Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/1277
Title: A split-step PSO algorithm in prediction of water quality pollution
Authors: Chau, KW 
Keywords: Particle swarm optimization
Artificial neural networks
Algorithms
Backpropagation
Benchmarking
Cost effectiveness
Algae
Tolo Harbour
Issue Date: 2005
Publisher: Springer Berlin / Heidelberg
Source: Lecture notes in computer science, 2005, v. 3498, p. 1034-1039 How to cite?
Abstract: In order to allow the key stakeholders to have more float time to take appropriate precautionary and preventive measures, an accurate prediction of water quality pollution is very significant. Since a variety of existing water quality models involve exogenous input and different assumptions, artificial neural networks have the potential to be a cost-effective solution. This paper presents the application of a split-step particle swarm optimization (PSO) model for training perceptrons to forecast real-time algal bloom dynamics in Tolo Harbour of Hong Kong. The advantages of global search capability of PSO algorithm in the first step and local fast convergence of Levenberg-Marquardt algorithm in the second step are combined together. The results demonstrate that, when compared with the benchmark backward propagation algorithm and the usual PSO algorithm, it attains a higher accuracy in a much shorter time.
URI: http://hdl.handle.net/10397/1277
ISBN: 978-3-540-25914-5
DOI: 10.1007/11427469_164
Rights: © Springer-Verlag Berlin Heidelberg 2005. The original publication is available at http://www.springerlink.com.
Appears in Collections:Book/Book Chapter

Files in This Item:
File Description SizeFormat 
LNCS7.pdfPre-published version203.31 kBAdobe PDFView/Open
Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

18
Last Week
0
Last month
Citations as of Jan 29, 2016

WEB OF SCIENCETM
Citations

21
Citations as of Feb 6, 2016

Page view(s)

276
Checked on Jan 31, 2016

Google ScholarTM
Citations

loading...

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.