosthetic control systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Surface electromyography (sEMG) has demonstrated significant potential in simultaneous and proportional control (SPC). However, existing algorithms for predicting joint angles based on sEMG often suffer from high inference costs or are limited to specific subjects rather than multi-subject scenarios. To address these challenges, we introduced a hierarchical Spiking Attentional Feature Decomposition Network (SAFE-Net). This network initially compresses sEMG signals into neural spiking forms using a Spiking Sparse Attention Encoder (SSAE). Subsequently, the compressed features are decomposed into kinematic and biological features through a Spiking Attentional Feature Decomposition (SAFD) module. Finally, the kinematic and biological features are used to predict joint angles and identify subject identities, respectively. Our validation on two datasets and comparison with two existing methods, Informer and Spikformer, demonstrate that SSAE achieves significant power consumption savings of 39.1% and 37.5% respectively over them in terms of inference costs. Furthermore, SAFE-Net surpasses Informer and Spikformer in recognition accuracy on both datasets. This study underscores the potential of SAFE-Net to advance the field of SPC in lower limb rehabilitation exoskeleton robots.

Problem

• sEMG signal processing
• joint motion prediction
• energy efficiency and personalization

Innovation

• SAFE-Net
• sEMG signal processing
• energy-efficient spiking representation