OPTIMIZING SELF-PACED LEARNING TRAJECTORIES IN HIGHER EDUCATION VIA ARTIFICIAL INTELLIGENCE

Abstract

In the evolving landscape of modern higher education, self-paced and independent learning has emerged as a cornerstone of student autonomy. However, traditional linear syllabi often fail to account for the diverse learning speeds and cognitive needs of individual students. This paper proposes an advanced computational framework designed to optimize self-paced learning trajectories using Artificial Intelligence and Fuzzy Logic. By moving beyond rigid numerical grading, the model utilizes a Fuzzy Inference System (FIS) to analyze dynamic input variables such as resource interaction depth, temporal consistency, and self-assessment accuracy. The methodology involves the application of triangular membership functions to model learning behavior and the utilization of the centroid method for defuzzification to generate a precise, adaptive learning velocity. Preliminary results indicate that this AI-driven approach significantly enhances learning efficiency by providing personalized interventions and reducing the cognitive load associated with unguided independent study. This research demonstrates that integrating computational intelligence into self-directed environments fosters a more equitable and granular mastery of complex subject matter.