Objective To determine if supervised hospital-based exercise can maintain the benefits of functional exercise ability and quality of life gained from a pulmonary rehabilitation program in COPD.Methods A prospective and randomized study was carried out. Following completion of an eight-week pulmonary rehabilitation program in hospital, 43 COPD patients were recruited and randomized into either a supervised group ( supervised, every 10 days, hospital-based exercise, 22 cases ) or a control group ( unsupervised home exercise,21 cases) and followed for 12 months. Measurements were taken at baseline and 12 months later. Exercise measurements include six-minute walk test( 6MWT) and pulmonary function test. Quality of life was measured using the Chronic Respiratory Questionnaire ( CRQ) . Results After 12 months of different exercise program,6MWT in the supervised group was significantly longer than that in the unsupervised group[ ( 532. 0 ±168. 4) m vs ( 485. 0 ±151. 6) m, P lt; 0. 05] . There was no significant difference in pulmonary function between the two groups. The quality of life of the supervised group was higher than that of the unsupervised group( 114. 6 ±20. 8 vs 105. 6 ±21. 7, P lt;0. 05) . Conclusions After the completion of pulmonary rehabilitation program, a supervised, every 10 days, hospital-based following exercise program can maintain better functional exercise capacity and quality of life compared to home exercise in COPD patients.
Aiming at the problem that the feature extraction ability of forehead single-channel electroencephalography (EEG) signals is insufficient, which leads to decreased fatigue detection accuracy, a fatigue feature extraction and classification algorithm based on supervised contrastive learning is proposed. Firstly, the raw signals are filtered by empirical modal decomposition to improve the signal-to-noise ratio. Secondly, considering the limitation of the one-dimensional signal in information expression, overlapping sampling is used to transform the signal into a two-dimensional structure, and simultaneously express the short-term and long-term changes of the signal. The feature extraction network is constructed by depthwise separable convolution to accelerate model operation. Finally, the model is globally optimized by combining the supervised contrastive loss and the mean square error loss. Experiments show that the average accuracy of the algorithm for classifying three fatigue states can reach 75.80%, which is greatly improved compared with other advanced algorithms, and the accuracy and feasibility of fatigue detection by single-channel EEG signals are significantly improved. The results provide strong support for the application of single-channel EEG signals, and also provide a new idea for fatigue detection research.