You are not logged in.

Neural network training by hybrid accelerated cuckoo particle swarm optimization algorithm

Nawi,NM, Khan,A, Rehman,MZ, Abdul Aziz, M, Abawajy,JH and Herawan,T 2014, Neural network training by hybrid accelerated cuckoo particle swarm optimization algorithm. In Loo, Chu Kiong, Yap, Keem Siah, Wong, Kok Wai, Teoh, Andrew and Huang, Kaizhu (ed), Neural information processing : 21st International Conference, ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings, Springer, Berlin, Germany, pp.237-244.

Attached Files
Name Description MIMEType Size Downloads

Title Neural network training by hybrid accelerated cuckoo particle swarm optimization algorithm
Author(s) Nawi,NM
Khan,A
Rehman,MZ
Abdul Aziz, M
Abawajy,JH
Herawan,T
Title of book Neural information processing : 21st International Conference, ICONIP 2014 Kuching, Malaysia, November 3-6, 2014 Proceedings
Editor(s) Loo, Chu Kiong
Yap, Keem Siah
Wong, Kok Wai
Teoh, Andrew
Huang, Kaizhu
Publication date 2014
Chapter number 29
Total chapters 71
Start page 237
End page 244
Total pages 8
Publisher Springer
Place of Publication Berlin, Germany
Keyword(s) Cuckoo search
Metaheuristic algorithm
Neural network
Optimization
Particle Swarm Optimization
Summary Metaheuristic algorithm is one of the most popular methods in solving many optimization problems. This paper presents a new hybrid approach comprising of two natures inspired metaheuristic algorithms i.e. Cuckoo Search (CS) and Accelerated Particle Swarm Optimization (APSO) for training Artificial Neural Networks (ANN). In order to increase the probability of the egg’s survival, the cuckoo bird migrates by traversing more search space. It can successfully search better solutions by performing levy flight with APSO. In the proposed Hybrid Accelerated Cuckoo Particle Swarm Optimization (HACPSO) algorithm, the communication ability for the cuckoo birds have been provided by APSO, thus making cuckoo bird capable of searching for the best nest with better solution. Experimental results are carried-out on benchmarked datasets, and the performance of the proposed hybrid algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The results show that the proposed HACPSO algorithm performs better than other algorithms in terms of convergence and accuracy.
ISBN 9783319126395
ISSN 0302-9743
1611-3349
Language eng
Field of Research 080501 Distributed and Grid Systems
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category B1 Book chapter
ERA Research output type B Book chapter
Copyright notice ©2014, Springer
Persistent URL http://hdl.handle.net/10536/DRO/DU:30070295

Document type: Book Chapter
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 281 Abstract Views, 3 File Downloads  -  Detailed Statistics
Created: Fri, 06 Mar 2015, 08:19:36 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.