Predicting academic performance of learners with the three domains of learning data using neuro-fuzzy model and machine learning algorithms

Abstract

In recent days, learners faced difficulties learning programming courses. This research study will help the learners learn complex concepts quickly with different activities like flipped classrooms, online quizzes, learning by doing, and a virtual laboratory. This research is carried out to address the difficulties of learners and cover all the domains of learning, including knowledge, Skill, and Attitude. The fuzzy logic method has recently been applied in education to overcome these restrictions. While employing the fuzzy logic approach to evaluate student achievement, qualifications are assessed qualitatively rather than quantitatively. This research study applies Fuzzy Logic in the first stage, Factor Analysis (FA), and Machine Learning (ML) techniques in the second stage to discover essential factors associated with the effective use of Active Learning Strategies (ALS) in the Learning Management System (LMS) of information technology course learners. Fuzzy logic and neural network topology can be coupled using ANFIS, an adaptable network. FA is performed to find the critical factors for successful learners. The study compares the performance of five supervised machine learning algorithms: K-Nearest Neighbor, Decision Tree, Naive Bayes, Discriminant Analysis, and Support Vector Machine. These classifiers are evaluated to determine their suitability and model fit in the context of the research. In this study, real-time data is collected from B.Tech Information Technology learners. The following prediction models achieved high accuracy before FA analysis: Naive Bayes (90 %), Support Vector Machine (89 %), Discriminant Analysis (88 %), Decision Tree (86 %), and K-Nearest Neighbors (82 %). Naive Bayes gives the best accuracy, with 90 %. Following factor analysis (FA), the accuracy achieved by various classifiers is as follows: Naive Bayes - 92 %, K-Nearest Neighbors - 92 %, Support Vector Machine - 90 %, Discriminant Analysis - 89 %, and Decision Tree - 88 %. Among these, Naive Bayes and K-Nearest Neighbors exhibit the highest accuracy of 92 %.