RePaint High-Density Surface Electromyography Signal Using Denoising Diffusion Probabilistic Model

High-density surface electromyography (HD-sEMG) has emerged as a powerful tool for myoelectric control and activation pattern analysis. However, signal loss due to poor electrode contact and channel corruption remains a significant challenge, limiting the reliability and practical applications of HD-sEMG signals. Conventional interpolation methods fail to effectively reconstruct corrupted signals, especially when multiple adjacent channels are affected. This paper proposes a novel HD-sEMG signal reconstruction approach based on the denoising diffusion probabilistic model (DDPM) with a repaint strategy. By leveraging a U-Net structure with spatiotemporal embedding modules that effectively learn the spatial and temporal characteristics of HD-sEMG signals, the proposed method achieves high-fidelity signal reconstruction without requiring prior knowledge of corruption patterns. Experimental evaluations are conducted on 6 corruption patterns with varying ratios (from 12.5% to 50%) using self-collected datasets (including an amputated subject) and a benchmark dataset. Results demonstrate that the proposed approach consistently outperforms interpolation methods (linear: 0.038±0.033, cubic: 0.038±0.032), generative adversarial net (GAN) (0.049±0.041), and variational autoencoder (VAE) (0.068±0.046) in terms of $nRMSE$ ($p < 0.001$), achieving the lowest error of 0.027±0.027 averaged across all corruption ratios. For $PSNR$, the proposed approach achieves the highest mean value (35.81± 17.95dB) compared to interpolation methods (linear: 33.89±26.85, cubic: 33.88± 26.88dB), GAN (31.08± 19.14dB), and VAE (26.98± 18.94dB) ($p < 0.001$). Furthermore, the proposed method maintained robust classification accuracy, achieving statistically equivalent performance to ground truth at the lower corruption ratio. The proposed HD-sEMG signal reconstruction approach offers a new solution for enhancing the fidelity and reliability of HD-sEMG signal acquisition.