Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 103
PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING
Edited by: Y. Tsompanakis
Paper 22

The Impact of Sampling on Flow Prediction using Support Vector Machines

M. Cisty and J. Bezak

Department of Land and Water Resources Management,
Slovak University of Technology in Bratislava, Slovakia

Full Bibliographic Reference for this paper
M. Cisty, J. Bezak, "The Impact of Sampling on Flow Prediction using Support Vector Machines", in Y. Tsompanakis, (Editor), "Proceedings of the Third International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 22, 2013. doi:10.4203/ccp.103.22
Keywords: sampling, data-driven models, flow predictions.

Summary
The inundation and flooding of a landscape is a serious problem which needs to be solved. This paper presents the application of a data-driven model for stream flow prediction, which can be one of the tools for the preventive protection of a population and its property. The authors have applied support vector machine methodology (SVMs) to the flow predictions in this paper. SVMs are gaining popularity as a result of various attractive features, which equip SVMs with a greater ability to generalize the main goal in data-driven modelling. From a practical point of view, perhaps the most serious problem with SVMs is their high algorithmic complexity and the extensive memory requirements of the quadratic programming required (which is part of solving a problem with an SVM model) for large-scale tasks. In this situation the pre-processing of the data, namely sampling methods are useful for reducing software-hardware requirements. The pre-processing methods investigated were applied to the Hron River watershed in Slovakia using hydrological and meteorological daily data of various variables, which are the predictants in SVM flow prediction models. Special sampling was used, bearing in mind the nuances of hydrological modelling. A compromise exists between the size of the training dataset and the degree of accuracy, when the degree of accuracy is not lowered and the computation time is significantly decreased. The authors demonstrate in the paper how such a compromise could be found. A model trained with a reduced dataset of 50% achieved the same degree of accuracy as the model with all the data, but with an execution time four times shorter.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £42 +P&P)