As the pandemic slowly winds down, how e-learning evolves may be a question for education and technology workers for some time to come.  This article discuss E-learning has been dramatically boosted by the pandemic to cope with the difficulties of offline learning. In China, Bilibili is a prominent example of Internet video platforms that are using their strengths to drive the popularity of online learning. How can people advance the benefits and eliminate the disadvantages of e-learning to make it the future of learning? Literature Review finds out, although many scholars have studied the influence of e-learning, this study fills the gap of the influencing factors of e-learning on students and the obstacles to the popularization of e-learning in China based on Chinese students of all ages. This paper collects questionnaires, surveys students in primary school, junior high school, senior high school and college in China, surveys the data of e-learning's impact on students. After the proposed advantages and disadvantages of the solution and analysis. Finally, it analyzes the feasibility of e-learning in the popularization of education in China.

No abstract

H-type hypertension increases the risks of stroke and cardiovascular disease, posing a great threat to human health. Pulse diagnosis in traditional Chinese medicine (TCM) combined with deep learning can independently predict suspected H-type hypertension patients by analyzing their pulse physiological activities. However, the traditional time-domain feature extraction has a higher noise and baseline drift, affecting the classification accuracy. In this literature, we propose an effective prediction on frequencydomain pulse wave features. First, we filter time-domain pulse waves via removal of high-frequency noises and baseline shift. Second, Hilbert-Huang Transform is explored to transform time-domain pulse wave into frequency-domain waveform characterized by Melfrequency cepstral coefficients (MFCC). Finally, an improved BiLSTM model, combined with mixed attention mechanism is built to applied for prediction of H-type hypertension. With 337 clinical cases from Longhua Hospital affiliated to Shanghai University of TCM and Hospital of Integrated Traditional Chinese and Western Medicine, the 3-fold cross-validation results show that sensitivity, specificity, accuracy, F1-score and AUC reaches 93.48%, 95.27%, 97.48%, 90.77% and 0.9676, respectively. The proposed model achieves better generalization performance than the classical traditional models. In addition, we calculate the feature importance both in time-domain and frequency-domain according to purity of nodes in Random Forest and study the correlations between features and classification that has a good reference value for TCM clinical auxiliary diagnosis.

No abstract

H-type hypertension increases the risks of stroke and cardiovascular disease, posing a great threat to human health. Pulse diagnosis in traditional Chinese medicine ( TCM ) combined with deep learning can independently predict suspected H-type hypertension patients by analyzing their pulse physiological activities. However, the traditional time-domain feature extraction has a higher noise and baseline drift, affecting the classification accuracy. In this literature, we propose an effective prediction on frequency-domain pulse wave features. First, we filter time-domain pulse waves via removal of high-frequency noises and baseline shift. Second, Hilbert-Huang Transform is explored to transform time-domain pulse wave into frequency-domain waveform characterized by Mel-frequency cepstral coefficients (MFCC). Finally, an improved BiLSTM model, combined with mixed attention mechanism is built to applied for prediction of H-type hypertension. With 337 clinical cases from Longhua Hospital affiliated to Shanghai University of TCM and Hospital of Integrated Traditional Chinese and Western Medicine, the 3-fold cross-validation results show that sensitivity, specificity, accuracy, F1-score and AUC reaches 93.48%, 95.27%, 97.48%, 90.77% and 0.9676, respectively. The proposed model achieves better generalization performance than the classical traditional models. In addition, we calculate the feature importance both in time-domain and frequency-domain according to purity of nodes in Random Forest and study the correlations between features and classification that has a good reference value for TCM clinical auxiliary diagnosis.