UROP Proceedings 2020-21

School of Engineering Department of Computer Science and Engineering 138 Machine Learning Approach to Creating Personalized E-Learning Paths Supervisor: MA Xiaojuan / CSE Student: ZHOU Taichang / COMP Course: UROP2100, Summer As online learning is generally becoming a significant learning method worldwide, teachers are facing new challenges. One of them is that it is not easy for teachers to find students’ learning status due to the unwillingness of students’ turning on the camera and the limit of the screen size. Therefore, we are building a new assistant system distributing students’ learning status in real-time. This report will introduce how we have designed and realized the user interface for the tool mentioned in my last UROP report based on data from the backend and the design of our experiment. For the interface implementation part, we developed a web-based interface that displays the overall condition of a set of students' learning statuses, including 1) engagement level, 2) confusion level, 3) gaze concentration, 4) emotion, and 5) some informative facial behaviors. For the experiment part, we rented and deployed a server running data collection and data integration. On the one hand, the server obtains data from each student. On the other hand, the server computes the overall statistical data and transfer it to the interface. Paper-based VR/AR Interaction Supervisor: MA Xiaojuan / CSE Student: CHAO Chung-chi / COGBM Course: UROP1100, Fall Augmented reality (AR), a tool to bring virtual objects to a real environment, has been applied in various settings such as e-shopping experience enhancement, entertainment, and assistance for people with disabilities. Applicable devices includes AR Head-Mounted Displays (HMD), AR glasses, and more. Common ways of interacting with such systems are through controllers, gestures, gaze or keyboard interactions. This study will discuss the possibility of applying voice recognition technology when commanding the systems to ease the difficulty users may face when interacting with an unfamiliar system. Various speech recognition methods and aspects of considerations that could be applied in the system will also be discussed.