Article

Shivam Choudhary, IMS Engineering College, Ghaziabad; Siddharth Yadav ,IMS Engineering College, Ghaziabad; Umang Kushwaha ,IMS Engineering College, Ghaziabad

This paper talks about hotspots and use of k means clustering for crime pattern detection. It first identifies significant attributes in the database. Unlike other papers, it then gives weights to attributes in the data set. The most important attribute (e.g. type of crime) is given the highest priority (weight) as compared to other attributes. We are using this feature of the research paper in our project. The data with missing values are made as test cases. It suggests dividing the database according to respective states, using classification, to make the data easier to analyze. In our project, we are subdividing the data into different types of crime allowing the user to get information of those crimes easily (e.g. percentage of the particular crime in a particular year, the hotspot of that particular crime)