An innovative deep learning-driven technique for restoration of lost high-density surface electromyography signals

Abstract High-density surface electromyography (HD-sEMG) plays a crucial role in medical diagnostics, prosthetic control, and human-machine interactions. Compared to traditional bipolar sEMG, HD-sEMG employs smaller electrode spacing and sizes. This configuration not only reduces the signal collection area but also increases sensitivity to individual variations in skin impedance. Additionally, smaller high-density electrodes are more susceptible to environmental electromagnetic interference, thereby increasing the risk of signal loss and limiting the further development and application of HD-sEMG technology. To address this issue, this study introduces a novel deep learning-based technique specifically designed to restore lost HD-sEMG signals. Through an improved novel convolutional neural network (CNN), our method can reconstruct HD-sEMG signals both efficiently and accurately. Experimental results demonstrate that the proposed CNN algorithm effectively reconstructs lost HD-sEMG signals with high fidelity. The average root mean square error (RMSE) across all participants was 0.108, the mean absolute error (MAE) was 0.070, and the coefficient of determination ( $$R^2$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msup> <mml:mi>R</mml:mi> <mml:mn>2</mml:mn> </mml:msup> </mml:math> ) was 0.98. Furthermore, the model achieved an average structural similarity index measure (SSIM) of 0.96 and a peak signal-to-noise ratio (PSNR) of 29.13 dB, indicating high levels of structural similarity and signal clarity in the reconstructed data. These findings highlight the robustness and effectiveness of our method, suggesting its potential for enhancing the reliability and utility of HD-sEMG signals in real applications.