Fuzzy Systems and its Applications

Fuzzy Systems and its Applications

Fuzzy Entropy-Based Method for Feature Selection

Document Type : Original Article

Authors
Hamid Reza Maleki S. 1
Zeinab Raeisi 1
Reza Akbari 2
1 Faculty of Sciences, Shiraz University of Technology, Shiraz, Iran
2 Faculty of IT, Shiraz University of Technology, Shiraz, Iran.
10.22034/jfsa.2025.516509.1269
Abstract
In the digital age era, data has been developed as a valuable asset. They contribute significantly to the performance of machine learning methods. With extensions of big data, the selection of relevant features and the removal of redundant features is a crucial step in improving the performance of machine learning algorithms. The filter-based method is one of the common ways for feature selection. A variety of criteria are used to evaluate features using the filter-based method. In this paper, a new method based on Fuzzy entropy is proposed to identify relevant and redundant features. The proposed method has improved the performance of the algorithm by reducing the selected features, space, and processing time. The performance of the proposed method is investigated using some UCI and Kaggle benchmark datasets. The results show that the proposed method improves the classification accuracy compared to the feature selection method based on entropy. Also, the data processing time is reduced.
Keywords
Feature Selection
Fuzzy Entropy
Classification
Optimization
Machin Learning
Subjects
[1]    Li, J., Cheng, K., Wang, S., Morstatter, F.,Trevino, R, P., Tang, J., Liu, H. (2017) Feature selection: A data perspective. ACM computing surveys (CSUR), 50(6),1–45.
[2]    Narendra and Fukunaga. (1977) A branch and bound algorithm for feature subset selection. IEEE Transactions on computers, 100(9), 917–922.
[3]    Dash, M and Liu, H. (2003) Consistency-based search in feature selection. Artificial intelligence, 151(1-2), 155–176.
[4]    Yamada, M., Jitkrittum, W., Sigal, L., Xing, E. P., Sugiyama, M. (2014) High-dimensional feature selection by feature-wise kernelized lasso. Neural computation, 26(1), 185–207.
[5]    Bahassine, S., Madani, A., Al-Sarem, M., Kissi, M. (2020) Feature selection using an improved Chi- square for Arabic text classification. Journal of King Saud University-Computer and Information Sciences, 32(2), 225–231.
[6]    Zadeh, L. A. (1965) Fuzzy sets. Information and control, 8(3), 338–353.
[7]    Lee, H., Chen, Ch,. Chen, J., Jou, Y. (2001) An efficient fuzzy classifier with feature selection based on fuzzy entropy, IEEE transactions on systems, man, and cybernetics, part B (cybernetics), 32(3), 426–432.
[8]    Hoque, N., Ahmed, HA., Bhattacharyya, DK., Kalita, JK. (2016) A fuzzy mutual information-based feature selection method for classification, Fuzzy Information and Engineering, 8(3), 355–384.
[9]    Harish, BS and Revanasiddappa, MB. (2018) A new feature selection method based on intuitionistic fuzzy entropy to categorize text documents. International Journal of Interactive Multimedia and Artificial Intelligence ….
[10]    De Luca, A and Termini, S. (1993) A definition of a non-probabilistic entropy in the setting of fuzzy sets theory. Elsevier, 197–202.
[11]    Khushaba, R. N., Kodagoda, S., Lal, S., Dissanayake, G. (2010) Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm. IEEE transactions on biomedical engineering, 58(1), 121–131.
Fuzzy Systems and its Applications
Volume 8, Issue 1 - Serial Number 16
Open Access Statement
June 2025
Pages 27-38

  • Receive Date 14 April 2025
  • Revise Date 06 May 2025
  • Accept Date 21 May 2025