Student Learning Behavior Recognition in Smart Classrooms Based on Artificial Intelligence Algorithms

The dramatic growth of e-learning has instigated an urgent necessity for precise and smart systems to analyze the performance and engagement of students based on multivariegated demographic and learning-related information. This research introduces a system proposal aimed to analyze, interpret, and process intricate student datasets by integrating spatial and sequential patterns along with high-level feature extraction and attention-based mechanisms for better decisionmaking. The model is utilizing artificial intelligence methods to promote transparency, interpretability, and trust in its predictions, allowing educators and policymakers to extract the most important factors contributing to student achievement. The suggested system displays excellent performance on various evaluation criteria, indicating its suitability to support adaptive learning environments and data-driven educational interventions. The results emphasize the capability of this method to facilitate personalized learning experiences and datadriven decision-making in contemporary education systems.