In Partial Fulfillment of the Requirements for the Degree of Master of Science
will defend his thesis
Design and Implementation of Real-time Student Performance Evaluation and Feedback System
Undergraduate education is challenged by high dropout rates and by delayed student graduation due to dropping courses or having to repeat courses due to low academic performance. In this context, an early prediction of student performance may help students to understand where they stand amongst their peers and challenge themselves. Moreover, to identify students who need special attention and providing appropriate interventions, such as mentoring and conducting review sessions. The proposed system addresses these two issues; its goal is the design and implementation of real-time student performance evaluation and feedback system (RSPEF) to improve graduation rates. RSPEF is an interactive, web-based system consisting of a Predictive Analysis System (PAS) that used machine learning techniques to interpolate student performance into future, and an Emergency Warning System (EWS) that identifies poor performing students in courses. A unified representation of student background and student performance data is collected that is suitable to be used to assess students’ performance across multiple courses, which is critical for the generalizability of the system. The system design includes core machine learning & data analysis engine, a relational database that is reusable across courses and an interactive web-based interface to continuously collect data and create dashboards for users.
Date: Tuesday, April 25, 2017
Time: 4:00 PM
Place: PGH 362
Advisor: Dr. Christoph F. Eick, Dr. Nouhad Rizk
Faculty, students, and the general public are invited.