A Deep Learning-Enabled Approach for Real-Time Monitoring of Learner Activities in Adaptive E-Learning Environments
H. Riaz Ahamed, D. Kerana Hanirex
Abstract
A DL-enabled strategy might improve learner outcomes in settings that are adaptable to online instruction. Before and during assesements, it closely monitored important metrics including learning progress, time on task, quiz accuracy, completion rates, and average engagement. After the intervention, significant gains were seen in every indicator. In particular, completion rates increased from 0.85 to 0.90, average engagement increased from 0.72 to 0.82, and quiz accuracy increased from 0.78 to 0.84. Most significantly, learning progress increased significantly, rising from 65% to 78%. These results highlight the ability of our DL-enabled approach to dynamically adjust the learning process based on real-time input, leading to increased student understanding, engagement, and overall development. Our research highlights how DL techniques may improve the flexibility and adaptation of e-learning environments, leading to more effective and individualized learning results. Future research projects should focus on expanding and improving our methods to handle new challenges and complexity present in adaptive e-learning environments. The ultimate goal is to support each student's academic progress and achievement by providing a more individualized and optimum learning experience.