论文信息 - Variable Scaling for Time Series Prediction: Application to the ESTSP'07 and the NN3 Forecasting Competitions

Variable Scaling for Time Series Prediction: Application to the ESTSP'07 and the NN3 Forecasting Competitions

In this paper, variable selection and variable scaling are used in order to select the best regressor for the problem of time series prediction. Direct prediction methodology is used instead of the classic recursive methodology. Least Squares Support Vector Machines (LS-SVM) and K-NN approximator are used in order to avoid local minimal in the training phase of the model. The global methodology is applied to the ESTSP'07 competition dataset and the dataset B of the NN3 Forecasting Competition.

Amaury Lendasse | Elia Liitiäinen

[1] Heekuck Oh,et al. Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[2] Lennart Ljung,et al. System Identification: Theory for the User , 1987 .

[3] S. Hyakin,et al. Neural Networks: A Comprehensive Foundation , 1994 .

[4] Andreas S. Weigend,et al. Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[5] Nenad Koncar,et al. A note on the Gamma test , 1997, Neural Computing & Applications.

[6] Antonia J. Jones,et al. New tools in non-linear modelling and prediction , 2004, Comput. Manag. Sci..

[7] R. Shah,et al. Least Squares Support Vector Machines , 2022 .

[8] Michel Verleysen,et al. Chemometric calibration of infrared spectrometers: selection and validation of variables by non-linear models , 2004 .

[9] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .