Design and Application of Higher Vocational Course Learning System based on Web based Learning Framework

The advancement of web technologies has played a pivotal role in transforming higher vocational education by enabling flexible, scalable, and interactive learning environments. This study focuses on the design and implementation of a smart learning system for higher vocational courses, utilizing a web-based platform integrated with intelligent analytics. The system aims to enhance the learning experience by offering personalized content delivery and real-time performance feedback. For model development, the Personalized Learning and Adaptive Education Dataset available publicly on Kaggle was employed. This dataset includes student interaction logs, quiz scores, time-based learning behavior, and engagement metrics across various online learning modules. To process and analyze this data effectively, a One-Dimensional Convolutional Neural Network (1D-CNN) was used, owing to its efficiency in handling sequential data and recognizing behavioural patterns. The approach was trained by utilizing normalized feature inputs and optimized with categorical cross-entropy loss and Adam optimizer. Experimental results showed that the proposed system achieved an accuracy of 98.2%, precision of 97.9%, recall of 97.6%, F1-score of 97.7%, and an AUC-ROC score of 0.989. These outcomes validate the efficacy of Deep Learning (DL) in elevating vocational education systems by enabling adaptive instruction and informed decision-making for both learners and educators.