Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction

Kulaglic A., ÜSTÜNDAĞ B. B.

TEM Journal, vol.10, no.4, pp.1955-1963, 2021 (ESCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 10 Issue: 4
  • Publication Date: 2021
  • Doi Number: 10.18421/tem104-61
  • Journal Name: TEM Journal
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Academic Search Premier, Central & Eastern European Academic Source (CEEAS), Directory of Open Access Journals
  • Page Numbers: pp.1955-1963
  • Keywords: predictive error compensated wavelet neural networks, spatial dimension, time series prediction, multivariable time series prediction, wavelet transform, neural networks
  • Istanbul Technical University Affiliated: Yes


Multivariable machine learning (ML) models are increasingly used for time series predictions. However, avoiding the overfitting and underfitting in ML-based time series prediction requires special consideration depending on the size and characteristics of the available training dataset. Predictive error compensating wavelet neural network (PEC-WNN) improves the time series prediction accuracy by enhancing the orthogonal features within a data fusion scheme. In this study, time series prediction performance of the PEC-WNNs have been evaluated on two different problems in comparison to conventional machine learning methods including the long short-term memory (LSTM) network. The results have shown that PECNET provides significantly more accurate predictions. RMSPE error is reduced by more than 60% with respect to other compared ML methods for Lorenz Attractor and wind speed prediction problems.