期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2013
卷号：5
期号：1
出版社：Seventh Sense Research Group
摘要：Clustering has been used extensively as a vital tool of data mining.Data gathering has been deliberated widely, but mostly all identified usual clustering algorithms lean towards to break down in high dimensional spaces because of the essential sparsity of the data points. Present subspace clustering methods for handling highdimensional data focus on numerical dimensions.The minimum spanning tree based clustering algorithms, because they do not adopt that data points are clustered around centers or split by a regular geometric curve and have been widely used in training.The present techniques allow these algorithms to extend much more easily with both the number of instances in the dataset and the number of attributes. But the performance minimizesoon with the size of the subspaces in which the groups are found. Theimportant parameter needed by these algorithms is the density threshold and it is not easy to set, particularly across all dimensions of the dataset. The aim of this paper is proposed method investigate the performance of different NeuroFuzzy classification methods for the distinction of benign and malign tissue in genes.
