Geospatial Knowledge Discovery Framework for Crime Domain
The value that an application delivers can be improved if the presentation of the underlying functionality is enhanced with user friendly features and intuitive results portrayal. Overlays on top of a map are one such feature which enables merely statistical results to be displayed in an intuitive manner. Crime Analysis is quite crucial in giving trends to the police department about the possibility of future crime and associated information such as location of the crime and probable methods, type of crime etc. The geospatial Knowledge Discovery Framework aims to meet the needs of various domains that have geospatial significance specifically a crime department, which can use this software to track the patterns of crime that have occurred using the data mining algorithms included in the framework, also, it can be used by a public user to find out the vulnerability of a particular location with respect to crime occurrences. The algorithms  used vary from simple geospatial search such as Bounded box query to complex clustering algorithms  such as Dbscan. Graphical visualization is also a part of the framework which uses Jasper reports to create bar charts of various forms.
KeywordsGeo-spatial Knowledge Discovery Geometrical Algorithms Computational Geometry Hibernate Spatial Clustering Spatial Mining k-means Nearest Neighborhood Range Query Spatial Query PostGIS Constraint based Searching
Unable to display preview. Download preview PDF.
- 2.Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 2nd edn. MIT Press and McGraw-Hill (2001) ISBN 0-262-03293-7, Section 34.2: Polynomial-time verification, pp. 979–983, Cambridge, MassachusettsGoogle Scholar
- 4.Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD 1996), pp. 226–231. AAAI Press, Menlo Park (1996) ISBN 1-57735-004-9Google Scholar
- 5.Buttenfield, B.P.: Looking Forward: Geographic Information Services and Libraries in the Future. In: Cartography and Geographic Information Society, American Congress on Surveying and Mapping (ACSM), vol. 25(3), pp. 161–171 (1998)Google Scholar
- 6.Miller, H.J., Han, J. (eds.): Geographic data mining and knowledge discovery. Taylor & Francis, London (2001)Google Scholar
- 8.WolframMath World, http://mathworld.wolfram.com/K-MeansClusteringAlgorithm.html
- 9.Pfeiffer, D.U.: Issues related to handling of spatial data. Massey University, Palmerston North (1996)Google Scholar
- 12.Schumacher, B.J., Leitner, M.: 1999 Spatial Crime Displacement Resulting from Large-Scale Urban Renewal Programs in the City of Baltimore, MD: A GIS Modeling Approach. GeoComputation CD-ROM, Greenwich, UK (1999)Google Scholar
- 13.Grubesic, T.: Detecting Hot Spots Using Cluster Analysis and GIS. Presentation at the National Institute of Justice’s Fifth Annual International Crime Mapping Research Conference, Dallas (December 2001), http://www.ojp.usdoj.gov/nij/maps/Conferences/01conf/Papers.html
- 15.Estivill-Castro, V., Lee, I.: Fast Spatial Clustering with Different Metrics and in the Presence of Obstacles. In: ACM-GIS, pp. 142–147 (2001)Google Scholar