Neural network sensitivity analysis applied for the reduction of the sensor matrix

  • Authors:

  • Przemyslaw M. Szecówka;Andrzej Szczurek;Maciej A. Mazurowski;Benedykt W. Licznerski;Franz Pichler

  • Affiliations:

  • Faculty of Microsystem Electronics and Photonics, Wroclaw University of Technology, Wroclaw, Poland;Institute of Environmental Protection Engineering, Wroclaw University of Technology, Wroclaw, Poland;Faculty of Microsystem Electronics and Photonics, Wroclaw University of Technology, Wroclaw, Poland;Faculty of Microsystem Electronics and Photonics, Wroclaw University of Technology, Wroclaw, Poland;Institut fur Systemwissenschaften, Johannes Kepler University, Linz, Austria

  • Venue:
  • EUROCAST'05 Proceedings of the 10th international conference on Computer Aided Systems Theory
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

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.