Abstract
Selection of highly discriminative feature in text document plays a major challenging role in categorization. Feature selection is an important task that involves dimensionality reduction of feature matrix, which in turn enhances the performance of categorization. This article presents a new feature selection method based on Intuitionistic Fuzzy Entropy (IFE) for Text Categorization. Firstly, Intuitionistic Fuzzy C-Means (IFCM) clustering method is employed to compute the intuitionistic membership values. The computed intuitionistic membership values are used to estimate intuitionistic fuzzy entropy via Match degree. Further, features with lower entropy values are selected to categorize the text documents. To find the efficacy of the proposed method, experiments are conducted on three standard benchmark datasets using three classifiers. F-measure is used to assess the performance of the classifiers. The proposed method shows impressive results as compared to other well known feature selection methods. Moreover, Intuitionistic Fuzzy Set (IFS) property addresses the uncertainty limitations of traditional fuzzy set.
Highlights
IN recent years, rapid development in internet technology generated massive amount of text documents by private and public sectors
It is evident from Fig, 1-9 that the proposed Intuitionistic Fuzzy Entropy (IFE)-FS method performs superior compared to Chi-Square, Mutual Information (MI), Information Gain (IG) and Entropy based Feature Selection (EFS) methods using K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Radial Basis Function Neural Network (RBF-NN) classifiers on the three standard datasets
The IFE is based on the intuitionistic fuzzy set
Summary
IN recent years, rapid development in internet technology generated massive amount of text documents by private and public sectors. Motivated by the significant advantages of IFCM and Fuzzy Entropy, in this article a new feature selection method called Intuitionistic Fuzzy Entropy-Feature Selection (IFE-FS) is proposed for text categorization. This method selects feature subsets based on intuitionistic fuzzy entropy for text document categorization It contains two phases: In the first phase, Intuitionistic membership degree is computed with the help of the IFCM clustering method. Selected feature subset is considered as input to the classifiers to categorize the text documents More popular classifiers such as K-Nearest Neighbor (KNN) [33], Support Vector Machine (SVM) [34] and Radial Basis Function-Neural Network (RBFNN) [35] are used. Proposes a new feature selection method (IFE-FS) based on Intuitionistic Fuzzy Entropy, which reduces high dimensionality of feature matrix and enhances the performance of classifiers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Interactive Multimedia and Artificial Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.