Mining Crime Data by Using New Similarity Measure
Authors:
- Guangzhu YuGYGuangzhu Yu
- Shihuang ShaoSSShihuang Shao
- Bing LuoBLBing Luo
- 1 September 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 389-392
Abstract
Clustering technique was introduced to the field of crime data analysis for finding crime suspects, but compared with the high requirements for public security work, traditional clustering methods used in existing application systems provide a relatively low accuracy. To solve the problem, we proposed a new similarity measure method, i.e., segmented multiple metric similarity measure (SMMSM), to improve the accuracy of similarity measure. In our method, attributes are divided into different groups according to their importance to similarity, compensation relationships does not exist among attributes in different groups. The new measure is scalable with dimensionality of data and is both suitable for numeric data and categorical data. Experiments on real data show that our method has higher accuracy than other measures.Keywords
This publication has 8 references indexed in Scilit:
- An outlier-based data association method for linking criminal incidentsDecision Support Systems, 2006
- Similarity concept for case-based design in process engineeringComputers & Chemical Engineering, 2006
- Cluster Cores-Based Clustering for High Dimensional Data2005
- Evaluating a rule evaluation support method with learning models based on objective rule evaluation indices - a case study with a meningitis data mining result2005
- Crime data mining: a general framework and some examplesComputer, 2004
- Data association methods with applications to law enforcementDecision Support Systems, 2003
- COPLINKCommunications of the ACM, 2003
- The Regional Crime Analysis Program (ReCAP): a framework for mining data to catch criminals2002