Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification | IGI Global Scientific Publishing
Welcome to the InfoSci Platform
Reference Hub2
Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification

Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification

Tutut Herawan (Technology University of Yogyakarta, Yogyakarta, Indonesia), Yana Mazwin Mohmad Hassim (Tun Hussein Onn University of Malaysia, Faculty of Computer Science and Information Technology, Batu Pahat, Malaysia), and Rozaida Ghazali (Tun Hussein Onn University of Malaysia, Faculty of Computer Science and Information Technology, Batu Pahat, Malaysia)
Copyright: © 2017 |Volume: 13 |Issue: 3 |Pages: 14
ISSN: 1548-3657|EISSN: 1548-3665|EISBN13: 9781522511472|DOI: 10.4018/IJIIT.2017070101
Cite Article Cite Article

MLA

Herawan, Tutut, et al. "Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification." IJIIT vol.13, no.3 2017: pp.1-14. https://doi.org/10.4018/IJIIT.2017070101

APA

Herawan, T., Hassim, Y. M., & Ghazali, R. (2017). Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification. International Journal of Intelligent Information Technologies (IJIIT), 13(3), 1-14. https://doi.org/10.4018/IJIIT.2017070101

Chicago

Herawan, Tutut, Yana Mazwin Mohmad Hassim, and Rozaida Ghazali. "Functional Link Neural Network with Modified Artificial Bee Colony for Data Classification," International Journal of Intelligent Information Technologies (IJIIT) 13, no.3: 1-14. https://doi.org/10.4018/IJIIT.2017070101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Functional Link Neural Network (FLNN) has emerged as an important tool for solving non-linear classification problem and has been successfully applied in many engineering and scientific problems. The FLNN structure is much more modest than ordinary feed forward network like the Multilayer Perceptron (MLP) due to its flat network architecture which employs less tuneable weights for training. However, the standard Backpropagation (BP) learning uses for FLNN training prone to get trap in local minima which affect the FLNN classification performance. To recover the BP-learning drawback, this paper proposes an Artificial Bee Colony (ABC) optimization with modification on bee foraging behaviour (mABC) as an alternative learning scheme for FLNN. This is motivated by good exploration and exploitation capabilities of searching optimal weight parameters exhibit by ABC algorithm. The result of the classification accuracy made by FLNN with mABC (FLNN-mABC) is compared with the original FLNN architecture with standard Backpropagation (BP) (FLNN-BP) and standard ABC algorithm (FLNN-ABC). The FLNN-mABC algorithm provides better learning scheme for the FLNN network with average overall improvement of 4.29% as compared to FLNN-BP and FLNN-ABC.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global Scientific Publishing bookstore.