PROJECT TITLE :

Modified AHP for Gene Selection and Cancer Classification Using Type-2 Fuzzy Logic

ABSTRACT:

This paper proposes a modification to the analytic hierarchy process (AHP) to select the foremost informative genes that function inputs to an interval type-a pair of fuzzy logic system (IT2FLS) for cancer classification. In contrast to the conventional AHP, the changed AHP permits us to process quantitative factors that are ranking outcomes of individual gene selection ways including t-test, entropy, receiver operating characteristic curve, Wilcoxon take a look at, and signal-to-noise ratio. The IT2FLS is introduced for the classification task due to its great ability for handling nonlinear, noisy, and outlier knowledge, which are common issues in cancer microarray gene expression profiles. An unsupervised learning strategy using the fuzzy c-means clustering is used to initialize parameters of the IT2FLS. Alternative classifiers like multilayer perceptron network, support vector machine, and fuzzy ARTMAP are implemented for comparisons. Experiments are dispensed on three well-known microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, and prostate. Rather than the traditional cross validation, leave-one-out cross-validation strategy is applied for the experiments. Results demonstrate the performance dominance of the IT2FLS against the competing classifiers. A lot of noticeably, the modified AHP improves the classification performance not solely of the IT2FLS but of all alternative classifiers still. Accordingly, the proposed combination between the modified AHP and IT2FLS is a powerful tool for cancer classification and can be implemented as a real clinical call support system that is helpful for medical practitioners.