Human-machine interaction, particularly in prosthetic and robotic control, has seen progress with gesture recognition via surface electromyographic (sEMG) signals.However, classifying similar gestures that produce nearly identical muscle signals remains a challenge, often reducing classification accuracy. Traditional deep learning models for sEMG gesture recognition are large and computationally expensive, limiting their deployment on resource-constrained embedded systems. In this work, we propose WaveFormer, a lightweight transformer-based architecture tailored for sEMG gesture recognition. Our model integrates time-domain and frequency-domain features through a novel learnable wavelet transform, enhancing feature extraction. In particular, the WaveletConv module, a multi-level wavelet decomposition layer with depthwise separable convolution, ensures both efficiency and compactness. With just 3.1 million parameters, WaveFormer achieves 95% classification accuracy on the EPN612 dataset, outperforming larger models. Furthermore, when profiled on a laptop equipped with an Intel CPU, INT8 quantization achieves real-time deployment with a 6.75 ms inference latency.
@article{arxiv.2506.11168,
title = {WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition},
author = {Yanlong Chen and Mattia Orlandi and Pierangelo Maria Rapa and Simone Benatti and Luca Benini and Yawei Li},
journal= {arXiv preprint arXiv:2506.11168},
year = {2025}
}
Comments
6 pages, 3 figures, accepted to IEEE EMBS Conference on Neural Engineering (NER) 2025. Code and data are available at https://github.com/ForeverBlue816/WaveFormer