No abstract

No abstract

Accurate extraction of EEG signal characteristics during exercise fatigue can provide a scientific basis for sports fatigue detection and exercise fatigue injury treatment. In this paper, based on multivariate empirical mode decomposition (MEMD) and Hilbert-Huang (HHT) algorithm, feature extraction of EEG signals during exercise fatigue is performed. MEMD extends standard experience mode to multi-channel signal processing and solves traditional algorithms. It is not suitable for self-adaptability, modal aliasing, and scale alignment. It is suitable for analyzing multi-time sequence; multi-channel and multi-scale EEG signal decomposition. After the original EEG signal passes through the MEMD, the energy mean, median and standard deviation of the EEG bands in different levels are calculated and used to form the feature set. Then the support vector machine (SVM) classifier is used to classify the extract the extracted features. The simulation results show that the proposed method can effectively extract the features of EEG signals during exercise fatigue.INDEX TERMS Exercise fatigue, EEG signal, multivariate empirical mode decomposition, Hilbert-Huang transform.

Introduction: Soccer is one of the sports with the highest incidence of injuries, generated both by the high performance required on the field and by physical conflicts between players. A fast rehabilitation is essential for the player’s performance. It has been empirically observed that an early recovery in patients’ rehabilitation is associated with physical training compared to players who received only the traditional rehabilitation. Objective: Verify the physical training influence on rehabilitation sports injuries in male soccer players. Method: 180 cases of male adolescents with sports injuries admitted to a Taiyuan hospital were selected. A division into two groups was randomly computerized to avoid statistical differences in the intensity of the injuries. The control group (14.3±2.45 years old) was treated with the standard protocol, while the experimental group (15.3±2.95 years old) received an intervention with physical training. Interviews and questionnaires were conducted involving analysis of time and severity of the injury, laterality, and location. The control group received treatment based on this information. The recovery rate and intervention satisfaction rate were collected. SPSS22.0 Statistical Software was used for student’s t-test and chi-square test. Results: Treatment efficiency was 82 (91.11%) in the control group versus 88 (97.78%) in the experimental group. The degree of dissatisfaction was 1 (2.11%) versus 8 (10%). The perceived overall satisfaction was 80 (89%) versus 87 (96.67%), (p <0.05). Conclusion: Rehabilitation associated with physical training intervention improved satisfaction and treatment efficiency. Evidence Level II; Therapeutic Studies – Investigating the results.

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.