Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/14316
DC Field | Value | |
---|---|---|
dc.title | Support vector machine in chaotic hydrological time series forecasting | |
dc.contributor.author | YU XINYING | |
dc.date.accessioned | 2010-04-08T10:41:57Z | |
dc.date.available | 2010-04-08T10:41:57Z | |
dc.date.issued | 2004-11-04 | |
dc.identifier.citation | YU XINYING (2004-11-04). Support vector machine in chaotic hydrological time series forecasting. ScholarBank@NUS Repository. | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/14316 | |
dc.description.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. | |
dc.language.iso | en | |
dc.subject | chaotic technique, support vector machine, decomposition method, linear ridge regression, feature space, evolutionary algorithm | |
dc.type | Thesis | |
dc.contributor.department | CIVIL ENGINEERING | |
dc.contributor.supervisor | LIONG SHIE-YUI | |
dc.description.degree | Ph.D | |
dc.description.degreeconferred | DOCTOR OF PHILOSOPHY | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Ph.D Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
Xinying_Ph.D.thesis.pdf | 1.87 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.