Assessment Student Daily Learning Behaviors based on Artificial Intelligence in Big Data for E-Learning

Information skills are now being taken into consideration as an essential skill for university students, and the conference should always explore social needs and encourage self-learning skills. A reliable technique for recognizing the practice of detail mastery is to assess the various cognitive processes inherent in detail skill. A student assessment behavior system based on artificial intelligence (SABSAI) is proposed which includes clustering performance prediction and recommendation for student daily learning behaviors. Individual ratings are identified with a Deep Neural Network (DNN), which considers both practitioner engagement and choice ratings. Consequently, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is used based on estimates obtained by the Mahalanobis Range Clustering Teams students. Student skill prediction is carried out using threshold-based MapReduce (TMR) treatment of score-based collections with the aim of providing effective comprehension recommendations. To assess these suggestions, a counseling support comprehension formula, the rule-based state-action-reward state-action (R-SARSA) approach was incorporated. This e-learning recommendation system shows improved performance metrics with accuracy, true-positive, false-positive, true-negative, false-negative, accurate and recall.