Main Article Content

Dr. J. Chockalingam
B. Venkatesan


In recent world, the crime factors are increasing day by day. Some of the preventive measures are taken to identify and avoid the crimes by their concern departments. There are huge amount of heterogeneous unstructured data are collected about the crime factors and the criminals. That the gathered unstructured data should be gathered, elicited and classified for analyzing the crime factors and find out the predictive measures for the prevention of crime activities. Many classification techniques are used in the analysis of crime factors and make predictive analysis through it. However the effective techniques are used for the analysis of the crime factors, this is potentially strong based on the dataset taken as an input or in training phase. In existing, for gathering the relevant data for the analysis is obtained through the Hierarchal Clustering. It is most efficient clustering technique but it works well in the structured text data. To obtain the effective data clustering in heterogeneous unstructured data, the K Means Clustering has been proposed. Next to clustering, the classification technique is required to classify the properties of the crime factors through the parameters in unstructured data using Cluster Based Support Vector Machine Classification. The main contribution of this proposed work is to create a novel mechanism for obtain the predictive analysis for prevention of crime factors from the various crime classes. The predictive analysis can be obtained through the continuous process of K means clustering and Multi Class SVM Classification. To prove the effectiveness of the proposed mechanism capable of deals with multiple domains, SVM Classification algorithm can be optimized through this algorithm. The experiments have been illustrating the efficiency of the mechanism with the dataset from UCI repository and data from government of India.


Download data is not yet available.

Article Details