Logo do repositório
 
Publicação

Anomaly detection in gas sensor data using LSTM autoencoder and latent space analysis

2026Comunicação em conferência Acesso aberto
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
dc.contributor.authorAhmadi, Mahdia
dc.contributor.authorIzidorio, Felipe
dc.contributor.authorIgrejas, Getúlio
dc.contributor.authorRodrigues, Pedro João
dc.contributor.authorLopes, Rui Pedro
dc.date.accessioned2026-03-27T11:35:58Z
dc.date.available2026-03-27T11:35:58Z
dc.date.issued2026
dc.description.abstractAnomaly detection in gas sensor data is crucial for food quality control, environmental monitoring, and industrial safety, yet traditional supervised approaches require labeled anomalous data that is often impossible to obtain. This paper presents a single-class LSTM autoencoder for BME688 gas sensor anomaly detection using latent space distance analysis. Training exclusively on normal samples (Anis estrellado), the model detects anomalies by measuring Euclidean distances in the learned 8-dimensional latent space. Treating the 10-step heater profile as a temporal sequence enables the capture of sequential dependencies in gas resistance patterns. Evaluation across seven compounds achieves 100% detection for olive oil and 50.4% for air while maintaining false positive rates at or below 5% for normal classes (coffee: 0.0%, tea: 0.4%, cocoa: 5.0%). Compared to reconstruction-based methods, our approach provides 3.7× better separation, faster inference (6.8ms vs 12.3ms), and improved interpretability, offering an efficient solution for real-time anomaly detection where only normal operational data is available.eng
dc.description.sponsorshipThis work has been supported by FCT –Fundação para a Ciência e Tecnologia within the Project Scope: 2024.07316.IACDC/2024 with DOI 10.54499/2024.07316.IACDC 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; Izidorio, Felipe; Igrejas, Getúlio; Rodrigues, Pedro João; Lopes, Rui Pedro (2026). Anomaly detection in gas sensor data using LSTM autoencoder and latent space analysis. In 24th World Symposium on Applied Machine Intelligence and Informatics. Stará Lesná, Slovakia. p. 41-46. ISBN 979-8-3315-9163-2. DOI: 10.1109/sami68106.2026.11420410
dc.identifier.doi10.1109/sami68106.2026.11420410
dc.identifier.isbn979-8-3315-9163-2
dc.identifier.urihttp://hdl.handle.net/10198/36345
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIEEE
dc.relationAssociate Laboratory for Sustainability and Tecnology in Mountain Regions
dc.relation.ispartof2026 IEEE 24th World Symposium on Applied Machine Intelligence and Informatics (SAMI)
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectanomaly detection
dc.subjectLSTM
dc.subjectautoencoder
dc.subjectgas sensors
dc.subjectBME688
dc.subjectlatent space analysis
dc.subjectsingle-class learning
dc.subjecttimeseries
dc.titleAnomaly detection in gas sensor data using LSTM autoencoder and latent space analysispor
dc.typeconference paper
dspace.entity.typePublication
oaire.awardNumberLA/P/0007/2020
oaire.awardTitleAssociate Laboratory for Sustainability and Tecnology in Mountain Regions
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0007%2F2020/PT
oaire.citation.conferenceDate2026
oaire.citation.conferencePlaceStará Lesná, Slovakia
oaire.citation.endPage46
oaire.citation.startPage41
oaire.citation.title24th World Symposium on Applied Machine Intelligence and Informatics
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameIgrejas
person.familyNameRodrigues
person.familyNameLopes
person.givenNameGetúlio
person.givenNamePedro João
person.givenNameRui Pedro
person.identifier.ciencia-id1316-21BB-9015
person.identifier.ciencia-id8E14-54E4-4DB5
person.identifier.orcid0000-0002-6820-8858
person.identifier.orcid0000-0002-0555-2029
person.identifier.orcid0000-0002-9170-5078
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.isAuthorOfPublication6c5911a6-b62b-4876-9def-60096b52383a
relation.isAuthorOfPublicatione1e64423-0ec8-46ee-be96-33205c7c98a9
relation.isAuthorOfPublication.latestForDiscoveryab4092ec-d1b1-4fe0-b65a-efba1310fd5a
relation.isProjectOfPublication6255046e-bc79-4b82-8884-8b52074b4384
relation.isProjectOfPublication.latestForDiscovery6255046e-bc79-4b82-8884-8b52074b4384

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Anomaly_Detection_in_Gas_Sensor_Data_Using_LSTM_Autoencoder_and_Latent_Space_Analysis.pdf
Tamanho:
2.41 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.75 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTiG - Artigos em Proceedings Não Indexados à WoS/Scopus