期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：7
页码：12524
DOI：10.15680/IJIRSET.2017.0607009
出版社：S&S Publications
摘要：Data mining is the combination of data assembled by customary information mining philosophies andprocedures with data accumulated over large no of data sources. Data mining is utilized to retrieve some usefulinformation from a set of accumulated data-K-Means is one of the common and simplest unsupervised algorithm forclustering- It classifies data on the basis of Euclidian distance. The PSO algorithm is an optimization technique basedon swarm intelligent which is further extended to data clustering. It is used to refine clusters produced by K-Means.The proposed work is aimed to find a solution for generating different .However the method can be computationallyexpensive in that a large number of function calls is required to advance the swarm at each optimization iteration. Inorder to increase the efficiency of the algorithm an concept of Surrogate function is incorporated which serves as anstand in for expensive objective function.The work also aims to provide better analysis of the proposed hybridapproach on the basis of obtained numerical results.
关键词：Data mining is the combination of data assembled by customary information mining philosophies and;procedures with data accumulated over large no of data sources. Data mining is utilized to retrieve some useful;information from a set of accumulated data-K-Means is one of the common and simplest unsupervised algorithm for;clustering- It classifies data on the basis of Euclidian distance. The PSO algorithm is an optimization technique based;on swarm intelligent which is further extended to data clustering. It is used to refine clusters produced by K-Means.;The proposed work is aimed to find a solution for generating different .However the method can be computationally;expensive in that a large number of function calls is required to advance the swarm at each optimization iteration. In;order to increase the efficiency of the algorithm an concept of Surrogate function is incorporated which serves as an;stand in for expensive objective function.The work also aims to provide better analysis of the proposed hybrid;approach on the basis of obtained numerical results.
