Stacked autoencoder for classification of glioma grade III and grade IV

Abstract

Invention of the microarray technology has rendered it possible to inspect the whole genome at once in cancer classification. However, in order to curtail the computational complexity and augment the accuracy of cancer classification, it is essential to sift the vast microarray data for the informative genes. In this paper, Thresholding and Ratio methods are presented, individually as well as conjointly (hybrid method) to choose optimal gene subset from the microarray data. Moreover, Discrete Wavelet Transform (DWT) is deployed to pare the size of microarray data still further. The classification is accomplished by using various neural network algorithms and Stacked Autoencoder algorithm. The results of classification are compared for number of thresholds, ratios, wavelets and classification algorithms. It is observed that the Stacked Autoencoder network trained by Back Propagation algorithm delivers the best results in terms of classification accuracy and number of genes.