Design of a Novel Ensemble Model of Classification Technique for Gene-Expression Data of Lung Cancer with Modified Genetic Algorithm

Abstract

INTRODUCTION: Gene expression levels are important for identifying and diagnosing diseases like cancer. Gene expression microarray information contains a high extent feature set, which minimizes the performance and the accuracy of classifiers.

OBJECTIVES: This paper proposes a Modified Genetic Algorithm (MGA) that is based on Classifier Subset Evaluators – Genetic Search (Eval-CSE_GS) for selecting the relevant feature subsets. The MGA feature selection procedure is applied to microarray information for cancer patients that minimize a high dimension feature subset into low dimension feature subsets.

METHODS: The various data mining methods for classifying the various kinds of cancer disease patients are presented. The proposed model refers to an ensemble model (PEM) for the organization of cancer disease by reducing the feature subsets, which results show improvements in the success rate.

RESULTS: The proposed ensemble model obtains the accuracy of 94.58%, 96.56% and 97.04% for PEM-1 to PEM-3, respectively.

CONCLUSION: Our proposed MGA-PEM model gives satisfactory results for cancer identification and classification.