arXiv cs.AI· Matteo Fasulo, Giusy Spacone, Thorir Mar Ingolfsson, Yawei Li, Luca Benini, Andrea Cossettini·· 2 小时前AI 评分39
TinyMyo:可在边缘端灵活处理 EMG 信号的迷你基础模型
TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
AI 导读
TinyMyo 是一个 3.6M 参数的 Transformer 编码器,通过自监督掩码重建在公开 EMG 数据集上预训练,支持手势分类、手部运动回归、语音产生与识别等多任务。
正文 · 原文
Abstract:Objective: Surface electromyography (EMG) is widely used in biomechanics, rehabilitation, prosthetic control, and human-machine interfaces. Generalization across subjects, recording systems, and acquisition protocols remains challenging. Existing EMG foundation models (FMs) have limited support for multiple downstream tasks and deployment on low-power devices. Methods: We introduce TinyMyo, a 3.6-million-parameter Transformer encoder pre-trained on public EMG datasets using self-supervised masked reconstruction. TinyMyo supports multiple tasks with minimal changes to the task-specific prediction head. Results: We evaluated TinyMyo on hand gesture classification, hand kinematic regression, speech production, and speech recognition. For gesture classification, TinyMyo outperformed previously reported EMG FMs, achieving accuracies of 87.98% on NinaPro DB5, 97.1% on UCI-EMG, and 96.6% on EPN-612. On the GAP9 ultra-low-power microcontroller, TinyMyo achieved an inference time of 0.785 s and consumed 44.91 mJ per inference at an average power of 57.18 mW. A 1.9-million-parameter variant processed 5 s and 1 s input windows in 0.496 s and 0.089 s, respectively. Conclusion: TinyMyo demonstrates that a compact, self-supervised EMG encoder can support multiple downstream tasks and run on a low-power microcontroller. Significance: To our knowledge, this is the first deployment of an EMG FM on an ultra-low-power microcontroller, opening a path to on-device motor intent decoding, neuromuscular assessment, and human-machine interaction.
| Subjects: | Signal Processing (eess.SP); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG) |
| Cite as: | arXiv:2512.15729 [eess.SP] |
| (or arXiv:2512.15729v3 [eess.SP] for this version) | |
| https://doi.org/10.48550/arXiv.2512.15729 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1109/TBME.2026.3736157
DOI(s) linking to related resources |
Submission history
From: Giusy Spacone [view email]
[v1]
Fri, 5 Dec 2025 17:36:57 UTC (398 KB)
[v2]
Thu, 15 Jan 2026 18:05:25 UTC (396 KB)
[v3]
Tue, 17 Nov 2026 20:59:30 UTC (710 KB)
来源:arXiv cs.AI · arxiv.org