Publication Date:
2012-04-17
Description:
Intelligent crime analysis allows for a greater understanding of the dynamics of unlawful activities, providing possible answers to where, when and why certain crimes are likely to happen. We propose to model density change among spatial regions using a density tracing based approach that enables reasoning about large areal aggregated crime datasets. We discover patterns among datasets by finding those crime and spatial features that exhibit similar spatial distributions by measuring the dissimilarity of their density traces. The proposed system incorporates both localized clusters (through the use of context sensitive weighting and clustering) and the global distribution trend. Experimental results validate and demonstrate the robustness of our approach. Content Type Journal Article Pages 49-74 DOI 10.1007/s10707-010-0116-1 Authors Peter Phillips, School of Business, Discipline of IT, James Cook University, Townsville, Australia Ickjai Lee, School of Business, Discipline of IT, James Cook University, Townsville, Australia Journal GeoInformatica Online ISSN 1573-7624 Print ISSN 1384-6175 Journal Volume Volume 15 Journal Issue Volume 15, Number 1
Print ISSN:
1384-6175
Electronic ISSN:
1573-7624
Topics:
Geography