论文信息 - Neural networks and abductive networks for chemical sensor signals: a case comparison

Neural networks and abductive networks for chemical sensor signals: a case comparison

Abstract Both artificial neural networks (ANNs) and the abductory induction mechanism (AIM) have been proven to be suitable for the evaluation of signals from chemical sensors with strong interactions of gas components on the catalytically active surface. The algorithms allow the calculation of calibration curves for a multisensor. AIM yields a good mean approximation within a very short time; ANN covers a broader concentration range with an adequate approximation. The signal evaluation of a set of two pellistors and another set of six MOSFETs is used for illustration.

[1] Ingemar Lundström,et al. Chemical sensor arrays and abductive networks , 1992 .

[2] D. Kohl,et al. Methane and butane concentrations in a mixture with air determined by microcalorimetric sensors and neural networks , 1993 .

[3] Julian W. Gardner,et al. Sensors and Sensory Systems for an Electronic Nose , 1992 .

[4] Stanley J. Farlow,et al. Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[5] G. Horner,et al. Gas analysis by partial model building , 1990 .

[6] Ingemar Lundström,et al. Artificial neural networks and gas sensor arrays: quantification of individual components in a gas mixture , 1991 .

[7] Ingemar Lundström,et al. Evaluation of a multiple gas mixture with a simple MOSFET gas sensor array and pattern recognition , 1990 .

[8] Evor L. Hines,et al. Detection of vapours and odours from a multisensor array using pattern-recognition techniques Part 2. Artificial neural networks , 1992 .