Continuous Estimation of sEMG-Based Upper-Limb Joint Angles in the Time–Frequency Domain Using a Scale Temporal–Channel Cross-Encoder

• Published in: Actuators Vol. 14; no. 8; p. 378
• Main Authors: Han, Xu, Chen, Haodong, Cheng, Xinyu, Zhao, Ping
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 31.07.2025
• Subjects: Accuracy; Coders; Correlation coefficients; Data collection; Datasets; Deep learning; Elbow; Elbow (anatomy); Electromyography; Experiments; Fourier transforms; Frequency domain analysis; Limbs; Neural networks; Rehabilitation; Root-mean-square errors; Sensors; Stroke; Test sets; Time-frequency analysis; Wavelet transforms
• ISSN: 2076-0825; 2076-0825
• DOI: 10.3390/act14080378

Surface electromyographic (sEMG) signal-driven joint-angle estimation plays a critical role in intelligent rehabilitation systems, as its accuracy directly affects both control performance and rehabilitation efficacy. This study proposes a continuous elbow joint angle estimation method based on time–frequency domain analysis. Raw sEMG signals were processed using the Short-Time Fourier Transform (STFT) to extract time–frequency features. A Scale Temporal–Channel Cross-Encoder (STCCE) network was developed, integrating temporal and channel attention mechanisms to enhance feature representation and establish the mapping from sEMG signals to elbow joint angles. The model was trained and evaluated on a dataset comprising approximately 103,000 samples collected from seven subjects. In the single-subject test set, the proposed STCCE model achieved an average Mean Absolute Error (MAE) of 2.96±0.24∘, Root Mean Square Error (RMSE) of 4.41±0.45∘, Coefficient of Determination (R2) of 0.9924±0.0020, and Correlation Coefficient (CC) of 0.9963±0.0010. It achieved a MAE of 3.30∘, RMSE of 4.75∘, R2 of 0.9915, and CC of 0.9962 on the multi-subject test set, and an average MAE of 15.53±1.80∘, RMSE of 21.72±2.85∘, R2 of 0.8141±0.0540, and CC of 0.9100±0.0306 on the inter-subject test set. These results demonstrated that the STCCE model enabled accurate joint-angle estimation in the time–frequency domain, contributing to a better motion intent perception for upper-limb rehabilitation.