Computational complexity and length of recorded data for fluctuation enhanced sensing method in resistive gas sensors

This paper considers complexity and accuracy of data processing for gas detection using resistance fluctuation data observed in resistance gas sensors. A few selected methods were considered (Principal Component Analysis - PCA, Support Vector Machine - SVM). Functions like power spectral density or histogram were used to create input data vector for these algorithms from the observed resistance fluctuations. The presented considerations are important for proposing relatively cheap and mobile gas detection devices of limited computations abilities and utilizing fluctuation enhanced gas sensing method