Predictive crime mapping model using association rule mining for crime analysis
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 relativ...
保存先:
| 主要な著者: | , , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
Publications International
2014
|
| 主題: | |
| オンライン･アクセス: | http://eprints.utem.edu.my/id/eprint/14087/1/PID063_PredictiveCrimeMapping.pdf http://eprints.utem.edu.my/id/eprint/14087/ |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | 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. |
|---|