文章基本信息

标题：An Enhanced Method for Randomized Dimensionality Reduction Using Roughset Based K-Means Clustering
本地全文：下载
作者：S. Brindha ; Dr. Antony Selvadoss Thanamani
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：11
DOI：10.15680/IJIRCCE.2015.0311067
出版社：S&S Publications
摘要：Dimensionality Reduction is the application of data mining techniques to discover patterns from the datasets.Finding the best features that are similar to a test data is challenging task in current trend. To discover the significancefeatures have more frequent change in the structural information, which involves feature dimensionality reduction, linked toone another and elimination of non-structural information. The proposed research work presents a new approach to measurethe features (attributes) in unsupervised datasets using the methodologies namely, preprocessing, k-means based principalcomponent analysis algorithm, Roughset Based Feature Selection and Rough-Set Based K- Means Feature Selection. Datafeature selection and dimensionality reduction is characterized by a regularity analysis where the feature values correspondto the number times that term appears in the dataset. This research proposes an enhanced roughset based k-means (RK)method to estimate the feature searching is measured using genetic optimization method corresponding unsupervised data.Each feature contains objective function and their description which is used to identify the type of datasets. Initially, thetotal numbers of features are identified to enhanced RK feature selection of the datasets where the terms of match betweenthe features are identified with help of genetic algorithm.
关键词：Rough-Set; k-means; feature selection; Dimensionality Reduction.