Particle swarm optimization with a modified sigmoid function for gene selection from gene expression data

In order to select a small subset of informative genes from gene expression data for cancer classification, recently, many researchers are analyzing gene expression data using various computational intelligence methods. However, due to the small number of samples compared to the huge number of genes (high-dimension), irrelevant genes, and noisy genes, many of the computational methods face difficulties to select the small subset. Thus, we propose an enhancement of binary particle swarm optimization to select a small subset of informative genes that is relevant for classifying cancer samples more accurately. In this proposed method, three approaches have been introduced to increase the probability of bits in particle's positions to be zero. By performing experiments on two gene expression data sets, we have found that the performance of the proposed method is superior to previous related works, including the conventional version of binary particle swarm optimization (BPSO) in terms of classification accuracy and the number of selected genes. The proposed method also produces lower running times compared to BPSO.