Abstract-The dropout high rate is a serious problem in Elearning programs. Thus, it is a concern of education administrators and researchers. Predicting the dropout potential of students is a workable solution for preventing dropouts. Based on the analysis of related literature, this study selected students' personal characteristics and academic performance as input attributions. Prediction models were developed using Artificial Neural Network (ANN), Decision Tree (DT) and Bayesian Networks (BNs). A large sample of 62,375 students was utilized in the procedures of model training and testing. The results of each model were presented in a confusion matrix and were analyzed by calculating the rates of accuracy, precision, recall, and F-measure. The results suggested all of the three machine learning methods were effective for student dropout prediction, but DT presented a better performance. Finally, some suggestions were made for future research.

Abstract-E-learning has been developing rapidly in recent years; however, as the student number and market scale are growing fast, there is also a growing concern over the issue of high dropout rates in e-learning. High dropout rate not only harms both education institutions and students, but also jeopardises the development of e-learning systems. Understanding the behavioural mechanism of students' continuance learning in online programmes would be helpful for reducing the dropout rate. In order to explain students continuance intention toward e-learning, this study combines theories from the fields of information management and pedagogy. By adding two constructs, namely academic integration and social integration, from the theories of dropout as antecedent variables, an improved ECM-ISC model for e-learners' continued learning intention was put forward. Results from structural equation modeling (SEM) demonstrate a stronger explanatory power of the new model. Based on the results from empirical analyses, corresponding suggestions are proposed in the end of this paper.

The pathogenesis of portal hypertension remains unclear, and is believed to involve dysfunction of liver sinusoidal endothelial cells (LSEC), activation of hepatic stellate cells (HSC), dysregulation of endogenous hydrogen sulfide (H 2 S) synthesis, and hypoxia-induced angiogenic responses. H 2 S, a novel gas transmitter, plays an important role in various pathophysiological processes, especially in hepatic angiogenesis. Inhibition of endogenous H 2 S synthase by pharmaceutical agents or gene silencing may enhance the angiogenic response of endothelial cells. Hypoxia-inducible factor-1 (HIF-1) is the main transcription factor of hypoxia, which induces hepatic angiogenesis through up-regulation of vascular endothelial growth factor (VEGF) in HSC and LSEC. H 2 S has also been shown to be involved in the regulation of VEGF-mediated angiogenesis. Therefore, H 2 S and HIF-1 may be potential therapeutic targets for portal hypertension. The effects of H 2 S donors or prodrugs on the hemodynamics of portal hypertension and the mechanism of H 2 S-induced angiogenesis are promising areas for future research.

While online education keeps expanding, web-based institutions face high dropout rate, pushing costs up and making a negative social impact. Based on the analysis of existing research, personal characteristics and learning behavior were selected as input variables to train a dropout prediction model using neural network algorithm. The outcomes of prediction model were analyzed by calculating the rates of accuracy, precision, and precision. The results suggest this method is effective in identifying potential dropouts, and can help the online education institutions prevent dropout.

No abstract