In data mining, clustering technique is an interesting and important technique. The main goal of the clustering is finding the similarity between the data points or similarity between the data within intrinsic data structure and grouping them the data into single groups (or) subgroups in clustering process. The existing Systems is mainly used for finding the next frequent item set using greedy method, greedy algorithm can reduce the overlapping between the documents in the itemset. The documents will contain both the item set and some remaining item sets. The result of the clustering process is based on the order for choosing the item sets in the greedy approach; it doesn't follow a sequential order when selecting clusters. This problem will lead to gain less optimal solution for clustering method. To resolve this problem, proposed system which is developing a novel hierarchal algorithm for document clustering which produces superlative efficiency and performance which is mainly focusing on making use of cluster overlapping phenomenon to design cluster merging criteria. Hierarchical Agglomerative clustering establishes through the positions as individual clusters and, by the side of every step, combines the mainly similar or neighboring pair of clusters. This needs a definition of cluster similarity or distance. With this we are proposing the multiview point clustering approach with the NMF clustering method. The experimental results will be displayed based on the clustering result of three algorithms.
展开▼
