A K-Elm Approach To the Prediction of Number of Students Taking Make-Up Exams

Abstract

Purpose: The main objective of this study is to present a novel problem, and novel methodology to solve this problem. The problem is to predict the number of students who fail the course and will join the make-up exams. Theory and Methods: The number of students who fail the course should take a make-up exam, but some of them do not join these exams due to internal or external motivations, and this causes waste of resources. Majority of voting-based extreme learning machines have been proposed to solve the problem, and the ELM parameters have been optimized by artificial bee colony algorithm. Results: The proposed approach shows better performance than the extreme learning machines in terms of classification accuracy. Conclusion: Before the scheduling make-up exams, the number of students who will join the exams should be predicted by the proposed or similar approaches in order to use resources efficiently.