This work examines the use of Hybrid Intelligent Systems in the pattern recognition system of an artificial nose. The connectionist approaches Multi-Layer Perceptron and Time Delay Neural Networks, and the hybrid approaches Feature-Weighted Detector and Evolving Neural Fuzzy Networks were investigated. A Wavelet Filter is evaluated as a preprocessing method for odor signals. The signals generated by an artificial nose were composed by an array of conducting polymer sensors and exposed to two different odor databases.

+More

artificial nose hybrid intelligent systems odor databases connectionist approaches multilayer perceptron and time delay neural networks pattern recognition system preprocessing method hybrid approaches featureweighted detector and evolving neural fuzzy networks wavelet filter conducting polymer sensors

Cleber, Zanchettin Teresa B, Ludermir,.Hybrid neural systems for pattern recognition in artificial noses.. 15 (1-2),137-49.

Cleber, Zanchettin Teresa B, Ludermir,"Hybrid neural systems for pattern recognition in artificial noses." 15

Cleber, Zanchettin Teresa B, Ludermir,"Hybrid neural systems for pattern recognition in artificial noses."