UROP Proceedings 2020-21

School of Engineering Department of Computer Science and Engineering 148 Research on Mining Course Structure Supervisor: WONG Raymond Chi Wing / CSE Student: HSU Shang-ling / COSC Course: UROP3100, Fall Student performance prediction is essential especially during the pandemic since automatic, personalized education has become more common thanks to the switch to online teaching mode. In this research, we aim to design a model that can accurately predict students' future performance given their performance in the past. Based on the previous progress report regarding the literature review, we have proposed a preliminary model. Since the model is based on many assumptions regarding the attributes of the data, in this report, we will examine those assumptions by answering a few research questions with experiments on our targeted dataset, which can lead to possible improvement of the model design. Research on Mining Course Structure Supervisor: WONG Raymond Chi Wing / CSE Student: ZHOU Jiaxi / DSCT Course: UROP1100, Spring For more than a decade, various recommendation systems have been developed and widely applied in multiple internet areas. As the problem of information overload heating up, internet users' demand for information is increasing, and recommendation systems are playing an increasingly important role in the digitalization of various fields. Among all kinds of recommendation systems, the session-based recommendation has been becoming increasingly favored by both academia and industry applications (Gorakala & Usuelli, 2015). This article will review the major recommendation systems and especially focus on some recent discoveries in the session-based recommendation. Research on Mining Course Structure Supervisor: WONG Raymond Chi Wing / CSE Student: LIU Ziming / COSC Course: UROP2100, Spring In this UROP 2100 project, students should perform data mining tasks on all important components of courses on a given list to extract their structure and correlation among different courses. As a well-developed data mining application, T-Music Web System is a maintainable and scalable system to deploy T-Music algorithm, which is an innovative algorithm that can compose a series of musical notes from a given series of input lyrics. Last semester we have learned JavaScript in order to read the code of the project and propose some ideas for the future work of the project. Before realizing it, I followed the advice from the project developer to start from learning JavaScript React. Besides, since I have finished learning of data structure and algorithm, I read papers that I have thought to be incomprehensible before. I will demonstrate what have learn in two parts.