Implementation of Fuzzy K-Means in Multi-Type Feature Coselection for Clustering
K. Parimala1, V. Palanisamy2
1Mrs. K.Parimala, Assistant Professor, MCA Department, NMS S.Vellaichamy Nadar College, Madurai-625019, TamilNadu, India.
2Dr. V.PalaniSamy, Professor & Head In-Charge, Department of Computer Science & Engineering, Alagappa University, Karaikudi, TamilNadu, India.
Manuscript received on November 01, 2012. | Revised Manuscript received on November 02, 2012. | Manuscript published on November 05, 2012. | PP: 213-217 | Volume-2 Issue-5, November 2012. | Retrieval Number: E1046102512/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Feature Selection is a preprocessing technique in supervised learning for improving predictive accuracy while reducing dimension in clustering and categorization. Multitype Feature Coselection for Clustering (MFCC) with hard k means is the algorithm which uses intermediate results in one type of feature space enhancing feature selection in other spaces, better feature set is co selected by heterogeneous features to produce better cluster in each space. Soft Clustering is an optimization technique of data analysis and pattern recognition which allocates a set of observations to cluster in a fuzzy way, constructing a membership-function matrix whose (i, j)th element represents the “the degree of belonging” of the ith observations to the jth cluster. This paper presents the empirical results of the MFCC algorithm with soft clustering and also gives the comparison results of MFCC with hard and soft k means. Fuzzy k-means clustering is proposed for getting the robustness against the outliers.
Keywords: Feature Selection, MFCC, Fuzzy k-means.