Using Shuffled Frog-Leaping Algorithm for Feature Selection and Fuzzy Classifier Design
- Авторы: Hodashinsky I.A.1, Bardamova M.B.1, Kovalev V.S.1
-
Учреждения:
- Tomsk State University of Control Systems and Radioelectronics
- Выпуск: Том 46, № 6 (2019)
- Страницы: 381-387
- Раздел: Article
- URL: https://journals.rcsi.science/0147-6882/article/view/175544
- DOI: https://doi.org/10.3103/S0147688219060030
- ID: 175544
Цитировать
Аннотация
This paper considers a new approach for designing fuzzy rule-based classifiers. To optimize the parameters of classifiers, a continuous shuffled frog-leaping algorithm is applied. On a set of constructed classifiers, the optimal classifier is selected in terms of the accuracy and the number of features used, using the statistical Akaike informational criterion. The efficiency of the proposed approach is tested on 15 KEEL data sets. The results are statistically compared with the results of similar algorithms. The new approach to designing fuzzy classifiers proposed in this article makes it possible to reduce the number of rules and attributes, thereby increasing the interpretability of classification results.
Об авторах
I. Hodashinsky
Tomsk State University of Control Systems and Radioelectronics
Автор, ответственный за переписку.
Email: hodashn@rambler.ru
Россия, Tomsk, 634050
M. Bardamova
Tomsk State University of Control Systems and Radioelectronics
Автор, ответственный за переписку.
Email: 722bmb@gmail.com
Россия, Tomsk, 634050
V. Kovalev
Tomsk State University of Control Systems and Radioelectronics
Автор, ответственный за переписку.
Email: vitaly_979@mail.ru
Россия, Tomsk, 634050
Дополнительные файлы
