Title :
Parallel consensual neural networks
Author :
Benediktsson, Jon Atli ; Sveinsson, Johanes R. ; Ersoy, Okan K. ; Swain, Philip H.
Author_Institution :
Eng. Res. Inst., Iceland Univ., Reykjavik, Iceland
fDate :
1/1/1997 12:00:00 AM
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
Keywords :
neural net architecture; optimisation; pattern classification; sensor fusion; statistical analysis; analog data; binary data; classification; consensual decision; data fusion; geographic data; multisource remote sensing data; neural-network architecture; parallel consensual neural networks; stage neural networks; statistical consensus theory; wavelet packets; Analog computers; Backpropagation; Neural networks; Optimization methods; Pattern recognition; Remote sensing; Statistical analysis; Testing; Time frequency analysis; Wavelet packets;
Journal_Title :
Neural Networks, IEEE Transactions on