期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：4
页码：5145-5148
出版社：TechScience Publications
摘要：Crimes cause terror and cost our society dearly in several ways. Data mining can be used to model crime profiling. Here we look at use of clustering algorithm for a data mining approach to analyze the crimes patterns. We will look at k-means clustering to aid in the process of crime profiling. We applied these techniques to primary crime data from Delhi police first information report (FIR) records. In this paper, firstly we desire to estimate which type of crime is dominant in Delhi city, India. Accordingly crime is divided into three types heinous crime, non-heinous crime and special & local laws violation. Second estimation is to find which area categories are more sensitive towards, areas categories which are considered are slums, residential, commercial, VIP zones, travel points and markets. Third is to show distributions of each crime type in every area category.
