AN IMPROVED QUANTUM-INSPIRED EVOLUTIONARY ALGORITHM FOR CLUSTERING GENE EXPRESSION DATA
Microarray technologies have made it straightforward to monitor simultaneously the expression pattern of thousands of genes. So an important task is to cluster gene expression data to identify groups of genes with similar patterns and hence similar functions. In this paper, an improved quantum-inspired evolutionary algorithm (IQEA) is first proposed for minimum sum-of-squares clustering. We have suggested a new representation form and added an additional mutation operation in IQEA. Experiment results show that IQEA appears to be much more robust in finding optimum or best-known solutions and be superior to conventional k-means and self-organizing maps clustering algorithms even with a small population.
Unable to display preview. Download preview PDF.