期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2019
卷号：19
期号：11
页码：174-178
出版社：International Journal of Computer Science and Network Security
摘要：Analyzing crime data is becoming a hot area of research because it has a direct connection to human life. This requires to discover hidden patterns in the crime data and group (or classify) them accordingly. Clustering is a discovery process that groups datasets into different categories based on their similarities. Clustering has been used in various areas like computing and IT, business, medicine, and biology. We used clustering by fast search and find of density peaks (CFSFDP) algorithm on crime data set. CFSFDP algorithm is based on two assumptions: (1) cluster center is a higher density data point as compared to other neighboring data points and (2) cluster centers lies at large distance from each other. Unlike k-mean clustering algorithm, number of clusters is automatically formed by CFSFDP algorithm however, cluster centers are manually selected by the user from decision graph. We performed experiments on crime dataset and tested different number of clusters to evaluate the performance of our approach.
关键词：Crime data analysis;Clustering;Decision graph;Information security.
