Title :
Fuzzy self-organizing hybrid neural network for gas analysis system
Author :
Osowski, Stanislaw ; Brudzewski, Kazimierz
Author_Institution :
Inst. of the Theory of Electr. Eng. & Electr. Meas., Warsaw Univ. of Technol., Poland
fDate :
4/1/2000 12:00:00 AM
Abstract :
The paper presents the gas analysis system applying the self-organizing fuzzy hybrid neural network. The network is composed of the self-organizing competitive fuzzy layer and the supervised multilayer perceptron (MLP) subnetwork, connected in cascade. The characteristic features of this network structure for gas analysis systems are discussed and the results of experiments compared to standard neural solutions based on MLP or classical hybrid network employing the Kohonen layer
Keywords :
air pollution measurement; array signal processing; chemical engineering computing; feature extraction; feedforward neural nets; fuzzy neural nets; gas sensors; learning (artificial intelligence); multilayer perceptrons; pattern clustering; self-organising feature maps; cascade connected; feature extraction; fuzzy self-organizing hybrid neural network; gas analysis system; gas pollutants recognition; learning patterns; mean absolute error; pattern clustering; self-organizing competitive fuzzy layer; semiconductor oxide gas sensors; sensor array; signal processing; supervised multilayer perceptron subnetwork; Fuzzy neural networks; Fuzzy systems; Gas detectors; Gases; Multilayer perceptrons; Neural networks; Neurons; Pollution measurement; Sensor arrays; Signal processing;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
