Skip to content
Open access

Real-time gesture classification via spike trains and multi-scale temporal features from sEMG signals

Oct 2026 · Scientific Reports · 0 citations

TL;DR

A lightweight deep learning framework that integrates multi-scale temporal features from spike trains to improve the accuracy, stability, and real-time applicability of classical gesture classification and provides a robust foundation for real-time neural decoding in advanced prosthetic control and rehabilitation interfaces.

Abstract

Classical gesture classification based on surface electromyographic (sEMG) signals often suffers from the cross-talk problem. To solve this, we propose a lightweight deep learning framework that integrates multi-scale temporal features from spike trains to improve the accuracy, stability, and real-time applicability. First, a hybrid offline-online decomposition framework based on Convolution Kernel Compensation (CKC) is adopted. In the offline phase, active signal segments are isolated with iteratively optimized filters to extract individual Motor Units (MUs). In the online phase, these pre-optimized filters are reused to enable real-time MU tracking. Second, features are extracted using Spike Count (SC) and Temporal Difference (TD) within a 200 ms sliding window with a 50 ms step, followed by gesture classification using a lightweight two-layer Multi-Layer Perceptron (MLP). The method was validated on three high-density sEMG (HD-sEMG) datasets: a 65-Gesture dataset (20 subjects), CSL-HDEMG (5 subjects), and CapgMyo DBa (10 subjects). Specifically for the 65-Gesture dataset (subset validation), the offline decomposition yielded an average of 1153.7 ± 75.2 high-quality MUs per subject, with an average Pulse-to-Noise Ratio (PNR) of 27.28 ± 2.4 dB. The system demonstrated high efficiency, with a single-window decomposition latency of less than 5 ms and a total end-to-end latency below 60 ms. In terms of classification performance, the proposed method achieved an accuracy of 91.02% ± 2.68% on this dataset. Additionally, it outperformed traditional time-domain features such as Root Mean Square on standard benchmarks, achieving 92.06% ± 11.17% on CSL-HDEMG and 86.63% ± 7.76% on CapgMyo DBa. The proposed framework achieves high precision and low latency in decoding MU discharges across diverse gesture types. By demonstrating the efficacy of multi-scale temporal features derived from decomposed motor unit spike trains and lightweight deep learning, the study provides a robust foundation for real-time neural decoding in advanced prosthetic control and rehabilitation interfaces.

Read PDF

Similar papers

Conference Oct 2026

An action-level gesture recognition method based on sEMG and channel-recalibrated multiscale temporal features

The proposed SE-MSCFormer offers an efficient and robust solution for low-sampling-rate sEMG gesture recognition and confirms that the synergy between the multi-scale temporal configuration and channel recalibration enhances overall recognition performance.

Chao Xian, Lei Liu, Bo Yang et al. · 0 citations
Open access Oct 2026

EdgeNetTF for lightweight time frequency representation learning in multiclass sEMG hand gesture recognition

Surface electromyography (sEMG)-based hand gesture recognition plays a critical role in human-machine interaction, rehabilitation, and myoelectric control. However, many deep learning models improve recognition performance by increasing architectural complexity, which limits their suitability for wearable and resourc...

Yu-Tao Li, Junghun Kim, Sang-Il Choi · 0 citations
Conference Open access Sep 2026

Spiking Convolutional Neural Network for Hand Movement Classification Using SEMG and Kinematic Data

Gesture recognition using surface Electromyography (sEMG) data is an emerging field of study that can help enable reliable human-machine interaction, with applications in the development of advanced prostheses. Despite Machine Learning and Deep Learning approaches show promising outcomes in classification of sEMG signa...

Luis Elias Salgado Solano, F. G. Castañeda · 0 citations
Open access Oct 2026

Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition

Experimental results indicate that QMM provides sharper and more discriminative scalograms than classical Morlet, Gaussian, and Mexican Hat wavelets, and a hybrid deep-learning architecture, the multi-scale frequency-attentive temporal network (MFATNet), is proposed as a novel hybrid deep learning architecture.

Hazret Tekin · 0 citations
Open access 2026

GestNet: An Adaptive Approach to Multi-Modal Gesture Recognition With Semi-Supervised Learning Through EEG and sEMG Fusion

The ability to reliably decode upper-limb motor intent from biosignals is a key requirement for next-generation Brain-Computer Interfaces (BCIs) and assistive neurorehabilitation systems. In this paper, the authors present GestNet, a semi-supervised deep learning framework for combining surface Electromyography (sEMG)...

Abdollah PourMottaghi, S. A. Zendehbad · 0 citations
Open access Oct 2026

FPGLNet: A Lightweight Frequency Prior-Gated Network for EEG Emotion Recognition

Although deep learning-based electroencephalography (EEG) emotion recognition methods have achieved promising performance, they generally depend on complex network architectures and high computational costs, which limits their deployment in resource-constrained scenarios. Meanwhile, existing approaches mainly focus on...

Yue Yuan, Ying-Zhou Bi, Shan-Rui Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.