A set of novel correlation tests for nonlinear system variables

Authors:
L. F. Zhang;Q. M. Zhu;A. Longden
Affiliations:
Faculty of Computing, Engineering and Mathematical Sciences, University of the West of England, Bristol, BS16 1QY, UK;Faculty of Computing, Engineering and Mathematical Sciences, University of the West of England, Bristol, BS16 1QY, UK;Faculty of Computing, Engineering and Mathematical Sciences, University of the West of England, Bristol, BS16 1QY, UK
Venue:
International Journal of Systems Science
Year:
2007

Citing 4
Cited 6

Applied regression analysis and other multivariable methods

Applied regression analysis and other multivariable methods
On covariance function tests used in system identification

Automatica (Journal of IFAC) - Identification and system parameter estimation
Time Series Analysis, Forecasting and Control

Time Series Analysis, Forecasting and Control
Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning

Development of omni-directional correlation functions for nonlinear model validation

Automatica (Journal of IFAC)
Model selection approaches for non-linear system identification: a review

International Journal of Systems Science
A correlation-test-based validation procedure for identified neural networks

IEEE Transactions on Neural Networks
Online identification of the system order with ANARX structure

ICAIS'11 Proceedings of the Second international conference on Adaptive and intelligent systems
Evolutionary design of the closed loop control on the basis of NN-ANARX model using genetic algorithm

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
A new hyper-parameters selection approach for support vector machines to predict time series

ICPCA/SWS'12 Proceedings of the 2012 international conference on Pervasive Computing and the Networked World

Quantified Score

Hi-index	0.00

Visualization

Abstract

A set of novel correlation tests using omni-directional cross-correlation functions (ODCCFs), which are based on the first order cross-correlation functions (CCF), are proposed in the present study to comprehensively detect nonlinear relationships between variables. Then the ODCCFs are combined into a set of concise formulations to provide better illustration of detected correlations and reduce the number of correlation plots. Compared to the other approaches, the new methodology brings much more power in detection of nonlinear correlations. The efficiency and effectiveness of the new algorithm are demonstrated through simulation studies and comparisons with other linear and nonlinear correlation tests. The results can be widely applied in many relevant fields.