Assessing over Time Performance of an eNose Composed of 16 Single-Type MOX Gas Sensors Applied to Classify Two Volatiles

This paper assesses the over time performance of a custom electronic nose (eNose) composed an array commercial low-cost and single-type miniature metal-oxide (MOX) semiconductor gas sensors. The eNose uses 16 BME680 versatile sensor devices, each including embedded non-selective MOX that was originally proposed to measure total volatile organic compounds (TVOC) in air. has been used previously detect ethanol acetone, obtaining initial promising classification results worsened because drift. current different methods applied process information gathered from eNose. best have obtained when applying linear discriminant analysis (LDA) normalized conductance sensing layer sensors available LDA procedure by itself reduced influence drift this during evaluation period three months.