Personalized Educational Knowledge Tracing using Graph Attention (GAT)
Predictive model modeling prerequisite concept graphs to estimate a student's mastery level and recommend optimal practice questions.
Project Overview
Models university syllabus curricula as prerequisite knowledge graphs. Uses Graph Attention Networks (GAT) to analyze students' historical quiz response sequences, predicting mastery gaps and generating personalized learning roadmaps to maximize retention.
Models university syllabus curricula as prerequisite knowledge graphs. Uses Graph Attention Networks (GAT) to analyze students' historical quiz response sequences, predicting mastery gaps and generating personalized learning roadmaps to maximize retention.
Predictive model modeling prerequisite concept graphs to estimate a student's mastery level and recommend optimal practice questions.
Core Project Objectives
Capture continuous analog/digital sensor readings with robust noise filtering and hardware calibration.