Analyse the Academic Performance of Students Using ANN Classification with Modified Pillar K-means and IWFA

Abstract

The main objective of our work is to analyse the educational performance of students using Artificial Neural Network (ANN) classification with Modified Pillar K-Means and Inertia Weight Firefly Algorithm. The two theoretical measure of an ANN is training and testing. Those are pre-processed based on Minkowski distance as modified pillar k-means algorithm. It is an algorithm to optimize the initial centroids for k-means clustering with Minkowski distance. Modified pillar k means make use of cluster analysis to segment students into groups according to their grade value. An efficient optimization method called inertia weight firefly optimization algorithm for optimizing weight in ANN Classification. In order to progress the performance of the Firefly Algorithm (FA), the time changeable inertia weight is imported into position resumption of FA. The performance of the proposed work is evaluated in terms of Sensitivity, Precision, Specificity, Negative Predictive Value, Fall-out, False Negative Rate, False Discovery Rate, Accuracy and Mathews Correlation Coefficient. The proposed work will be implemented in the MATLAB tool.