Classification of microarray data using Fuzzy inference system

The DNA microarray classification is one of the most popular technique among researchers and practitioners. In microarray data analysis, huge useful information may be lost due to irrelevant and insignificant features of the dataset. To overcome this drawback of the data set, only those features are selected which have high relevance with the classes and high significance in the feature set. In this paper, the t-statistic is used for feature selection with high relevance; and Fuzzy inference system (FIS) has been presented for classification purpose. FIS model is applied to classify the leukemia data set for gene classification. A comparative analysis of Fuzzy inference system (FIS) with different set of features (genes) have been presented. The comparison was performed on the basis of available performance parameters in literature such as: precision, recall, specificity, F-Measure, ROC curve and accuracy. The obtained results have been critically examined with the existing classifiers in the literature and it is observed that the proposed system obtained promising results with an increase in classification accuracy rate.