论文信息 - Comparative study of connectionist techniques for implementing the pattern recognition system of an artificial nose

Comparative study of connectionist techniques for implementing the pattern recognition system of an artificial nose

This work presents an experimental analysis on the use of different neural model for the implementation of the pattern recognition system of an artificial nose. The models investigated are the multi-layer perceptrons with, respectively, the backpropagation, tabu search and resilient backpropagation; and the radial basis function networks.

M.B. de Almeida | M.C.P. de Souto | T.B. Ludermir

[1] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[2] A. Yamazaki,et al. Optimization of neural network weights and architectures for odor recognition using simulated annealing , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[3] Teresa B. Ludermir,et al. Classification of vintages of wine by artificial nose using time delay neural networks , 2001 .

[4] Julian W. Gardner,et al. Electronic noses — development and future prospects , 1996 .

[5] Marizete Silva Santos,et al. Pattern recognition of gases of petroleum based on RBF model , 2002, VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings..

[6] Teresa Bernarda Ludermir,et al. Neural Network Training with Global Optimization Techniques , 2003, Int. J. Neural Syst..

[7] Marcílio Carlos Pereira de Souto,et al. Global optimization methods for designing and training neural networks , 2002, VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings..

[8] Teresa B. Ludermir,et al. Artificial Nose And Data Analysis Using MultiLayer Perceptron , 1970 .