Criminal Identification System Based on Advanced Clustering Technique

Document clustering addresses the problem of identifying groups of similar documents without human supervision. In computer forensic analysis, thousands of files are examined. Much of the data in those files consist of unstructured text, whose analysis is difficult to performed. In such situation, automated methods of analysis are of nice interest. We present an approach that applies document clustering algorithms to forensic analysis that helps investigation. To automatically group the available data into an meaningful set of classes various clustering techniques will be used. It’s seen that there is a huge amount of increase in the crime rate due to lack of technologies. Because of this there are many new opportunities for the development of new methodologies and techniques in the field of crime investigation using the methods based on data mining. Document clustering involves descriptor and descriptors extraction. Here, we are representing a model using new methodology for evaluation of document clustering of criminal database by using naïve bays and k-means clustering technique. This model clusters the criminal information basing on the sort crime which helps to police investigation and also we are generating graphs which are used to analysis of crime rate.