Predictive crime mapping model using association rule mining for crime analysis

Asmai, S. A. and Rosmiza Wahida, Abdullah and Sabrina, Ahmad (2014) Predictive crime mapping model using association rule mining for crime analysis. Science International-Lahore. pp. 1703-1708. ISSN 1013-5316

[img] PDF
PID063_PredictiveCrimeMapping.pdf - Published Version
Restricted to Repository staff only

Download (476kB) | Request a copy

Abstract

This study focuses on developing a model of crime mapping using association rule mining for criminal based on geographical and demographic factors. It examined the occurrence of crime at a specific location. The predictive crime mapping is one of the solutions that can be used to analyse the relatively high future crime location that can improve the crime prevention implementation. However, most of the predictive crime mapping focused only on the variations of human behaviour variables without established the solution that able to find inherent regularities from geographical and demographic crime data. By understanding the pattern and particular location behaviours, the possible occurrence of crime can be predicted. Data collected from UC Irvine Machine Learning Repository (UCI) were modified by choosing only geographic and demographic attributes and were classified for training and testing. After training the data, the rules of relationship between attributes were generated. Here, the technique of association rule mining is being used. Then, the result which is the testing part will able to do the prediction of the crime occurrence at certain point of location.

Item Type: Article
Uncontrolled Keywords: crime, association rule mining, geographical, demographic
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Information and Communication Technology > Department of Industrial Computing
Depositing User: Dr. Siti Azirah Asmai
Date Deposited: 22 Jan 2015 02:58
Last Modified: 28 May 2015 04:36
URI: http://eprints.utem.edu.my/id/eprint/14087
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item