Design and Development of Machine Learning based Digital Resource Platform for Intelligent Control Course Teaching Technique

In wise control course learning, individual resource delivery is challenging owing to differences in student learning behaviour. Conventional platforms tend to provide fixed content, and this content does not accommodate differences. This paper proposes a digital resource platform driven by clustering algorithms to group learners according to learning interactions and scale content appropriately. Based on K-Means clustering, the platform divides learners according to engagement metrics, quiz scores, and time spent on topics. Every cluster gets tailored resources and tasks designed to suit its learning profile. This adaptive mapping provides enhanced content relevance and better understanding. Real-time feedback and suggestions enhance the adaptive learning cycle further. Silhouette Score and Davies-Bouldin Index are employed for clustering performance verification. Outcomes values are accuracy of 98.4 %, precision of 98.2% and recall of 98.2%. The system is effective for scalable, data-driven instructional design in control systems learning.