p.3526
p.3531
p.3538
p.3542
p.3547
p.3554
p.3559
p.3564
p.3573
Water Quality Prediction Based on Improved Wavelet Transformation and Support Vector Machine
Abstract:
In the process of monitoring water quality, as the transient variable data lead to unsound prediction models and the traditional parameter optimization method based on signal factor experiments is not only time-consuming but also can not ensure the most optimal parameters. We propose to combine wavelet transformation with data translation to reduce the influence of transient variations on prediction models, and use genetic algorithm (GA) to optimize the parameters of support vector machine (SVM). The new prediction model is applied to predict water quality time series, which is compared with the traditional modeling methods based on SVM and BP neural network. The results show that the new model is superior to traditional modeling methods.
Info:
Periodical:
Pages:
3547-3553
Citation:
Online since:
August 2013
Authors:
Price:
Сopyright:
© 2013 Trans Tech Publications Ltd. All Rights Reserved
Share:
Citation: