A modified PNN algorithm with optimal PD modeling using the orthogonal least squares method

Authors:
E. Delivopoulos;J. B. Theocharis
Affiliations:
Department of Electrical and Computer Engineering, Electronics and Computer Division, Aristole University of Thessaloniki, Thessaloniki 54124, Greece;Department of Electrical and Computer Engineering, Electronics and Computer Division, Aristole University of Thessaloniki, Thessaloniki 54124, Greece
Venue:
Information Sciences—Informatics and Computer Science: An International Journal
Year:
2004

Citing 18
Cited 3

A clustering algorithm for fuzzy model identification

Fuzzy Sets and Systems
A neural network classifier with disjunctive fuzzy information

Neural Networks
A simply identified Sugeno-type fuzzy model via double clustering

Information Sciences—Informatics and Computer Science: An International Journal - Special issue on modeling with soft-computing
About the use of fuzzy clustering techniques for fuzzy model identification

Fuzzy Sets and Systems
A new artificial neural network based fuzzy inference system with moving consequents in if-then rules and selected applications

Fuzzy Sets and Systems
Identification of fuzzy systems by means of an auto-tuning algorithm and its application to nonlinear systems

Fuzzy Sets and Systems
Self-Organizing Methods in Modeling: Gmdh Type Algorithms

Self-Organizing Methods in Modeling: Gmdh Type Algorithms
The design of self-organizing polynomial neural networks

Information Sciences—Informatics and Computer Science: An International Journal
Time Series Analysis, Forecasting and Control

Time Series Analysis, Forecasting and Control
On robust nonlinear modeling of a complex process with large numberof inputs using m-QRcp factorization and Cp statistic

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new method for constructing membership functions and fuzzy rulesfrom training examples

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Performance evaluation of fuzzy classifier systems formultidimensional pattern classification problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An efficient fuzzy classifier with feature selection based on fuzzyentropy

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new approach to fuzzy modeling

IEEE Transactions on Fuzzy Systems
Implementation of evolutionary fuzzy systems

IEEE Transactions on Fuzzy Systems
GA-fuzzy modeling and classification: complexity and performance

IEEE Transactions on Fuzzy Systems
Self-adaptive neuro-fuzzy inference systems for classification applications

IEEE Transactions on Fuzzy Systems
A new approach to fuzzy-neural system modeling

IEEE Transactions on Fuzzy Systems

A multilayered neuro-fuzzy classifier with self-organizing properties

Fuzzy Sets and Systems
A CBR-based fuzzy decision tree approach for database classification

Expert Systems with Applications: An International Journal
A diversity-driven structure learning algorithm for building hierarchical neuro-fuzzy classifiers

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a modified algorithm is suggested for developing polynomial neural network (PNN) models. Optimal partial description (PD) modeling is introduced at each layer of the PNN expansion, a task accomplished using the orthogonal least squares (OLS) method. Based on the initial PD models determined by the polynomial order and the number of PD inputs, OLS selects the most significant regressor terms reducing the output error variance. The method produces PNN models exhibiting a high level of accuracy and superior generalization capabilities. Additionally, parsimonious models are obtained comprising a considerably smaller number of parameters compared to the ones generated by means of the conventional PNN algorithm. Three benchmark examples are elaborated, including modeling of the gas furnace process as well as the iris and wine classification problems. Extensive simulation results and comparison with other methods in the literature, demonstrate the effectiveness of the suggested modeling approach.