用于缓解HD-EMG手势识别中电极偏移的Swin Transformer网络掩码自编码器
Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition
AI总结：
本文提出MAST框架，通过四种掩码策略与三路径Swin-Unet编码器-解码器结构对HD-sEMG信号进行自监督预训练，有效缓解电极偏移导致的手势识别性能下降。
摘要：
多通道表面肌电图（sEMG），也称为高密度sEMG（HD-sEMG），在提高肌电控制的手势识别性能方面发挥着关键作用。然而，基于HD-sEMG开发的模式识别模型容易受到记录条件变化的影响（例如，电极偏移导致的信号变异性），这导致跨受试者和跨会话的性能显著下降。在此背景下，本文提出了基于Swin Transformer的掩码自编码器（MAST）框架，该框架在HD-sEMG通道的掩码子集上进行训练。结合四种掩码策略，即随机块掩码、时间掩码、传感器级随机掩码和多尺度掩码，用于学习潜在表示并增强对电极偏移的鲁棒性。掩码后的数据随后通过MAST的三路径编码器-解码器结构，利用多路径Swin-Unet架构同时捕获底层HD-sEMG信号的时域、频域和基于幅值的特征。这些增强输入随后以自监督预训练的方式使用，以提高模型的泛化能力。实验结果表明，与同类方法相比，所提出的MAST框架具有优越的性能。
英文摘要：
Multi-channel surface Electromyography (sEMG), also referred to as high-density sEMG (HD-sEMG), plays a crucial role in improving gesture recognition performance for myoelectric control. Pattern recognition models developed based on HD-sEMG, however, are vulnerable to changing recording conditions (e.g., signal variability due to electrode shift). This has resulted in significant degradation in performance across subjects, and sessions. In this context, the paper proposes the Masked Autoencoder with Swin Transformer (MAST) framework, where training is performed on a masked subset of HDsEMG channels. A combination of four masking strategies, i.e., random block masking; temporal masking; sensor-wise random masking, and; multi-scale masking, is used to learn latent representations and increase robustness against electrode shift. The masked data is then passed through MAST's three-path encoder-decoder structure, leveraging a multi-path Swin-Unet architecture that simultaneously captures time-domain, frequency-domain, and magnitude-based features of the underlying HD-sEMG signal. These augmented inputs are then used in a self-supervised pre-training fashion to improve the model's generalization capabilities. Experimental results demonstrate the superior performance of the proposed MAST framework in comparison to its counterparts.
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。
