The automatic recognition technology of muscle fatigue has widespread application in the field of kinesiology and rehabilitation medicine. In this paper, we used surface electromyography (sEMG) to study the recognition of leg muscle fatigue during circuit resistance training. The purpose of this study was to solve the problem that the sEMG signals have a lot of noise interference and the recognition accuracy of the existing muscle fatigue recognition model is not high enough. First, we proposed an improved wavelet threshold function denoising algorithm to denoise the sEMG signal. Then, we build a muscle fatigue state recognition model based on long short-term memory (LSTM), and used the Holdout method to evaluate the performance of the model. Finally, the denoising effect of the improved wavelet threshold function denoising method proposed in this paper was compared with the denoising effect of the traditional wavelet threshold denoising method. We compared the performance of the proposed muscle fatigue recognition model with that of particle swarm optimization support vector machine (PSO-SVM) and convolutional neural network (CNN). The results showed that the new wavelet threshold function had better denoising performance than hard and soft threshold functions. The accuracy of LSTM network model in identifying muscle fatigue was 4.89% and 2.47% higher than that of PSO-SVM and CNN, respectively. The sEMG signal denoising method and muscle fatigue recognition model proposed in this paper have important implications for monitoring muscle fatigue during rehabilitation training and exercise.
Objectives To explore the characteristics of thrombosis in critically ill patients with Omicron infection and the therapeutic value of prophylactic low molecular weight heparin (LMWH) treatment. MethodsA single center, retrospective cohort study included critically ill adult patients with Omicron variant of SARS-CoV-2 admitted to Peking University Third Hospital from December 7, 2022, to February 8, 2023. The patients were categorized into two groups based prophylactic LMWH. Propensity score (PS) matching was used to match patients (1: 1 ratio) based on the predefined criteria. General clinical information and laboratory parameters were compared. This study was retrospectively registered at Chinese Clinical Trail Registry (ChiCTR2300067434). ResultsFour hundred and fifty-two patients and 360 patients were included before and after PS matching. There were no statistical differences in mortality, the incidence of pulmonary embolism, arterial thrombosis or bleeding between the anticoagulation group and non-coagulation group before and after PS matching. There were 91 thrombotic events in 82 patients (18.14%), of which 54 cases (59.34%) were lower limb intermuscular vein thrombosis, 3 cases (3.30%) were pulmonary embolism, 14 cases (15.38%) were acute myocardial infarction and 3 cases (3.30%) were acute cerebral infarction. The thrombotic event resulted in the death of 5 patients. D-dimer increased in 385 cases (85.56%). On the 1st, 3rd, 6th and 9th day, the concentration of D-dimer in the anticoagulant group was higher than that in the non-anticoagulant group (P=0.006, 0.001, 0.024 and 0.006, respectively). ConclusionsAlthough thrombosis and coagulation disorders are still common complications of COVID-19, it is not the direct cause of most death in COVID-19 patients caused by Omicron. The role of prophylactic anticoagulation treatment for Omicron-infected patients needs further study.