Zijun Wei

The scarcity of high-quality surface electromyography (sEMG) data, caused by ethical constraints, privacy concerns, and noise interference, poses significant challenges for developing robust deep learning models in sEMG analysis. Multi-channel sEMG signals exhibit complex inter-channel correlations reflecting neuromuscular coordination. However, existing generative methods suffer from error accumulation in sequential channel generation, insufficient inter-channel relationship modeling, and lack of physiological constraints, producing data-driven valid but physiologically implausible signals that compromise biological fidelity for clinical applications. To address these fundamental limitations, we propose a Muscle Synergy-Constrained Conditional GAN (MS-cGAN) framework that simultaneously generates multi-channel sEMG signals while preserving bio-mechanical fidelity. Firstly, A novel Graph Convolutional Network (GCN)-based generator architecture specifically tailored for sparse sEMG signals, which enables the generator to capture and model complex inter-channel relationship features through graph-based representation learning, thereby circumventing error accumulation issues by leveraging the inherent inter-channel correlations. Secondly, Integration of Muscle Synergy (MS) prior constraints as dynamic loss functions based on MS theory, which enforces generator optimization within a physiologically plausible parameter space and ensures signals maintain synergistic consistency with underlying physiological mechanisms. Lastly, experiments on IRASS datasets and public datasets (NinaPro DB1 and DB2) demonstrate that MS-cGAN significantly improves signal authenticity and enhances downstream task performance compared to traditional GANs and state-of-the-art diffusion models. The generated data effectively supplement scarce sEMG datasets and improve kinematic prediction precision for deep learning models.

The key to achieving assist-as-needed (AAN) control in rehabilitation robots lies in accurately predicting patient motion intentions. This study, for the first time, redefines motion intention prediction from the perspective of sequence-to-sequence translation by analogizing sEMG signals and joint angles to the source language and target language, respectively. The proposed 3DCNN-TF model achieves precise translation of neural control signals into kinematic representations. This model comprises three modules: an sEMG “sentence” generation module that compiles multiple sEMG sliding windows into a “sentence,” a 3DCNN module based on muscle anatomy and electrode placement to extract muscle synergy features from each “word” in the “sentence,” and a Transformer (TF) module that autoregressively generates the next joint angle as the translation result. Experimental results indicate that the 3DCNN-TF model achieves superior overall performance compared to eight baseline models and existing studies in continuously predicting wrist and knee flexion/extension angles across varying speeds. Moreover, the 3DCNN-TF achieves an optimal balance between prediction accuracy and computational efficiency while exhibiting exceptional robustness and generalizability. Specifically, the 3DCNN-TF achieves average nRMSE and R² values of (6.2%/95.5%) and (5.5%/96.2%) on wrist and knee datasets, respectively, with an average training time of less than two minutes. Additionally, the 3DCNN-TF can predict joint angles up to 300 ms in advance without compromising accuracy, which is critical for real-time AAN control in rehabilitation robots.

sEMG signals hold significant potential for motion prediction, with promising applications in areas such as rehabilitation, sports training, and human-computer interaction. However, achieving robust prediction accuracy remains a critical challenge, as even minor inaccuracies in motion prediction can severely affect the reliability and practical utility of sEMG-based systems. In this study, we propose a novel framework, muscle synergy (MS)-based graph attention networks (MSGAT-LSTM), specifically designed to address the challenges of continuous motion prediction using sparse sEMG electrodes. By leveraging MS theory and graph-based learning, the framework effectively compensates for the limitations of sparse sEMG setups and achieves significant improvements in prediction accuracy compared to existing methods. Based on MS theory, the framework calculates cosine similarity between sEMG signal features from different muscles to assign edge weights, effectively capturing their coordinated contributions to motion. The proposed framework integrates GAT for relational feature learning with LSTM networks for temporal dependency modeling, leveraging the strengths of both architectures. Experimental results on the public dataset Ninapro DB2 and a self-collected dataset demonstrate that MSGAT-LSTM achieves superior performance compared to state-of-the-art methods, including the muscle anatomy and MS-based 3DCNN, GCN-LSTM, and classic models such as CNN-LSTM, CNN, and LSTM, in terms of RMSE and R2. Furthermore, experimental results reveal that incorporating MS into GCN reduces training time by 13% compared to GCN-LSTM, significantly enhancing computational efficiency and scalability. This study highlights the potential of integrating MS theory with graph-based deep learning methods for motion prediction based on sEMG.

Post-stroke upper limb dysfunction severely impacts patients' daily life quality. Utilizing sEMG signals to predict patients' motion intentions enables more effective rehabilitation by precisely adjusting the assistance level of rehabilitation robots. Employing the muscle synergy (MS) features can establish more accurate and robust mappings between sEMG and motion intentions. However, traditional matrix factorization algorithms based on blind source separation still exhibit certain limitations in extracting MS features. This paper proposes four deep learning models to extract MS features from four distinct perspectives: spatiotemporal convolutional kernels, compression and reconstruction of sEMG, graph topological structure, and the anatomy of target muscles. Among these models, the one based on 3DCNN predicts motion intentions from the muscle anatomy perspective for the first time. It reconstructs 1D sEMG samples collected at each time point into 2D sEMG frames based on the anatomical distribution of target muscles and sEMG electrode placement. These 2D frames are then stacked as video segments and input into 3DCNN for MS feature extraction. Experimental results on both our wrist motion dataset and public Ninapro DB2 dataset demonstrate that the proposed 3DCNN model outperforms other models in terms of prediction accuracy, robustness, training efficiency, and MS feature extraction for continuous prediction of wrist flexion/extension angles. Specifically, the average nRMSE and R2 values of 3DCNN on these two datasets are (0.14/0.93) and (0.04/0.95), respectively. Furthermore, compared to existing studies, the 3DCNN outperforms musculoskeletal models based on direct collocation optimization, physics-informed GANs, and CNN-LSTM-based deep Kalman filter models when evaluated on our dataset

Upper limb functional impairments persisting after stroke significantly affect patients’ quality of life. Precise adjustment of robotic assistance levels based on patients’ motion intention using sEMG signals is crucial for active rehabilitation. This paper systematically reviews studies over the past decade on continuous prediction of upper limb single joint and multi-joint combinations motion intention using Model-Based (MB) and Model-Free (MF) approaches, based on 186 relevant studies screened from six major electronic databases. The findings indicate ongoing challenges in terms of subject composition, algorithm robustness and generalization, and feasibility for practical applications. Moreover, it suggests integrating the strengths of both MB and MF approaches to improve existing algorithms. Therefore, future research should further explore personalized MB-MF combination methods incorporating deep learning, attention mechanisms, muscle synergy features, motor unit features, and closed-loop feedback to achieve precise, real-time, and long-duration prediction of multi-joint complex movements, while further refining the transfer learning strategy for rapid algorithm deployment across days and subjects. In summary, this review summarizes the current state and challenges of research, aiming to provide inspiration for future research on predicting upper limb motion intention based on sEMG.