WCBP: A new water cycle based back propagation algorithm for data classification

Mohd. Nawi, Nazri and Khan, Abdullah and Firdaus, Naim and M. Z., Rehman and Siming, Insaf Ali (2016) WCBP: A new water cycle based back propagation algorithm for data classification. ARPN Journal of Engineering and Applied Sciences, 11 (24). pp. 14132-14135. ISSN 1819-6608

Text AJ 2016 (36).pdf Restricted to Registered users only Download (159kB) | Request a copy

Abstract

Water Cycle algorithm is a modern nature inspired meta-heuristic algorithm to provide derivative-free solution to optimize complex problems. The back-propagation neural network (BPNN) algorithm performs well on many complex data types but it possess the problem of network stagnancy and local minima. Therefore, this paper proposed the use of WC algorithm in combination with Back-Propagation neural network (BPNN) algorithm to solve the local minima problem in gradient descent trajectory. The performance of the proposed Water Cycle based Back-Propagation (WCBP) algorithm is compared with the conventional BPNN, ABC-BP and ABC-LM algorithms on selected benchmark classification problems from UCI Machine Learning Repository. The simulation results show that the BPNN training process is highly enhanced when combined with WC algorithm.

Item Type:	Article
Uncontrolled Keywords:	back propagation neural network;water cycle search; local minima; meta-heuristic optimization; hybrid neural networks
Subjects:	Q Science > QA Mathematics > QA299.6-433 Analysis
Divisions:	Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User:	Mrs. Mashairani Ismail
Date Deposited:	02 Dec 2021 02:40
Last Modified:	02 Dec 2021 02:40
URI:	http://eprints.uthm.edu.my/id/eprint/4299

Actions (login required)

View Item