An Efficient Fuzzy c-Means Neural Network Approach for the Prediction of Student Cheating Tendency for Online Learning System

Due to its adaptability and versatility, online education has gained widespread popularity among university students. Students can customize their education to fit their schedules and lifestyles with the help of this technology. It is worth noting, however, that even the brightest student may feel pressured into cheating to earn a perfect score. If a student is having trouble finishing an assessment before the due date, or if the assignment is uninteresting, irrelevant, or very difficult, they may resort to cheating to get it done. The main objective of this study is to recommend the use of a fuzzy c-means neural network for forecasting student online cheating behavior. The students’ identities were trained and verified in this manner to make predictions about their propensity to cheat. Fuzzy c-means neural networks were found to have a high degree of accuracy when applied to these datasets. Thus, this method can aid educators like lecturers and teachers in assessing and grading each student's test and assignment and lowering the prevalence of cheating. The methods also represent a novel approach to ensuring the safety of distance education.