arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.01855cs.LGcs.AIeess.SP
收藏

用于低密度sEMG的Time2Vec变换器鲁棒手势识别

Time2Vec Transformer for Robust Gesture Recognition from Low-Density sEMG

University “Ss. Cyril and Methodius”(圣西里尔与美多德大学);Faculty of Electrical Engineering and Information Technologies(电气工程与信息技术学院)

Blagoj Hristov, Hristijan Gjoreski, Vesna Ojleska Latkoska, Gorjan Nadzinski

AI总结:

本文提出Time2Vec变换器,通过低密度sEMG实现鲁棒手势识别,展示了高保真时间嵌入对低空间分辨率的补偿能力,提升了假肢控制的准确性和效率。

摘要:

准确且响应迅速的肌电假肢控制通常依赖于复杂的、密集的多传感器阵列,这限制了消费者可及性。本文提出了一种新颖且数据高效的深度学习框架,旨在通过最少的传感器硬件实现精确和准确的控制。利用一个包含8名受试者的外部数据集,我们的方法实现了一种优化的Transformer混合架构,专为稀疏的两通道表面肌电图(sEMG)设计。与标准架构使用固定位置编码不同,我们整合了Time2Vec可学习的时间嵌入,以捕捉生物信号中固有的随机时间扭曲。此外,我们采用归一化的加法融合策略,对空间和时间特征的潜在分布进行对齐,防止标准实现中常见的破坏性干扰。利用两阶段课程学习协议以确保在数据稀缺的情况下实现鲁棒的特征提取。所提出的架构在10类运动集上实现了最先进的多受试者F1分数为95.7%±0.20%,统计上优于标准Transformer和递归CNN-LSTM模型。架构优化表明,空间和时间维度之间平衡分配模型容量可获得最高稳定性。此外,虽然直接转移到新未见受试者导致准确性下降,但利用仅两个试次每手势的快速校准协议,性能从21.0%±2.98%提升至96.9%±0.52%。通过验证高保真时间嵌入可以补偿低空间分辨率,本工作挑战了高密度传感的必要性。所提出的框架提供了一种稳健、成本效益的蓝图,用于下一代假肢接口,能够快速个性化。

英文摘要:

Accurate and responsive myoelectric prosthesis control typically relies on complex, dense multi-sensor arrays, which limits consumer accessibility. This paper presents a novel, data-efficient deep learning framework designed to achieve precise and accurate control using minimal sensor hardware. Leveraging an external dataset of 8 subjects, our approach implements a hybrid Transformer optimized for sparse, two-channel surface electromyography (sEMG). Unlike standard architectures that use fixed positional encodings, we integrate Time2Vec learnable temporal embeddings to capture the stochastic temporal warping inherent in biological signals. Furthermore, we employ a normalized additive fusion strategy that aligns the latent distributions of spatial and temporal features, preventing the destructive interference common in standard implementations. A two-stage curriculum learning protocol is utilized to ensure robust feature extraction despite data scarcity. The proposed architecture achieves a state-of-the-art multi-subject F1-score of 95.7% $\pm$ 0.20% for a 10-class movement set, statistically outperforming both a standard Transformer with fixed encodings and a recurrent CNN-LSTM model. Architectural optimization reveals that a balanced allocation of model capacity between spatial and temporal dimensions yields the highest stability. Furthermore, while direct transfer to a new unseen subject led to poor accuracy due to domain shifts, a rapid calibration protocol utilizing only two trials per gesture recovered performance from 21.0% $\pm$ 2.98% to 96.9% $\pm$ 0.52%. By validating that high-fidelity temporal embeddings can compensate for low spatial resolution, this work challenges the necessity of high-density sensing. The proposed framework offers a robust, cost-effective blueprint for next-generation prosthetic interfaces capable of rapid personalization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑