Parallel consensual neural networks

Jon Atli Benediktsson*, Johannes R. Sveinsson, Okan K. Ersoy, Philip H. Swain

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

132 Citations (Scopus)

Abstract

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

Original languageEnglish
Pages (from-to)54-64
Number of pages11
JournalIEEE Transactions on Neural Networks
Volume8
Issue number1
DOIs
Publication statusPublished - 1997

Bibliographical note

Funding Information:
Manuscript received December 19, 1995; revised June 26, 1996. This work was supported in part by the Icelandic Research Council and the Research Fund of the University of Iceland. J. A. Benediktsson and J. R. Sveinsson are with the Engineering Research Institute, University of Iceland, 107 Reykjavik, Iceland. O. K. Ersoy and P. H. Swain are with the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907 USA. Publisher Item Identifier S 1045-9227(97)00238-5.

Other keywords

  • Accuracy
  • Classification
  • Consensus theory
  • Data fusion
  • Probability density estimation
  • Statistical pattern recognition
  • Time-frequency analysis
  • Wavelet packets

Fingerprint

Dive into the research topics of 'Parallel consensual neural networks'. Together they form a unique fingerprint.

Cite this