Spatial Data mining is one of the challenging field in data mining. The explosive development of spatial data and common use of spatial databases highlight the need for the automated detection of spatial knowledge. Extracting interesting and useful patterns from spatial datasets is more difficult than extracting the corresponding patterns from traditional numeric and categorical data due to the complexity of spatial data types, spatial relationships, and spatial autocorrelation. Remote sensing is the one of the area very much depend on sophisticated data clustering and classification algorithms. In this research first we elaborate a study on data clustering, particularly on spatial data clustering. Some of the existing classical clustering algorithm and the proposed PANN were tested with UCI repository datasets for spatial data clustering and classification. Several tests were made on the system and overall significant results were achieved. The average accuracy of classification is defined by the Rand index as well as Sensitivity, Specificity and Accuracy. Proposed method is an influential tool for the classification of multidimensional spatial data sets. © 2011 Springer-Verlag.
CITATION STYLE
Naga Saranya, N., Megala, S., Revathi, P., Nadiammai, G. V., Krishnaveni, S., & Hemalatha, M. (2011). An efficient PANN algorithm for effective spatial data mining. In Communications in Computer and Information Science (Vol. 250 CCIS, pp. 705–709). https://doi.org/10.1007/978-3-642-25734-6_122
Mendeley helps you to discover research relevant for your work.