An Algorithm for Automated View Reduction in Weighted Clustering of Multiview Data

Clustering multiview data is one of the major research topics in the area of data mining. Multiview data can be defined as instances that can be viewed differently from different viewpoints. Usually while clustering data the differences among views are ignored. In this paper, a new algorithm for clustering multiview data is proposed. Here, both view and variable weights are computed simultaneously. The view weight is used to determine the closeness or density of view. Those views which have a weight less than a predefined value are considered insignificant and are eliminated. Variable weight is used to identify the significance of each variable. In order to determine the cluster of objects both these weights are used in the distance function. In the proposed method, enhancement to the usual iterative k-means is done so that it automatically computes both view and variable weights