Prediction Using ANN-Based Classifier in DNA Microarray Pradhan Manaswini1,* 1Assistant Professor, P.G. Department of Information and Communication Technology, Fakir Mohan University, Balasore, Orissa, India *Email id: mrs.manaswini.pradhan@gmail.com
Abstract DNA microarray is an efficient new technology that allows analysing, at the same time, measure the expression level of millions of genes Advancements in DNA microarray technology and genome sequencing have made the possibility of measuring gene expression levels on a genomic scale. One of the most significant aims of genome sequencing is to predict the genes for various diagnosis purposes. In such diagnosis purposes, the disease can be predicted using such microarray gene expression dataset and also the gene expressions that are relevant to a particular type of genes. One of such applications is cancer prediction using microarray gene expression dataset. Lot of research works have been carried out to produce a better solution to improve the prediction accuracy of cancer gene prediction. However, the achieved accuracy level is yet to be reached at a convincing level for a sensitive field in medical diagnosis. Most of the works exploit artificial intelligence to improvise the prediction accuracy. Meanwhile state-of-the-art insists for necessary enhancements in the classification module instead in the features module. The present study intends to apply the classifier and dominant gene prediction methodology to predict extensive set of cancer expression datasets. The experimental study will be carried out by considering the techniques on Central Nervous System tumour, colon tumour, lung tumour and diffuse large B-cell lymphoma. The prediction performance of the proposed methodology will be compared against the conventional prediction methodologies and the results will be validated extensively. Top Keywords Artificial neural network, Back Propagation (BP), B-cell lymphoma, CNS tumour, Colon tumour, Dimensionality reduction, Lung tumour and diffuse large, Microarray, Probabilistic PCA (PPCA). Top |