A wavelet based prediction method for time series

Cristina Laura Stolojescu (1, 2, 3) , Ion Railean (1, 4, 3) , Sorin Moga (5, 1) , Philippe Lenca (5, 1) , Alexandru Isar (2)

1 LUSSI - Département Logique des Usages, Sciences sociales et Sciences de l'Information
2 UPT - Universității Politehnica Timișoara [România] = Polytechnic University of Timişoara [Romania] = Université polytechnique de Timișoara [Roumanie]
3 Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (UMR 3192)
4 TUCN - Department of Communications, Technical University of Cluj-Napoca (.)
5 Lab-STICC_TB_CID_DECIDE

The paper proposes a wavelet-based forecasting method for time series. We used the multiresolution decomposition of the signal implemented using trous wavelet transform. We combined the Stationary Wavelet Transform (SWT) with four prediction methodologies : Artificial Neural Networks, ARIMA, Linear regression and Random walk. These techniques were applied to two types of real data series: WiMAX network traffic and financial. We proved that the best results are obtained using ANN combined with the wavelet transform.Also, we compared the results using various types of mother wavelets. It is shown that Haar and Reverse biorthogonal 1 give the best results.

Domaines: Traitement du signal et de l'image [eess.SP]; Machine Learning [stat.ML]

Cristina Laura Stolojescu, Ion Railean, Sorin Moga, Philippe Lenca, Alexandru Isar. A wavelet based prediction method for time series. SMTDA2010 : Stochastic Modeling Techniques and Data Analysis International Conference, Jun 2010, Chania, Greece. ⟨hal-00498385⟩