Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions

Using a single sensor as a virtual electronic nose, we demonstrate the possibility of obtaining good results with underperforming sensors that, at first glance, would be discarded. For this aim, we characterized chemical gas sensors with low repeatability and random drift towards both dangerous and...

Full description

Saved in:
Bibliographic Details
Main Authors: Guillem Domènech-Gil, Donatella Puglisi
Format: Article
Language:English
Published: MDPI AG 2024-03-01
Series:Proceedings
Subjects:
Online Access:https://www.mdpi.com/2504-3900/97/1/87
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037306022428672
author Guillem Domènech-Gil
Donatella Puglisi
author_facet Guillem Domènech-Gil
Donatella Puglisi
author_sort Guillem Domènech-Gil
collection DOAJ
description Using a single sensor as a virtual electronic nose, we demonstrate the possibility of obtaining good results with underperforming sensors that, at first glance, would be discarded. For this aim, we characterized chemical gas sensors with low repeatability and random drift towards both dangerous and innocuous volatile organic compounds (VOCs) under different levels of relative humidity. Our results show classification accuracies higher than 90% when differentiating harmful from harmless VOCs and coefficients of determination, R<sup>2</sup>, higher than 80% when determining their concentration in the parts per billion to parts per million range.
format Article
id doaj-art-043299d2a53d4843ab1b6fcbc2097801
institution DOAJ
issn 2504-3900
language English
publishDate 2024-03-01
publisher MDPI AG
record_format Article
series Proceedings
spelling doaj-art-043299d2a53d4843ab1b6fcbc20978012025-08-20T02:56:54ZengMDPI AGProceedings2504-39002024-03-019718710.3390/proceedings2024097087Machine Learning for Enhanced Operation of Underperforming Sensors in Humid ConditionsGuillem Domènech-Gil0Donatella Puglisi1Department of Thematic Studies and Environmental Change (TEMA M), Linköping University, 58183 Linköping, SwedenDepartment of Physics, Chemistry and Biology (IFM), Linköping University, 58183 Linköping, SwedenUsing a single sensor as a virtual electronic nose, we demonstrate the possibility of obtaining good results with underperforming sensors that, at first glance, would be discarded. For this aim, we characterized chemical gas sensors with low repeatability and random drift towards both dangerous and innocuous volatile organic compounds (VOCs) under different levels of relative humidity. Our results show classification accuracies higher than 90% when differentiating harmful from harmless VOCs and coefficients of determination, R<sup>2</sup>, higher than 80% when determining their concentration in the parts per billion to parts per million range.https://www.mdpi.com/2504-3900/97/1/87air quality monitoringindoorelectronic nosevirtual sensormachine learning
spellingShingle Guillem Domènech-Gil
Donatella Puglisi
Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
Proceedings
air quality monitoring
indoor
electronic nose
virtual sensor
machine learning
title Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
title_full Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
title_fullStr Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
title_full_unstemmed Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
title_short Machine Learning for Enhanced Operation of Underperforming Sensors in Humid Conditions
title_sort machine learning for enhanced operation of underperforming sensors in humid conditions
topic air quality monitoring
indoor
electronic nose
virtual sensor
machine learning
url https://www.mdpi.com/2504-3900/97/1/87
work_keys_str_mv AT guillemdomenechgil machinelearningforenhancedoperationofunderperformingsensorsinhumidconditions
AT donatellapuglisi machinelearningforenhancedoperationofunderperformingsensorsinhumidconditions