Symmetric-embedding prediction of the CATS benchmark

  • Authors:

  • P. F. Verdes;P. M. Granitto;M. I. Széliga;A. Rébola;H. A. Ceccatto

  • Affiliations:

  • Institut für Umweltphysik, Universität Heidelberg, Im Neuenheimer Feld 229, D-69120 Heidelberg, Germany;Istituto Agrario di San Michelle a/A, Via E. Mach 2, I-38010 San Michelle a/A, Italy;Instituto de Física Rosario, CONICET and Universidad Nacional de Rosario, Blvd. 27 de Febrero 210 Bis, S2000EZP Rosario, Argentina;Instituto de Física Rosario, CONICET and Universidad Nacional de Rosario, Blvd. 27 de Febrero 210 Bis, S2000EZP Rosario, Argentina;Instituto de Física Rosario, CONICET and Universidad Nacional de Rosario, Blvd. 27 de Febrero 210 Bis, S2000EZP Rosario, Argentina

  • Venue:
  • Neurocomputing
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

We present a general strategy for filling the missing data of the CATS benchmark time series prediction competition. Our approach builds upon a time-symmetric embedding of this time series and the use of a one-shot forecasting for each missing value inside the gaps from distant-enough delayed and forwarded predictors. In the extrapolation region we perform standard, non-iterated forward predictions. For modeling purposes we consider bagging of multi-layer perceptrons (MLPs). We discuss two different implementations of this strategy: The first one is based on a simultaneous modeling of both large- and short-scale dynamics information, using (suitably delayed and forwarded) original CATS values and their first differences as inputs to MLPs. The second one follows a two-stage strategy, in which behaviors at different scales are modeled separately. First, the overall behavior at large scales is fitted with a smooth curve obtained by repeated application of a Savitzky-Golay filter. Then, the remaining short-scale variability is approximated using bagged MLPs. Expected error levels for these two implementations are provided according to performance on test data.