Please use this identifier to cite or link to this item:
DC FieldValue
dc.titleEfficient and prediction enhancement schemes in chaotic hydrological time series analysis
dc.contributor.authorDULAKSHI S.K. KARUNASINGHA
dc.identifier.citationDULAKSHI S.K. KARUNASINGHA (2006-02-14). Efficient and prediction enhancement schemes in chaotic hydrological time series analysis. ScholarBank@NUS Repository.
dc.description.abstractThis study looked into means of improving prediction accuracy and facilitating efficient analysis of chaotic hydrological time series. The objectives were: (1) to investigate in detail the prediction performances of global prediction models (Artificial Neural Network (ANN) and Support Vector Machine (SVM)) compared to some widely used local prediction models (local averaging and local polynomial), and (2) to find means of incorporating noise reduction techniques in prediction improvement schemes, and (3) to investigate means of extracting system representative smaller sets of data from long data records. The superiority of the global prediction models over the widely used local prediction models is shown. ANN and SVM were shown to be equally good predictors. Kalman filtering technique was introduced to further improve the prediction accuracy of noisy chaotic time series. A noise reduction scheme for real-time prediction was proposed. A methodology to extract system representative data smaller data sets from long chaotic data records was proposed. A simple and much more efficient clustering technique was also developed for data extraction purposes.
dc.subjectchaos, Artificial Neural Network, Support Vector Machine, noise, Kalman filtering, clustering
dc.contributor.departmentCIVIL ENGINEERING
dc.contributor.supervisorLIONG SHIE-YUI
dc.contributor.supervisorLIN PENGZHI
dc.description.degreeconferredDOCTOR OF PHILOSOPHY
Appears in Collections:Ph.D Theses (Open)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PhD_thesis.pdf4.67 MBAdobe PDF



Page view(s)

checked on May 22, 2019


checked on May 22, 2019

Google ScholarTM


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