An Efficient Framework for Performing Discriminative Classification Technique Using WALIF & PSO-GSA Algorithms for Cancer Disease Prediction based on Gene Expression Data

Abstract

Cancer is one of the deadly diseases that affect many people globally. This disease spreads to different parts of the body. So it becomes essential to predict the abnormal growth and the extent of their spread. The goal of this study is to look into the many strategies for cancer disease identification using gene expression data as well as the obstacles that come with them. For gene selection, the model comprises preprocessing of the micro array data of gene expression. Analyzing the characteristics of gene, provide a deep understanding about cancer disease classification. The use of machine learning approaches and statistical methods are used to identify abnormal genes or mutated genes that could be modeled efficiently. We propose a design for predictive gene selection using WALIFS algorithm and PSO-GSA algorithm is used for cancer disease identification. A comparative study with various classification algorithms is made to determine the most appropriate algorithm to classify the gene expression data for cancer. Hence this research work delivers uniqueness and predicts cancer disease using gene expression data with high accuracy.