Cancer Classification Using Green Computing Techniques

Abstract

Biological studies progress through the expansion of the expertise technologies. A DNA microarray is a high throughput technology used in molecular biology and in medicine. DNA micro arrays can be used to measure changes in expression levels or to detect single nucleotide polymorphisms. One can analyze the expression of many genes in a single reaction quickly and in an efficient manner. The main application of microarray technology is disease diagnosis. Patterned DNA microarrays are promising as a potent and cost-effective tool for large scale analysis of gene expression. Microarrays can be used to measure the relative quantities of specific mRNAs in two or more tissue samples for thousands of genes simultaneously. As the power of this technology has been recognized, many open queries remain about appropriate analysis of microarray data. One such is about the valid estimates of the relative expression for genes that are not biased by ancillary sources of variation. Be acquainted with that there is inherent noise in microarray data will the recognition system estimates the error variation associated with an estimated change in expression and construct the error bars. For the above impenetrability and to get better consequences of the system with accuracy a new learning algorithm called Extreme Learning Machine (ELM) is used. ELM avoids problems like local minima improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. ELM uses the error free ANOVA methods in the preprocessing phase itself. Here it demonstrates that ANOVA methods can be used to normalize microarray data and provide estimates of changes in gene expression that are corrected for potential perplexing effects. The multicategory classification performance of ELM is evaluated on Lymphoma data set. The results indicate that ELM with ANOVA test produces comparable or better classification accuracies with reduced training time and implementation complexity compared to Support Vector Machine (SVM) with ANOVA.