Microarray Data Classification using Artificial Neural Network

Abstract

The accurate cancer classification is very important task for cancer treatment. Recently the informative genes are identified from the thousands of genes for correct cancer classification. The collection of microscopic Deoxyribo Nucleic Acid (DNA) microarray is attached in the solid surface. In this study, DNA microarray data is used for cancer classification. The system uses Artificial Neural Network (ANN) for DNA Microarray Data Classification (MDC). Initially, the preprocessing step is made by using log transformation method to remove the raw data and feature selection. These selected features are classified by using ANN. REctified Linear Unit (RELU) activation function is used as the activation function in each ANN layer. Softmax is used for classification. The performance of the system is made by using leukemia dataset. MDC system produces the classification accuracy of 91.65% by using ANN