MLP, Gaussian Processes and Negative Correlation Learning for Time Series Prediction

Waleed M. Azmy, Neamat El Gayar, Amir F. Atiya, Hisham El-Shishiny

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Time series forecasting is a challenging problem, that has a wide variety of application domains such as in engineering, environment, finance and others. When confronted with a time series forecasting application, typically a number of different forecasting models are tested and the best one is considered. Alternatively, instead of choosing the single best method, a wiser action could be to choose a group of the best models and then to combine their forecasts. In this study we propose a combined model consisting of Multi-layer perceptron (MLP), Gaussian Processes Regression (GPR) and a Negative Correlation Learning (NCL) model. The MLP and the GPR were the top performers in a previous large scale comparative study. On the other hand, NCL suggests an alternative way for building accurate and diverse ensembles. No studies have reported on the performance of the NCL in time series prediction. In this work we test the efficiency of NCL in predicting time series data. Results on two real data sets show that the NCL is a good candidate model for forecasting time series. In addition, the study also shows that the combined MLP/GPR/NCL model outperforms all models under consideration.

Original languageEnglish
Title of host publicationMultiple Classifier Systems. MCS 2009
PublisherSpringer
Pages428-437
Number of pages10
ISBN (Electronic)9783642023262
ISBN (Print)9783642023255
DOIs
Publication statusPublished - 2009
Event8th International Workshop on Multiple Classifier Systems 2009 - Reykjavik, Iceland
Duration: 10 Jun 200912 Jun 2009

Publication series

NameLecture Notes in Computer Science
Volume5519
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference8th International Workshop on Multiple Classifier Systems 2009
Abbreviated titleMCS 2009
CountryIceland
CityReykjavik
Period10/06/0912/06/09

Keywords

  • Diversity
  • Gaussian Processes
  • MLP
  • Negative Correlation Learning
  • NN3 data
  • Time series prediction
  • Wilcoxon

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'MLP, Gaussian Processes and Negative Correlation Learning for Time Series Prediction'. Together they form a unique fingerprint.

  • Cite this

    Azmy, W. M., El Gayar, N., Atiya, A. F., & El-Shishiny, H. (2009). MLP, Gaussian Processes and Negative Correlation Learning for Time Series Prediction. In Multiple Classifier Systems. MCS 2009 (pp. 428-437). (Lecture Notes in Computer Science; Vol. 5519). Springer. https://doi.org/10.1007/978-3-642-02326-2_43