Clustering gene data via pulse-coupled neural network

We describe a new approach to the clustering analysis of gene expression data using pulse coupled neural network (PCNN). PCNN dynamically evaluates similarity between any two samples owing to the outstanding centralization characteristic based on the vicinity in space and the comparability of brightness. It has higher accuracy and faster performance than those classical algorithms. Furthermore, the proposed algorithm solves the puzzle of confirming the number of clusters at beginning. The clustering performance of PCNN has been tested in the paper. The experimental results demonstrate that PCNN can achieve superior performance especially for the data with non-Gaussian distribution. The performance can be further enhanced when some useful parameters selection methodologies are incorporated.