AI-aided e-nose calibration

Abstract

The development of the semiconductor technology and computer methods contributes to the improvements in measurement techniques of air pollution. Besides traditional techniques of air pollution measurement, such as chromatography or dynamic olfactometry, the electronic nose (EN) is attracting an increasing amount of attention in this area. EN is a device which imitates the human sense of smell. The main component of the device is an array of many non-specific gas sensors. The aim of this article is to present the result of calibration of EN composed of MOS (metal-oxide semiconductor) sensor with the use of the artificial neural networks. For data analysis, linear and artificial intelligence algorithms were employed, whose accuracy was compared.