Reduced Feature Based Efficient Cancer Classification Using Single Layer Neural Network

Abstract Cancer classification is one of the major applications of the microarray technology. When standard machine learning techniques are applied for cancer classification, they face the small sample size (SSS) problem of gene expression data. The SSS problem is inherited from large dimensionality of the feature space (due to large number of genes) compared to the small number of samples available. In order to overcome the SSS problem, the dimensionality of the feature space is reduced either through feature selection or through feature extraction. For achieving this objective different feature reduction schemes with a set of simple classifiers have been suggested in this paper. Firstly the dimension have been reduced using Principal Component Analysis(PCA), Factor Analysis(FA), Discrete Fourier Transform(DFT) and Discrete Cosine Transform(DCT).Then the reduced dimensions are used to design intelligent classifiers using different Functional Link Artificial Neural Network (FLANN). The simulation results demonstrate that the reduction based Chebyshev classifier perform the best compared to other alternatives.