By Topic

Modelling of river discharges using neural networks derived from support vector regression

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Choy, K.Y. ; Dept. of Mech. Eng., Hong Kong Univ., China ; Chan, C.W.

Neural networks are often used to model complex and nonlinear systems, as they can approximate nonlinear systems with arbitrary accuracy and can be trained from data. Amongst the neural networks, Associative Memory Networks (AMNs) are often used, since they are less computation intensive, and yet good generalization results can be obtained. However, this can only be achieved if the structure of the AMNs is suitably chosen. An approach to choose the structure of the AMNs is to use the Support Vectors (SVs) obtained from the Support Vector Machines. The SVs are obtained from a constrained optimization for a given data set and an error bound. For convenience, this class of AMNs is referred to as the Support Vector Neural Networks (SVNNs). In this paper, the modelling of river discharges with rainfall as input using the SVNN is presented, from which the nonlinear dynamic relationship between rainfall and river discharges is obtained. The prediction of river discharges from the SVNN can give early warning of severe river discharges when there are heavy rainfalls.

Published in:

Fuzzy Systems, 2003. FUZZ '03. The 12th IEEE International Conference on  (Volume:2 )

Date of Conference:

25-28 May 2003