SCTNET: Shifted Windows and Convolution Layers Transformer for Continuous Angle Estimation of Finger Joints Using sEMG

Using noninvasive technology to control prosthetics remains a real-life challenge due to the low acceptability of prosthetics stemming from their unnatural motion trajectory. The continuous angle estimation of fingers based on surface electromyography (sEMG) can effectively improve the unnatural motion trajectory. This article proposes the transformer using shifted windows and convolution networks (SCTNets) to achieve high-precision, fine-grained, and high naturalness finger continuous angle estimation. The shifted windows are used to encrease receptive field and capture multiscale sEMG signals. The transformer is used to capture the long-term dependencies within multiscale sEMG signals, facilitating the extraction of global features, while CNN is used to extract local features. We use 20 subjects of the Ninapro DB2 dataset to test the model, and compared with LS-TCN, CNN-Attention, ConvLSTM and long short-term memory network (LSTM) models. The Pearson correlation coefficient (PCC), the normalized root-mean-square error (NRMSE), and the coefficient of determination (
${R}^{{2}}$
) of the SCTNet was 84.35%, 8.85%, and 69.65%. Compared with the indicator results of other models, the SCTNet has improved by 1% (PCC), 0.15% (NRMSE), and 2.13% (
${R}^{{2}}$
) in each index, and achieved competitive results in real-time computing performance. The results indicate that the SCTNet can effectively estimate the natural continuous finger joint angles.