A Novel Approach for Serial Crime Detection with the Consideration of Class Imbalance Problem

Objective: The main objective of this research is to reduce the burden of crime investigators by identifying the series of crimes happening at different places. And also, this work aims to reduce the investigation time by grouping similar crimes happened in different places based on its behavior with the consideration of the class imbalance problem. Methods: In this research, Majority Weighted Class Oversampling (MWCS) method is introduced which overcomes the problem of class imbalance problem. It is introduced to handle class imbalance problem by identifying the hard to learn information which is named as minority class samples from the major class samples. And also in this work, the Incremental Clustering (IC) is introduced which can handle the insertion and deletion operations where the existing methodology called graph cut clustering algorithm cant handle these problems. The proposed methodologies deal with the class imbalance problems effectively and also the modification processes over the partitioned graphs are supported well than the existing researches. Results: The methods used in this work namely MWCS and IC are used to detect the series of crimes by identifying the similarity relationship exists among the crimes happened in different places. The experimental tests conducted were proves that the proposed methodology can leads to well detection of serial residential crimes than the existing methodologies. The experimental results of this work prove that the proposed methodology is improved in terms of all performance metrics called jaccard index, mantel index and the journey distance time. Conclusion: The findings demonstrate that serial residential crimes are identified by clustering them effectively using the methodologies called MWCs and IC and it has high possibility of detection of crimes than the existing methodology.