The week's pick
Reseach Article
Spatial Data Mining with the Application of Spectral Clustering: A Trend Detection Approach
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 173 - Number 2 |
| Year of Publication: 2017 |
| Authors: Arvind Sharma, R. K. Gupta |
10.5120/ijca2017915252
|
Arvind Sharma, R. K. Gupta . Spatial Data Mining with the Application of Spectral Clustering: A Trend Detection Approach. International Journal of Computer Applications. 173, 2 ( Sep 2017), 11-18. DOI=10.5120/ijca2017915252
Abstract
Spectral clustering in spatial data mining plays a very important and innovative role due to its capacity of handling of large size of data ,effective application of linear algebra to solve graphical representation and problems, and application of very low cost of clustering algorithms like k-nearest or є neighbourhood graph. Most of the research in this area is focused on efficient query processing for static or dynamic data. This paper extends the current spatial data mining algorithms to efficient mode of spectral clustering algorithms with the application of Laplacians graph properties and present new approach of spatial data mining methods. These algorithms and methods are used to scratch new knowledge from huge data sets having property of graphs. Obtained results of spectral clustering shows various aspects of spatial data mining and their applications.Spatial database systems contains various spatial objects representing natural objects like mountain or river ,infrastructure like railroad, location, highways with spatial and as well as non spatial attributes. This paper reveals very important and uncovered aspects of spectral clustering.
References
- Bach, F. and Jordan,M (2004), Learning spectral clustering. pp 305-312,Cambridge, MA:MIT press.
- Dhillon,I, Guan,Y.,andKulis,B(2005).A unified view of kernel k-means, spectral clustering, and graph partitioning.
- Kempe, D. and Mcsherry, F.(2004).A decentralized algorithm for spectral analysis (PP 561-568), NY, USA; ACM press.
- M. Audibert, J-Y.,and Von Luxburg ,U(2007)Graph Laplacian and their convergence on random neighbourhood graphs.JMLR,8,1325-1370.
- Xianchao ZHANG at al, Dalian university of technology” An improved spectral clustering algorithm based on random walk”. Springer-Verlag Berlin, 2011(PP 268-278)
- Arvind Sharma, R K Gupta at al (2016). “Improved DBSCAN”, Hindawi publication
- Jia H., Ding S. at al. “A Nystrom spectral clustering algorithm based on probability incremental sampling” DOI 10.1007/s00500-016-2160-8.
- Liu T., Gu Y., at al “Class specific sparse multiple kernel learning for spectral – spatial hyperspectral image classification” IEEE transactions on Geo Science and Remote sensing-2016.
- H. jia. S. Ding.X. Xu. “The latest research progress on spectral clustering” DOI 10.1007/s00521-s013-1439-2, Springer-Verlag,2013.
- Ding, C., He, X., Zha,H., et al: A Min-Maxcut algorithm for graph partitioning and data clustering. pp 107-114(2001), California .
- Open Geospatial Consortium (OGC) http://www.opengeospatial.com
- Office of Policy Development and Research (PD&R) U.S. Department of Housing and Urban Development. www.huduser.gov
- L.,Ulrike von. “A Tutorial on Spectral clustering”,17(4),2007,Germany.
- Hendrickson, B. And Leland, R (1995). An improved Spectral graph partitioning algorithm for mapping parallel computations. SIAM J. On Scientific Computing, 16, 452-469.
Index Terms
Keywords