Accurately decoding human motion intentions from surface electromyography (sEMG) is essential for myoelectric control and has wide applications in rehabilitation robotics and assistive technologies. However, existing sEMG-based motion estimation methods often rely on subject-specific musculoskeletal (MSK) models that are difficult to calibrate, or purely data-driven models that lack physiological consistency. This paper introduces a novel Physics-Embedded Neural Network (PENN) that combines interpretable MSK forward-dynamics with data-driven residual learning, thereby preserving physiological consistency while achieving accurate motion estimation. The PENN employs a recursive temporal structure to propagate historical estimates and a lightweight convolutional neural network for residual correction, leading to robust and temporally coherent estimations. A two-phase training strategy is designed for PENN. Experimental evaluations on six healthy subjects show that PENN outperforms state-of-the-art baseline methods in both root mean square error (RMSE) and R2metrics.

Muscle force and joint kinematics estimation from surface electromyography (sEMG) are essential for real-time biomechanical analysis of the dynamic interplay among neural muscle stimulation, muscle dynamics, and kinetics. Recent advances in deep neural networks (DNNs) have shown the potential to improve biomechanical analysis in a fully automated and reproducible manner. However, the small sample nature and physical interpretability of biomechanical analysis limit the applications of DNNs. This paper presents a novel physics-informed low-shot adversarial learning method for sEMG-based estimation of muscle force and joint kinematics. This method seamlessly integrates Lagrange's equation of motion and inverse dynamic muscle model into the generative adversarial network (GAN) framework for structured feature decoding and extrapolated estimation from the small sample data. Specifically, Lagrange's equation of motion is introduced into the generative model to restrain the structured decoding of the high-level features following the laws of physics. A physics-informed policy gradient is designed to improve the adversarial learning efficiency by rewarding the consistent physical representation of the extrapolated estimations and the physical references. Experimental validations are conducted on two scenarios (i.e. the walking trials and wrist motion trials). Results indicate that the estimations of the muscle forces and joint kinematics are unbiased compared to the physics-based inverse dynamics, which outperforms the selected benchmark methods, including physics-informed convolution neural network (PI-CNN), vallina generative adversarial network (GAN), and multi-layer extreme learning machine (ML-ELM).

Brain-computer interface (BCI) can provide a direct communication path between the human brain and an external device. The steady-state visual evoked potential (SSVEP)-based BCI has been widely explored in the past decades due to its high signal-to-noise ratio and fast communication rate. Several spatial filtering methods have been developed for frequency detection. However the temporal knowledge contained in the SSVEP signal is not effectively utilized. In this study, we propose a canonical correlation analysis (CCA)-based spatio-temporal filtering method to improve target classification. The training signal and two types of template signals (i.e. individual template and artificial sine-cosine reference) are first augmented via temporal information. Three sets of augmented data are then concatenated by trials. The CCA is performed twice, between the newly obtained training data and each template. The trained four spatial filters can be applied in the following test process. A public benchmark dataset was used to evaluate the performance of the proposed method and the other three comparing methods, such as CCA, MsetCCA, and TRCA. The experimental results indicate that the proposed method yields significantly higher performance. This paper also explored the effects of the number of electrodes and training blocks on classification accuracy. The results further demonstrated the effectiveness of the proposed method in SSVEP detection.

EMG-driven musculoskeletal model has been broadly used to detect human intention in rehabilitation robots. This approach computes muscle-tendon force and translates it to the joint kinematics. However, the muscle-tendon parameters of the musculoskeletal model are difficult to measure in vivo and varied across subjects. In this study, a direct collocation (DC) method is proposed to optimize the subject-specific parameters in a wrist musculoskeletal model. The resultant optimized parameters are used to estimate the wrist flexion/extension motion. The estimation performance is compared with the parameters optimized by the genetic algorithm. Experiment results show that the DC methods have a similar performance compared with GA, in which the mean correlation are 0.96 and 0.93 for the genetic algorithm and DC method respectively. But the direction collocation method requires less optimization time.