Logo do repositório
 
Publicação

Synthetic data generation for volatile organic compounds recognition

2025Comunicação em conferência Acesso aberto
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
dc.contributor.authorAhmadi, Mahdia
dc.contributor.authorIbrahim, Ahmad Gamal
dc.contributor.authorJvarsheishvili, Mariam
dc.contributor.authorIgrejas, Getúlio
dc.contributor.authorIzidorio, Felipe
dc.contributor.authorLopes, Rui Pedro
dc.contributor.authorSoares, Caio
dc.contributor.authorRodrigues, Pedro João
dc.date.accessioned2026-03-25T12:20:53Z
dc.date.available2026-03-25T12:20:53Z
dc.date.issued2025
dc.description.abstractThe fact that machine learning (ML) models to recognize volatile organic compounds (VOC) are typically developed with limited datasets and can be expensive to gather scaled sensor data is an obstacle in their development. The Bosch BME688 is a multi-gas sensor that can give detailed environmental data, but needs large experimental campaigns to construct representative data sets. To overcome this issue, we introduce a Python library on synthetic data generation to the BME688. The tool uses the Kernel Density Estimation (KDE) to generate an empirical gas resistance distribution according to various heater profiles and uses mathematical gas mixing to generate self-configurable multi-gas simulations. Experiments by validation on coffee and oil gases show that the resulting datasets retain the statistical characteristics of actual measurements, both at the stepwise level of gas resistance distributions and at the multivariate level with Principal Component Analysis (PCA). The library generates machine learning reproducible experimentation, machine learning algorithm prototyping on mixtures of percentages, and provision of systematic evaluation of VOC recognition systems. The contribution of the work is a modular and lightweight framework to address the problem of the lack of data, facilitate the reproducible research and speed up the creation of air quality monitoring solutions based on ML.eng
dc.description.sponsorshipThis work has been supported by FCT – Fundação para a Ciência e Tecnologia within the Project Scope: 2024.07316.IACDC/2024 and by national funds: UID/05757 – Research Centre in Digitalization and Intelligent Robotics (CeDRI); and SusTEC, LA/P/0007/2020 (DOI: 10.54499/LA/P/0007/2020).
dc.identifier.citationAhmadi, Mahdia; Ibrahim, Ahmad Gamal; Jvarsheishvili, Mariam; Igrejas, Getúlio; Izidorio, Felipe, Lopes, Rui Pedro; Soares, Caio; Rodrigues, João Pedro (2025). Synthetic data generation for volatile organic compounds recognition. In RECPAD 2025 - 31st Portuguese Conference on Pattern Recognition. Aveiro, Portugal.
dc.identifier.urihttp://hdl.handle.net/10198/36269
dc.language.isoeng
dc.peerreviewedyes
dc.relationAssociate Laboratory for Sustainability and Tecnology in Mountain Regions - LA/P/0007/2020
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.titleSynthetic data generation for volatile organic compounds recognitionpor
dc.typeconference paper
dspace.entity.typePublication
oaire.awardNumberLA/P/0007/2020
oaire.awardTitleAssociate Laboratory for Sustainability and Tecnology in Mountain Regions - LA/P/0007/2020
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0007%2F2020/PT
oaire.citation.conferencePlaceAveiro, Portugal
oaire.citation.titleRECPAD 2025 - 31st Portuguese Conference on Pattern Recognition
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_ab4af688f83e57aa
person.familyNameIgrejas
person.familyNameLopes
person.familyNameRodrigues
person.givenNameGetúlio
person.givenNameRui Pedro
person.givenNamePedro João
person.identifier.ciencia-id8E14-54E4-4DB5
person.identifier.ciencia-id1316-21BB-9015
person.identifier.orcid0000-0002-6820-8858
person.identifier.orcid0000-0002-9170-5078
person.identifier.orcid0000-0002-0555-2029
person.identifier.ridM-8571-2013
person.identifier.scopus-author-id47761255900
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublicationab4092ec-d1b1-4fe0-b65a-efba1310fd5a
relation.isAuthorOfPublicatione1e64423-0ec8-46ee-be96-33205c7c98a9
relation.isAuthorOfPublication6c5911a6-b62b-4876-9def-60096b52383a
relation.isAuthorOfPublication.latestForDiscoveryab4092ec-d1b1-4fe0-b65a-efba1310fd5a
relation.isProjectOfPublication6255046e-bc79-4b82-8884-8b52074b4384
relation.isProjectOfPublication.latestForDiscovery6255046e-bc79-4b82-8884-8b52074b4384

Ficheiros

Coleções

ESTiG - Artigos em Proceedings Não Indexados à WoS/Scopus