RETRACTED ARTICLE: A User-Centric Machine Learning for Learning Support System with Adequate Cyber Security

Abstract

Cyber security offers digital data sets that allow learning analysis, for example, to use tracks to enhance the learning process and environment that learners leave behind. Focus on using learning analytics in data security training to provide a more evidence-based systemic method for evaluating the effects of learning and developing more successful learning. For educators, organizers, and cyber business entrepreneurs, there is a crucial factor to remember. The article aims primarily to explore all current approaches to data hacking that use cybersecurity learning. Specifically, the proposed UM-LSS-CS solution provides a warning information-based user-centered machine learning system architecture to determine user risk. The strategy helps security analysts to obtain a full risk ranking for a device, and a safety analyst will concentrate on users with high-risk ratings. Finally, the approaches of the proposed method to be obtained in UM-LSS-CS are an increasing number of learner's activities ratio is 86.2%, performance orientation of learners' in ML ratio is 89.05%, insecure information reduced via cybersecurity ratio is 88.6%, the accuracy of the learning system in user-centric approaches ratio is 91.3%, and overall performance ratio is 97.2% are estimated.