AI-Based Model to Enhance the Performance Of Engineering Students in Physics Course

The performance of students in the introductory foundation physics course at the liberal arts college has been unsatisfactory, which negatively affects course outcomes and delays graduation. To enhance both teaching and student performance, it is crucial to assess the prior knowledge of incoming students. This paper analyzes the performance of PHY 101 students, offered in the first semester at the university for science and engineering majors. We examined students’ final grades in $12^{\text {th }}$-grade physics and math, along with an analysis of their prior knowledge using a fixed Q/A method for both subjects. The results from the first-class test indicate that students’ 12th-grade performance does not align with their results in the university-level foundation course. The gap year, instructional methods, high school curriculum, and assessment process all influence their performance. To address this gap, we have developed an AI-based assessment and teaching-learning model aimed at improving performance.