A ovel Parameters Selection Approach for Support Vector Machines to Predict Time Series
作者： Yanhua Yu , Junde Song , Zhijun Ren
DOI: 10.1007/978-3-642-37015-1_68
关键词:
摘要: Aimed to solve the problem that there is no structural approach select best free parameters for Support Vector Machines when being used in time series prediction, a novel proposed. In this method, SVM not got at minimal MSE (Mean Squared Error) of validation set, but residue training set White Noise form. This conclusion deduced from fact targets have inherent correlations with each other. also effective predict nolinear and non-stationary characteristics. Furthermore, by using confidence interval can be computed under any given degree 1 - alpha which an important value many applications. Two algorithms compute are different circumstances. Program about how make dynamic on-line prediction. Experiment was made annual sunspot number perfect result achieved.
springer.com
sci-hub.se 参考文章(35)
Nicholas Sapankevych, Ravi Sankar, Time Series Prediction Using Support Vector Machines: A Survey IEEE Computational Intelligence Magazine. ,vol. 4, pp. 24- 38 ,(2009) , 10.1109/MCI.2009.932254
Li-Juan Cao, Francis Eng Hock Tay, Support vector machine with adaptive parameters in financial time series forecasting IEEE Transactions on Neural Networks. ,vol. 14, pp. 1506- 1518 ,(2003) , 10.1109/TNN.2003.820556
Jin Wei-dong, Selection of Kernel Functions and Parameters for Support Vector Machines in System Identification Computer Simulation. ,(2006)
Artificial Neural Networks — ICANN 2001 Springer Berlin Heidelberg. ,(2001) , 10.1007/3-540-44668-0
Oliver D. Anderson, George E. P. Box, Gwilym M. Jenkins, Time Series Analysis: Forecasting and Control The Statistician. ,vol. 27, pp. 265- 265 ,(1978) , 10.2307/2988198
Simon Haykin, Davide Mattera, Support vector machines for dynamic reconstruction of a chaotic system Advances in kernel methods. pp. 211- 241 ,(1999)
James T. Kwok, Linear Dependency between epsilon and the Input Noise in epsilon-Support Vector Regression international conference on artificial neural networks. pp. 405- 410 ,(2001)
James T Kwok, None, Linear Dependency between ε and the Input Noise in ε-Support Vector Regression Artificial Neural Networks — ICANN 2001. pp. 405- 410 ,(2001) , 10.1007/3-540-44668-0_57
B. Schölkopf, P. Bartlett, A. Smola, R. Williamson, Support vector regression with automatic accuracy control. international conference on artificial neural networks. pp. 111- 116 ,(1998) , 10.1007/978-1-4471-1599-1_12
Filip M. Mulier, Vladimir Cherkassky, Learning from Data: Concepts, Theory, and Methods John Wiley & Sons, Inc.. ,(1998)