Logo do repositório
 
Publicação

Ecg biometrics using deep learning and relative score threshold classification

2020-08-01Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorBelo, David
dc.contributor.authorBento, Nuno
dc.contributor.authorSilva, Hugo
dc.contributor.authorFred, Ana
dc.contributor.authorGamboa, Hugo
dc.contributor.institutionLIBPhys-UNL
dc.contributor.institutionDF – Departamento de Física
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2021-03-26T23:26:12Z
dc.date.available2021-03-26T23:26:12Z
dc.date.issued2020-08-01
dc.descriptionPD/BDE/130216/2017
dc.description.abstractThe field of biometrics is a pattern recognition problem, where the individual traits are coded, registered, and compared with other database records. Due to the difficulties in reproducing Electrocardiograms (ECG), their usage has been emerging in the biometric field for more secure applications. Inspired by the high performance shown by Deep Neural Networks (DNN) and to mitigate the intra-variability challenges displayed by the ECG of each individual, this work proposes two architectures to improve current results in both identification (finding the registered person from a sample) and authentication (prove that the person is whom it claims) processes: Temporal Convolutional Neural Network (TCNN) and Recurrent Neural Network (RNN). Each architecture produces a similarity score, based on the prediction error of the former and the logits given by the last, and fed to the same classifier, the Relative Score Threshold Classifier (RSTC).The robustness and applicability of these architectures were trained and tested on public databases used by literature in this context: Fantasia, MIT-BIH, and CYBHi databases. Results show that overall the TCNN outperforms the RNN achieving almost 100%, 96%, and 90% accuracy, respectively, for identification and 0.0%, 0.1%, and 2.2% equal error rate (EER) for authentication processes. When comparing to previous work, both architectures reached results beyond the state-of-the-art. Nevertheless, the improvement of these techniques, such as enriching training with extra varied data and transfer learning, may provide more robust systems with a reduced time required for validation.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent20
dc.format.extent9870755
dc.identifier.doi10.3390/s20154078
dc.identifier.issn1424-8220
dc.identifier.otherPURE: 26661873
dc.identifier.otherPURE UUID: 07795a22-68af-4044-81c7-864e4740bf4e
dc.identifier.otherScopus: 85088308102
dc.identifier.otherPubMed: 32707861
dc.identifier.otherPubMedCentral: PMC7435887
dc.identifier.otherWOS: 000567705800001
dc.identifier.otherORCID: /0000-0002-4022-7424/work/91301494
dc.identifier.urihttp://hdl.handle.net/10362/114527
dc.identifier.urlhttps://www.scopus.com/pages/publications/85088308102
dc.language.isoeng
dc.peerreviewedyes
dc.subjectArtificial neural networks
dc.subjectAuthentication
dc.subjectBiometrics
dc.subjectBiosignal
dc.subjectConvolutional neural network
dc.subjectDeep learning
dc.subjectElectrocardiogram
dc.subjectIdentification
dc.subjectRecurrent neural network
dc.subjectRLTC
dc.subjectAnalytical Chemistry
dc.subjectBiochemistry
dc.subjectAtomic and Molecular Physics, and Optics
dc.subjectInstrumentation
dc.subjectElectrical and Electronic Engineering
dc.titleEcg biometrics using deep learning and relative score threshold classificationen
dc.typejournal article
degois.publication.firstPage1
degois.publication.issue15
degois.publication.lastPage20
degois.publication.titleSensors
degois.publication.volume20
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
sensors_20_04078.pdf
Tamanho:
9.41 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

FCT: DF - Artigos em revista internacional com arbitragem científica