This paper analyses the effectiveness of determining gas concentrations by using a prototype WO₃ resistive gas sensor together with fluctuation enhanced sensing. We have earlier demonstrated that this method can determine the composition of a gas mixture by using only a single sensor. In the present study, we apply Least-Squares Support-Vector-Machine-based (LS-SVM-based) nonlinear regression to determine the gas concentration of each constituent in a mixture. We confirmed that the accuracy of the estimated gas concentration could be significantly improved by applying temperature change and ultraviolet irradiation of the WO₃ layer. Fluctuation-enhanced sensing allowed us to predict the concentration of both component gases.

Sensing technology has been developed for detection of gases in some environmental, industrial, medical, and scientific applications. The main tasks of these works is to enhance performance of gas sensors taking into account their different applicability and scenarios of operation. This paper presents the descriptions, comparison and recent progress in some existing gas sensing technologies. Detailed introduction to optical sensing methods is presented. In a general way, other kinds of various sensors, such as catalytic, thermal conductivity, electrochemical, semiconductor and surface acoustic wave ones, are also presented. Furthermore, this paper focuses on performance of the optical method in detecting biomarkers in the exhaled air. There are discussed some examination results of the constructed devices. The devices operated on the basis of enhanced cavity and wavelength modulation spectroscopies. The experimental data used for analyzing applicability of these different sensing technologies in medical screening. Several suggestions related to future development are also discussed.

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.