Saved in:
Bibliographic Details
Main Authors: Jiang, Boxuan, Dai, Chenyun, Han, Can
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.13685
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918448301342720
author Jiang, Boxuan
Dai, Chenyun
Han, Can
author_facet Jiang, Boxuan
Dai, Chenyun
Han, Can
contents Deep learning-based surface electromyography (sEMG) gesture recognition is frequently bottlenecked by data scarcity and limited subject diversity. While synthetic data generation via Generative Adversarial Networks (GANs) and diffusion models has emerged as a promising augmentation strategy, these approaches often face challenges regarding training stability or inference efficiency. To bridge this gap, we propose EMGFlow, a conditional sEMG generation framework. To the best of our knowledge, this is the first study to investigate the application of Flow Matching (FM) and continuous-time generative modeling in the sEMG domain. To validate EMGFlow across three benchmark sEMG datasets, we employ a unified evaluation protocol integrating feature-based fidelity, distributional geometry, and downstream utility. Extensive evaluations show that EMGFlow outperforms conventional augmentation and GAN baselines, and provides stronger standalone utility than the diffusion baselines considered here under the train-on-synthetic test-on-real (TSTR) protocol. Furthermore, by optimizing generation dynamics through advanced numerical solvers and targeted time sampling, EMGFlow achieves improved quality-efficiency trade-offs. Taken together, these results suggest that Flow Matching is a promising and efficient paradigm for addressing data bottlenecks in myoelectric control systems. Our code is available at: https://github.com/Open-EXG/EMGFlow.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13685
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching
Jiang, Boxuan
Dai, Chenyun
Han, Can
Human-Computer Interaction
Machine Learning
Deep learning-based surface electromyography (sEMG) gesture recognition is frequently bottlenecked by data scarcity and limited subject diversity. While synthetic data generation via Generative Adversarial Networks (GANs) and diffusion models has emerged as a promising augmentation strategy, these approaches often face challenges regarding training stability or inference efficiency. To bridge this gap, we propose EMGFlow, a conditional sEMG generation framework. To the best of our knowledge, this is the first study to investigate the application of Flow Matching (FM) and continuous-time generative modeling in the sEMG domain. To validate EMGFlow across three benchmark sEMG datasets, we employ a unified evaluation protocol integrating feature-based fidelity, distributional geometry, and downstream utility. Extensive evaluations show that EMGFlow outperforms conventional augmentation and GAN baselines, and provides stronger standalone utility than the diffusion baselines considered here under the train-on-synthetic test-on-real (TSTR) protocol. Furthermore, by optimizing generation dynamics through advanced numerical solvers and targeted time sampling, EMGFlow achieves improved quality-efficiency trade-offs. Taken together, these results suggest that Flow Matching is a promising and efficient paradigm for addressing data bottlenecks in myoelectric control systems. Our code is available at: https://github.com/Open-EXG/EMGFlow.
title EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching
topic Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2604.13685