Discovering Student Learning Style using Min Max Cascade Neural Network

Objectives: This paper develops a scale to effective and efficient determination of individual student learning style identification. Methods: It proposes a Fuzzy Min Max Cascade Correlation Neural Network (FMMCasCorNN) for identifying the student learning behavior based on Kolb's experiential learning style. It uses questionnaires for determining a student learning style; and then adapting their behavior according to the students' styles. After preprocessing step, the student data is then input to an FMMC as CorNN for predicting the student learning style. Findings: The performance of the proposed method has been evaluated through experimental results. The proposed work is compared to the existing classification algorithms (Naïve Bayes, SMO, and Back Propagation) with precision, recall, and f-measure metrics. The experimental results shows that proposed work has better classification accuracy compared to other methods. Application: The proposed model will be highly beneficial in the field of education and the instructor will have the provision of offering better insights for the students.