Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals.

Computational biomechanical analysis plays a pivotal role in understanding and improving human movements and physical functions. Although physics-based modeling methods can interpret the dynamic interaction between the neural drive to muscle dynamics and joint kinematics, they suffer from high computational latency. In recent years, data-driven methods have emerged as a promising alternative due to their fast execution speed, but label information is still required during training, which is not easy to acquire in practice. To tackle these issues, this paper presents a novel physics-informed deep learning method to predict muscle forces without any label information during model training. In addition, the proposed method could also identify personalized muscle-tendon parameters. To achieve this, the Hill muscle model-based forward dynamics is embedded into the deep neural network as the additional loss to further regulate the behavior of the deep neural network. Experimental validations on the wrist joint from six healthy subjects are performed, and a fully connected neural network (FNN) is selected to implement the proposed method. The predicted results of muscle forces show comparable or even lower root mean square error (RMSE) and higher coefficient of determination compared with baseline methods, which have to use the labeled surface electromyography (sEMG) signals, and it can also identify muscle-tendon parameters accurately, demonstrating the effectiveness of the proposed physics-informed deep learning method.

Research progress of mechanism of anti-NMDA-receptor antibodies in NPSLE / 中国免疫学杂志

Systemic lupus erythematosus (SLE)is an autoimmune disease,involving multiple organs and systems,and it is defined as neuropsychiatric systemic lupus erythematosus (NPSLE) when neuropsychiatric symptoms appear.The N-methyl-D-aspartate (NMDA) receptor is a kind of membrane-spanning ion channels' glutamate receptors,which mainly contains NR1 subunit and NR2 subunit.In recent years,the role of anti-NMDA-receptor antibodies in the pathogenesis of NPSLE has become a research hotspot,especially for anti-NR2 antibody.Therefore we review the research progress of the mechanism of the anti-NMDA-receptor antibodies in NPSLE in this paper.

Tandem Stance Avoidance Using Adaptive and Asymmetric Admittance Control for Fall Prevention.

Fall prevention is one of the most important functions of walking assistance devices for user's safety. It is preferable that these devices prevent the user from being in the state where the risk of falling is high rather than helping them recovering from falling motion. During turning, when the user is in the tandem stance, a state where both legs form a line along walking direction, a support base that is surrounded by two legs becomes small, and a stability margin becomes small. This paper therefore aims to prevent the tandem stance by using nonwearable robot "intelligent cane" for the elderly or physically challenged person. Generally, the behavior of the lower limb follows the upper body turning. This paper therefore introduces a cane robot control method which constrains the behavior of user's upper body. By adjusting an admittance parameter of the robot according to the positions of a support leg, the robot resists to turn while a support leg is on the same side of the turning direction. A swing leg on the turning direction side therefore freely moves to the turning direction, while a swing leg on the opposite direction side of turning hardly move to the turning direction.