Table of Content

Open Access iconOpen Access

ARTICLE

Effective and Efficient Ranking and Re-Ranking Feature Selector for Healthcare Analytics

S.Ilangovan1,*, A. Vincent Antony Kumar2

1 K. L. N. College of Engineering, Madurai, India.
2 PSNA College of Engineering and Technology, Dindigul, India

* Corresponding Author: S. Ilangovan, email

Intelligent Automation & Soft Computing 2020, 26(2), 261-268. https://doi.org/10.31209/2019.100000154

Abstract

In this work, a Novel Feature selection framework called SU embedded PSO Feature Selector has been proposed (SU-PSO) towards the selection of optimal feature subset for the improvement of detection performance of classifiers. The feature space ranking is done through the Symmetrical Uncertainty method. Further, memetic operators of PSO include features and remove features are used to choose relevant features and the best of best features are selected using PSO. The proposed feature selector efficiently removes not only irrelevant but also redundant features. Performance metric such as classification accuracy, subset of features selected and running time are used for comparison.

Keywords


Cite This Article

APA Style
S.Ilangovan, , Kumar, A.V.A. (2020). Effective and efficient ranking and re-ranking feature selector for healthcare analytics. Intelligent Automation & Soft Computing, 26(2), 261-268. https://doi.org/10.31209/2019.100000154
Vancouver Style
S.Ilangovan , Kumar AVA. Effective and efficient ranking and re-ranking feature selector for healthcare analytics. Intell Automat Soft Comput . 2020;26(2):261-268 https://doi.org/10.31209/2019.100000154
IEEE Style
S.Ilangovan and A.V.A. Kumar, "Effective and Efficient Ranking and Re-Ranking Feature Selector for Healthcare Analytics," Intell. Automat. Soft Comput. , vol. 26, no. 2, pp. 261-268. 2020. https://doi.org/10.31209/2019.100000154



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1811

    View

  • 1130

    Download

  • 0

    Like

Share Link