Identifying learning styles and cognitive traits in a learning management system

Fuzzy clustering algorithm for university students' psychological fitness and performance detection

Students' psychological fitness is unavoidable, hindering personal development, social interactions, peer influence, and adolescence. Academic stress may be the most dominant factor affecting college students' mental well-being. Therefore, improving the monitoring of mental health issues among college students is a vital topic for study. However, identifying the student's stress level is challenging, leading to uncertainty. Hence, this paper suggests Heuristic Fuzzy C-means Clustering Algorithm (HFCA) for analyzing college students' stress levels, psychological well-being and academic performance detection. The data are collected from the Kaggle stress dataset for predicting student mental health. This study investigates the psychological factors affecting students' academic performance using the suggested HFCA. Students' performance may be predicted using the Fuzzy Cognitive Map (FCM) in this study. This study used fuzzy clustering algorithms to discover the most crucial aspects of student success, such as student involvement and satisfaction. A better understanding of the risk factors for and protective factors against poor mental health can serve as the basis for developing policies and targeted interventions to prevent mental health problems and guarantee that at-risk students can access the help they need. The experimental analysis shows the proposed method HFCA to achieve a high student performance ratio of 96.7%, cognitive development ratio of 97.2%, student engagement ratio of 97.5% and prediction ratio of 95.1% compared to other methods.

Multi-Label Classification and Explanation Methods for Students’ Learning Style Prediction and Interpretation

The current paper attempts to describe the methodology guiding researchers on how to use a combination of machine learning methods and cognitive-behavioral approaches to realize the automatic prediction of a learner’s preferences for the various types of learning objects and learning activities that may be offered in an adaptive learning environment. Generative as well as discriminative machine learning methods may be applied to the classification of students’ learning styles, based on the student’s historical activities in the e-learning process. This paper focuses on the discriminative models that try to learn which input activities of the student(s) will correlate with a particular learning style, discriminating among the inputs. This paper also investigates several interpretability approaches that may be applicable for the multi-label models trained on non-correlated and partially correlated data. The investigated methods and approaches are combined in a consistent procedure that can be used in practical learning personalization.

Cloud secured mobile e-learning system solutions using machine learning approach

Specifically designed learning models namely the mobile learning systems are conveniently available at a mobile device. The following are the difficulties that mobile learning systems must overcome: connection speed, processing power, adaptability, and the difficulty of attaining security. In this paper, we design and construct a cloud-based secure mobile e-learning management system (CSMELMS) for educational purposes. The system is made up of three primary modules, which are the client, mobile network, and cloud model. The client model makes the users to access the data via mobile application, which is connected to a mobile network using the client model. The authentication server is responsible for ensuring that each user attempting to access the system is who they claim to be. The CSMELMS system was developed using the Java programming language with the database being provided by MySQL. When the model is tested using a machine learning algorithm, it was found to be effective at enabling it for available to students when and where they need them. The utilisation of machine learning concepts enables better and secured operations for educational purposes. The results of simulation shows that this model is better at providing a better e-learning portal for students and teachers.