We present an Electronic Nose (ENose), which isaimed at identifying the presence of one out of two gases, possiblydetecting the presence of a mixture of the two. Estimation of theconcentrations of the components is also performed for a volatileorganic compound (VOC) constituted by methanol and acetone, forthe ranges 40-400 and 22-220 ppm (parts-per-million), respectively.Our system contains 8 sensors, 5 of them being gas sensors (of theclass TGS from FIGARO USA, INC., whose sensing element is a tindioxide (SnO2) semiconductor), the remaining being a temperaturesensor (LM35 from National Semiconductor Corporation), ahumidity sensor (HIH–3610 from Honeywell), and a pressure sensor(XFAM from Fujikura Ltd.).Our integrated hardware–software system uses some machinelearning principles and least square regression principle to identify atfirst a new gas sample, or a mixture, and then to estimate theconcentrations. In particular we adopt a training model using theSupport Vector Machine (SVM) approach with linear kernel to teachthe system how discriminate among different gases. Then we applyanother training model using the least square regression, to predictthe concentrations.The experimental results demonstrate that the proposedmulticlassification and regression scheme is effective in theidentification of the tested VOCs of methanol and acetone with96.61% correctness. The concentration prediction is obtained with0.979 and 0.964 correlation coefficient for the predicted versus realconcentrations of methanol and acetone, respectively.

Gas Detection via Machine Learning

Khalaf W;PACE, Calogero;
2008-01-01

Abstract

We present an Electronic Nose (ENose), which isaimed at identifying the presence of one out of two gases, possiblydetecting the presence of a mixture of the two. Estimation of theconcentrations of the components is also performed for a volatileorganic compound (VOC) constituted by methanol and acetone, forthe ranges 40-400 and 22-220 ppm (parts-per-million), respectively.Our system contains 8 sensors, 5 of them being gas sensors (of theclass TGS from FIGARO USA, INC., whose sensing element is a tindioxide (SnO2) semiconductor), the remaining being a temperaturesensor (LM35 from National Semiconductor Corporation), ahumidity sensor (HIH–3610 from Honeywell), and a pressure sensor(XFAM from Fujikura Ltd.).Our integrated hardware–software system uses some machinelearning principles and least square regression principle to identify atfirst a new gas sample, or a mixture, and then to estimate theconcentrations. In particular we adopt a training model using theSupport Vector Machine (SVM) approach with linear kernel to teachthe system how discriminate among different gases. Then we applyanother training model using the least square regression, to predictthe concentrations.The experimental results demonstrate that the proposedmulticlassification and regression scheme is effective in theidentification of the tested VOCs of methanol and acetone with96.61% correctness. The concentration prediction is obtained with0.979 and 0.964 correlation coefficient for the predicted versus realconcentrations of methanol and acetone, respectively.
Electronic Nose; Least square regression; Mixture of gases; Support Vector machine
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/133593
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact