Classification is one of the important tasks in astronomy, especially in spectra analysis. Support Vector Machine (SVM) is a typical classification method, which is widely used in spectra classification. Although it performs well in practice, its classification accuracies can not be greatly improved because of two limitations. One is it does not take the distribution of the classes into consideration. The other is it is sensitive to noise. In order to solve the above problems, inspired by the maximization of the Fisher’s Discriminant Analysis (FDA) and the SVM separability constraints, fuzzy minimum within-class support vector machine (FMWSVM) is proposed in this paper. In FMWSVM, the distribution of the classes is reflected by the within-class scatter in FDA and the fuzzy membership function is introduced to decrease the influence of the noise. The comparative experiments with SVM on the SDSS datasets verify the effectiveness of the proposed classifier FMWSVM.
Volume 41, 2020
Continuous Article Publishing mode
Since January 2016, the Journal of Astrophysics and Astronomy has moved to Continuous Article Publishing (CAP) mode. This means that each accepted article is being published immediately online with DOI and article citation ID with starting page number 1. Articles are also visible in Web of Science immediately. All these have helped shorten the publication time and have improved the visibility of the articles.
Click here for Editorial Note on CAP Mode