Enhancing predictive crime mapping model using association rule mining for geographical and demographic structure
This research project is to enhanced predictive crime mapping model with data mining technique to predict the possible rate of crime occurrence. Few specific objectives are stated in order to achieve the aim of this research project. This project proposed a data mining technique called Association R...
Saved in:
| Main Author: | |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/14090/1/eP20_Izzatul.pdf http://eprints.utem.edu.my/id/eprint/14090/ http://isoris14.utem.edu.my/eproceeding/46-enhancing-predictive-crime-mapping-model-using-association-rule-mining-for-geographical-and-demographic-structure |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research project is to enhanced predictive crime mapping model with data mining technique to predict the possible rate of crime occurrence. Few specific objectives are stated in order to achieve the aim of this research project. This project proposed a data mining technique called Association Rule Mining. Basically Association Rule Mining is to investigate the rules according to the predefined parameter. This technique considered useful if it can satisfy both minimum confidence and support. Apriori is a popular algorithm in finding frequent set of items in data and association rule. Dataset of Communities and Crime from UCI Machine Learning Repository is used in order to setup the experiment. 60% of the dataset is used for training to generate association rules by using WEKA. The association rules generated shows the prediction of the rate of crime occurrence. The other 40% of the dataset is used to test generated rules. A simple program of C++ is implemented using Microsoft Visual Studio to test generated rules until accuracy of performance is obtained. At the end of the project, generated rules tested and come out with difference accuracy according to predefined minimum support. |
|---|