Data clustering in data mining has become an increasingly important research area in recent days. The proposed hybrid algorithms k-means hierarchical clustering uses k-mean clustering combined with the hierarchical cluster centres to analyze the crime patterns. The representative points will then construct the hierarchical tree using agglomerative hierarchical clustering algorithm called dendrogram. We have performed experiments to evaluate our approach on crime data available from National Crime Record Bureau, Ministry of Home Affairs, Govt. of India, website. Clustering is used for grouping the similar patterns to identify crime pattern. The experimental result shows that the proposed hybrid algorithm is more effective. This hybrid approach performs better than hierarchical clustering algorithm in terms of accuracy of clusters.
Volume 11 | 06-Special Issue
Pages: 1249-1258