A Multi-Objective Unsupervised Feature Selection using Genetic Algorithm

Rizwan Ahmed Khan, Indu Mandwi

Abstract: Data mining is related to large number of databases. Dealing with such large number of datasets may create some obstacles. Such problems can be avoided by using feature selection Technique. Feature selection Technique is a method which selects an optimal subset from original feature set. The implementation is done by removing repetitive features. The underlying structure has been neglected by the previous feature selection method and it determines the feature separately. The group feature selection method for the group structure may be formulated. It performs the task for filtering purpose for group structure technique. Group feature selection improves accuracy and may achieve relatively better classification performance.

Keywords: Genetic Algorithm, Supervised Feature Selection, Optimization, classification, K-Nearest Neighbor

How to Cite?: Rizwan Ahmed Khan, Indu Mandwi, "A Multi-Objective Unsupervised Feature Selection using Genetic Algorithm", Volume 6 Issue 1, January 2017, International Journal of Science and Research (IJSR), Pages: 1790-1794, https://www.ijsr.net/getabstract.php?paperid=ART20164612, DOI: https://dx.doi.org/10.21275/ART20164612