Abstract
The neural network sensitivity analysis, involving neural network training and the calculation of its outputs derivative on inputs, was applied to select the least significant sensor in the multicomponent gas mixtures analysis system. The sensitivity analysis results, collected for various neural network structures were compared with the real significances of the sensors, determined experimentally. The question of the influence of the correlation of the input vector elements on the analysis results was also illustrated and discussed.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Gutierrez, F.J., Ares, L., Robla, J., et al.: Integrated Sensors for Monitoring Contaminant Gases in Atmospheres and Soils. In: Proc. IEEE International Symposium on Industrial Electronics, Guimaraes, Portugal, pp. SS113–SS115 (1997)
Szczurek, A., Szecówka, P.M., Licznerski, B.W.: Application of sensor array and neural networks for quantification of organic solvents vapours in air. Sensors and Actuators B 58, 427–432 (1999)
Martin, M.A., Santos, J.P., Agapito, J.A.: Application of artificial neural networks to calculate the partial gas concentrations in a mixture. Sensors and Actuators B 77, 471–681 (2001)
Sobański, T., Saffarpour, N.: Analysis of gas mixture using sensor array and artificial neural networks. In: Cybernetics and systems 2002. Proceedings of the Sixteenth European Meeting on Cybernetics and Systems Research, vol. 1, pp. 97–100 (2002)
Jervis, B.W., Desfieux, J., Jimenez, J., et al.: Quantification of gas concentrations in mixtures of known gases using an array of different tin-oxide sensors. IEE P-Sci. Meas. Tech. 150(3), 97–106 (2003)
Żurada, J.M., Malinowski, A., Usui, S.: Perturbation method for deleting redundant inputs of perceptron networks. Neurocomputing 14, 177–193 (1997)
Engelbrecht, A.P.: A New Pruning Heuristic Based on Variance Analysis of Sensitivity Information. IEEE Trans. on Neural Networks 12(6), 1386–1399 (2001)
Kornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Representations by Back-Propagating Errors. Nature 322, 533–536 (1986)
Figaro Gas Sensors, TGS 800 series specification, Figaro Engineering Inc.
Szecówka, P.M., Szczurek, A.: Sensors selection for gas mixtures analysis systems. In: Proc. 26th International Spring Seminar on Electronic Technology, Stara Lesna, pp. 398–403 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Szecówka, P.M., Szczurek, A., Mazurowski, M.A., Licznerski, B.W., Pichler, F. (2005). Neural Network Sensitivity Analysis Applied for the Reduction of the Sensor Matrix. In: Moreno Díaz, R., Pichler, F., Quesada Arencibia, A. (eds) Computer Aided Systems Theory – EUROCAST 2005. EUROCAST 2005. Lecture Notes in Computer Science, vol 3643. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11556985_5
Download citation
DOI: https://doi.org/10.1007/11556985_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29002-5
Online ISBN: 978-3-540-31829-3
eBook Packages: Computer ScienceComputer Science (R0)