Cluster validity for DNA microarray data using a geometrical index

A number of clustering methods have been used for DNA microarray data analysis. It is an important problem how to evaluate the results of these algorithms. In this paper, we introduce a new cluster validity index, which measures the geometrical feature of the data. The essential concept of this index is to measure the squared total length of the data eigen-axes with respect to the between-cluster separation. We show that this cluster validity index works well for data, which are close together or have different sizes. In our experiments, the proposed index is compared to five other validity indices and experiment results show that the proposed index gives more accurate results.