Jie Kong’s research while affiliated with Xi'an Shiyou University and other places

In recent years, data mining techniques have been widely applied in education. However, studies on analyzing the similarity or difference of the same learning pattern in different student groups are still rare. In this study, a data mining method which combines the concepts of contrast sets mining and association rules mining is introduced. It could provide quantitative analysis for the similarity and difference of association rules obtained from the academic records datasets of multiple grades. On this basis, student psychological features are deduced without being sensitive to privacy. The work in this study can help educators understand the learning and psychological states of students in different grades, so as to formulate teaching plans that are more targeted to improve their academic performance.

The job-hunting and graduate school admission of college students are important tasks in universities. To investigate the impact of students’ academic achievement to their graduation whereabouts, Self-Organizing Maps is introduced in this study. Through the analysis of experiment results, the features of academic performance in different students’ graduation whereabouts segments are proposed. The findings could help educators better understand the relationship between academic performance and graduation whereabouts.

In recent years, although Optical Character Recognition (OCR) has made considerable progress, low-resolution text images commonly appearing in many scenarios may still cause errors in recognition. For this problem, the technique of Generative Adversarial Network in super-resolution processing is applied to enhance the resolution of low-quality text images in this study. The principle and the implementation in TensorFlow of this technique are introduced. On this basis, a system is proposed to perform the resolution enhancement and OCR for low-resolution text images. The experimental results indicate that this technique could significantly improve the accuracy, reduce the error rate and false rejection rate of low-resolution text images identification.

While the data mining in education field gained more and more popularity in recent years, there have many research endeavors to find association rules in students' academic situation. The current methods normally apply traditional association rules mining technique to identify those rules. However, traditional association rules mining technique can not identify difference between different types of students' academic situation. To solve this problems, we applied a novel contrast target rules mining method in this paper. Real world data set from Computer Science department of a university of China, the empirical results show the difference characteristics of different types of students in their academic situation.

In major colleges and universities, in order to mobilize students enthusiasm for studying and participating in extracurricular activities, all colleges make an evaluation on students comprehensive quality and set different rewards regulations for the various level. The main way is to provide financial incentives, they distribute scholarship for students of meeting requirements. The Decision Tree algorithm is frequently used all the time, however, because of the tree node selected is based on attribute's mutual information, which will lead to some crucial attribute lost their decisive role. Therefore, in this paper, we focused on predicting whether students obtain scholarship on the comprehensive quality of students with Naive Bayes algorithm.