The motor imagery brain-computer interface (MI-BCI) based on electroencephalography (EEG) is a widely used human-machine interface paradigm. However, due to the non-stationarity and individual differences among subjects in EEG signals, the decoding accuracy is limited, affecting the application of the MI-BCI. In this paper, we propose the EISATC-Fusion model for MI EEG decoding, consisting of inception block, multi-head self-attention (MSA), temporal convolutional network (TCN), and layer fusion. Specifically, we design a DS Inception block to extract multi-scale frequency band information. And design a new cnnCosMSA module based on CNN and cos attention to solve the attention collapse and improve the interpretability of the model. The TCN module is improved by the depthwise separable convolution to reduces the parameters of the model. The layer fusion consists of feature fusion and decision fusion, fully utilizing the features output by the model and enhances the robustness of the model. We improve the two-stage training strategy for model training. Early stopping is used to prevent model overfitting, and the accuracy and loss of the validation set are used as indicators for early stopping. The proposed model achieves within-subject classification accuracies of 84.57% and 87.58% on BCI Competition IV Datasets 2a and 2b, respectively. And the model achieves cross-subject classification accuracies of 67.42% and 71.23% (by transfer learning) when training the model with two sessions and one session of Dataset 2a, respectively. The interpretability of the model is demonstrated through weight visualization method.

To improve the recognition rate of lower limb actions based on surface electromyography (sEMG), an effective weighted feature method is proposed, and an improved genetic algorithm support vector machine (IGA-SVM) is designed in this paper. First, for the problem of high feature redundancy and low discrimination in the surface electromyography feature extraction process, the weighted feature method is proposed based on the correlation between muscles and actions. Second, to solve the problem of the genetic algorithm selection operator easily falling into a local optimum solution, the improved genetic algorithm-support vector machine is designed by championship with sorting method. Finally, the proposed method is used to recognize six types of lower limb actions designed, and the average recognition rate reaches 94.75%. Experimental results indicate that the proposed method has definite potentiality in lower limb action recognition.

Joint angle estimation during continuous motion based on surface electromyography (sEMG) plays a crucial role in the exoskeleton robot applications. To estimate joint angles using sEMG signals, a Hill-based muscle model (HMM) can be incorporated into forward dynamics algorithms. Nevertheless, obtaining muscle parameters remains challenging, and the strongly nonlinear ’open-loop’ system can lead to significant cumulative errors. To address these issues, this article applies a novel ’closed-loop’ sEMG-driven state space model to estimate the elbow joint angle in the human upper limb during continuous motion. The forward kinematics of the human joints are integrated with the HMM, and a torque-based musculoskeletal parameter estimation (TBMPE) is introduced to derive more accurate state transition function by utilizing angular velocity as a cost function. The observation function are constructed by utilizing sEMG features to design the ‘closed-loop’ sEMG-driven state space model. Subsequently, the particle filter (PF) algorithm is introduced to stably estimate the joint angles within the strongly nonlinear model. Experiments were conducted based on the elbow joints of six healthy subjects. The experimental results indicate that the proposed new model has an average root mean square error of 0.09 for cases with and without loads. The estimation results are better than those of similar algorithms, proving the validity of the proposed approach.