Unsupervised machine learning application to identify single-event transients (SETs) from noise events in MOSFET transistor ionizing radiation effects

Página do item simplificado
dc.contributor.advisorOrcidhttps://orcid.org/0000-0001-7110-7241
dc.contributor.authorALLEGRO, P. R. P.
dc.contributor.authorTOUFEN, D. L.
dc.contributor.authorAGUIAR, V. A. P.
dc.contributor.authorSANTOS, L. S. A.
dc.contributor.authorOLIVEIRA W. N.
dc.contributor.authorADDED, N.
dc.contributor.authorMEDINA, N. H.
dc.contributor.authorMACCHIONE, E. L. A.
dc.contributor.authorALBERTON , S. G.
dc.contributor.authorMarcilei Aparecida Guazzelli
dc.contributor.authorMELO, M. A. A.
dc.contributor.authorOLIVEIRA, J. A.
dc.date.accessioned2023-03-27T23:28:17Z
dc.date.available2023-03-27T23:28:17Z
dc.date.issued2023
dc.description.abstract© 2023This article presents a novel application of the k-means unsupervised machine learning algorithm to the problem of identifying single event transient (SET) events from noise during heavy-ion irradiation experiments of an electronic device. We explore the performance of the k-means algorithm by analyzing experimental datasets of SET events produced by several heavy-ions irradiations of a MOSFET transistor. Data anomalies and effectiveness of the chosen features (mean, standard deviation, skewness, and kurtosis) were investigated using the Isolation Forest and Random Forest algorithms, respectively. The results show a high capability of the K-means algorithm to identify SET events from noise using the first four statistical moments as features, allowing in the future the use of this method for in situ event detection and diagnosis without previous algorithm training or pre-analysis of the experimental data.
dc.description.volume142
dc.identifier.citationALLEGRO, P. R. P.; TOUFEN, D. L; AGUIAR, V. A. P.; SANTOS, L. S. A.; OLIVEIRA, W. N.; ADDED, N.; MEDINA, N. H.; MACCHIONE, E. L. A.; ALBERTON, S. G.; GUAZZELLI, M. A.; MELO , M. A. A.; OLIVEIRA, J. A. Unsupervised machine learning application to identify single-event transients (SETs) from noise events in MOSFET transistor ionizing radiation effects. Microelectronics Reliability, v. 142, march, 2023.
dc.identifier.doi10.1016/j.microrel.2023.114916
dc.identifier.issn0026-2714
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4755
dc.relation.ispartofMicroelectronics Reliability
dc.rightsAcesso Restrito
dc.subject.otherlanguageIsolation Forest anomaly detection
dc.subject.otherlanguageK-means clustering
dc.subject.otherlanguageMachine learning
dc.subject.otherlanguageMOSFET
dc.subject.otherlanguageRadiation effects
dc.subject.otherlanguageRandom Forest
dc.titleUnsupervised machine learning application to identify single-event transients (SETs) from noise events in MOSFET transistor ionizing radiation effects
dc.typeArtigo
fei.scopus.citations6
fei.scopus.eid2-s2.0-85147092260
fei.scopus.subjectAnomaly detection
fei.scopus.subjectIsolation forest anomaly detection
fei.scopus.subjectK-means++ clustering
fei.scopus.subjectMachine-learning
fei.scopus.subjectMOS-FET
fei.scopus.subjectMOSFETs
fei.scopus.subjectRandom forests
fei.scopus.subjectSingle event transients
fei.scopus.subjectTransient events
fei.scopus.subjectUnsupervised machine learning
fei.scopus.updated2025-01-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85147092260&origin=inward
Arquivos
Coleções
Artigos