The proliferation of artificial intelligence (AI) in schools like higher ed has largely been centered around learning through text-based sources, often lacking visual components, even though these are essential in many subjects (STEM): science, technology, engineering, and mathematics. In this paper, we propose an AI-focused learning framework that integrates Microsoft Copilot Vision to accelerate visual perception and understanding in university settings. The system will interpret pedagogical diagrams, charts, and handwritten notes to develop them into organized textual explanations and interactive learning materials. It aims at making text with natural language generation accessible and engaging as well as encouraging cognitive development in learners with image recognition. Experimental observation on open education datasets and real classroom resources show to better enhance learner understanding and lower the cognitive load than classical static visual aids. This study provides a foundation for intelligent, multimodal learning that closes the gap between visual and linguistic perception, leading to personalized and inclusive education in higher learning institutions.

The project endeavored to design and develop a Web-based Performance Evaluation System with integration of rule-based algorithm that will analyze the performance of each reviewee based on the scores from their examination. The algorithm automatically provides suggested reading materials based on the result of the assessment. With this, the system will help the reviewees assess their own performance. The system was developed using Agile Methodology Model of Software Development. The software produced was tested using Alpha and Beta software tastings. The FURPS model was used to assess the software quality as perceived by the selected group of respondents. The system was found to be functional, meeting the designed functional requirements specifications.

According to National Center for Education Statistics, almost half of the first-time freshmen full time students who began seeking a bachelor’s degree do not graduate. The imbalance between the student enrolment and student graduation can be solved by early predicting and identifying students who are prone of not having graduation on time, so proper remediation and retention policies can be formulated and implemented by institutions. The study focused on the application of the ensemble models in predicting student graduation. Ensemble modeling is the process of running two or more related but different analytical models and then synthesizing the results into a single score or spread in order to improve the accuracy of predictive analytics and data mining applications. The study recorded an increase of classification accuracy in predicting student graduation using ensemble models and combining multiple algorithms.