The air quality is a fundamental aspect for human health and its monitoring is a crucial task that needs to be performed. In this framework, an IoT ready proposal is here reported to perform both the sensing and the classification of possible air contaminants. In particular, the paper focuses on the analysis of the measurement data, by characterizing them from a metrological point of view. In detail, after having designed a suitable measurement procedure by adopting several sensors available on the platform, data are acquired during clean air exposition, air contaminant injection and steady state conditions, where contaminant has been fully injected and measurements have reached a stable state. Considerations arising from the analysis of acquired data are the basis for a classification stage, based on machine learning mechanisms. Definitively, this work represents an extension of previously presented results, and it shows how the sensor technology has been greatly improved, thus allowing to feed the detection systems with higher reliable results and therefore enhancing their performance.

A Preliminary Characterization of an Air Contaminant Detection System Based on a Multi-sensor Microsystem

Manfredini G.;Ria A.;
2021-01-01

Abstract

The air quality is a fundamental aspect for human health and its monitoring is a crucial task that needs to be performed. In this framework, an IoT ready proposal is here reported to perform both the sensing and the classification of possible air contaminants. In particular, the paper focuses on the analysis of the measurement data, by characterizing them from a metrological point of view. In detail, after having designed a suitable measurement procedure by adopting several sensors available on the platform, data are acquired during clean air exposition, air contaminant injection and steady state conditions, where contaminant has been fully injected and measurements have reached a stable state. Considerations arising from the analysis of acquired data are the basis for a classification stage, based on machine learning mechanisms. Definitively, this work represents an extension of previously presented results, and it shows how the sensor technology has been greatly improved, thus allowing to feed the detection systems with higher reliable results and therefore enhancing their performance.
2021
Gerevini, L.; Bourelly, C.; Manfredini, G.; Ria, A.; Alfano, B.; Vito, S. D.; Massera, E.; Miglietta, M. L.; Polichetti, T.
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/11568/1207589
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact