Please use this identifier to cite or link to this item:
Title: Support vector machine in chaotic hydrological time series forecasting
Keywords: chaotic technique, support vector machine, decomposition method, linear ridge regression, feature space, evolutionary algorithm
Issue Date: 4-Nov-2004
Citation: YU XINYING (2004-11-04). Support vector machine in chaotic hydrological time series forecasting. ScholarBank@NUS Repository.
Abstract: This research attempts to demonstrate the promising applications of a relatively new machine learning tool, support vector machine (SVM), in chaotic hydrological time series forecasting. The ability to achieve high prediction accuracy is one of the central problems in water recourses management. The high prediction accuracy is achieved based on the following: (1) Forecasting with SVM applied to data in reconstructed phase space; (2) Handling large chaotic data set effectively; and (3) automatic parameter optimization with evolutionary algorithm. The proposed scheme, EC-SVM, is developed and incorporates these three features. The performance of EC-SVM is tested on daily runoff data of Tryggev?|lde catchment and daily flow of Mississippi river. Prediction accuracy of EC-SVM is compared with that of the conventional approaches and the recently developed approaches. Significantly higher prediction accuracies with EC-SVM are achieved than other techniques. In addition, the training speed required is very much faster.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Xinying_Ph.D.thesis.pdf1.87 MBAdobe PDF



Page view(s)

checked on Dec 16, 2018


checked on Dec 16, 2018

Google ScholarTM


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