An Extended Laplacian Score Algorithm for Unsupervised Feature Selection
K.Sutha1, J. Jebamalar Tamilselvi2
1K.Sutha Research Scholar, Bharathiar University, Coimbatore, Tamil Nadu, India.
2Dr.J. Jebamalar Tamilselvi, Professor, Department of MCA, Jaya Engineering College, Chennai, Tamil Nadu, India.
Manuscript received on July 30, 2019. | Revised Manuscript received on August 25, 2019. | Manuscript published on August 30, 2019. | PP: 4359-4362 | Volume-8 Issue-6, August 2019. | Retrieval Number: F8931088619/2019©BEIESP | DOI: 10.35940/ijeat.F8931.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. 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: Experts from various sectors, utilize data mining techniques to discover most useful information from the huge amount of data, to improve their quality of outcomes. The Presence of irrelevant and redundant features affects the accuracy of mining result. Before applying any mining technique, the data need to be preprocessed. Feature selection, a preprocessing step in data mining provides better mining performance. In this paper, we propose a new two step algorithm for unsupervised feature selection. In the first step Laplacian Score is used to select the important features. And in the second step, Symmetric Uncertainty is used to remove redundant features. The experimental results show that the proposed algorithm outperforms the Laplacian Score algorithm.
Keywords: Feature Selection, unsupervised, Clustering, classification.