A novel biometric identification system based on fingertip electrocardiogram and speech signals

Basit Öğe Kaydı
dc.authorid0000-0001-9107-6665
dc.authorid0000-0002-4597-0954
dc.authorid0000-0002-7008-4778
dc.contributor.authorGüven, Gökhanen_US
dc.contributor.authorGüz, Ümiten_US
dc.contributor.authorGürkan, Hakanen_US
dc.date.accessioned2021-12-06T19:01:09Z
dc.date.available2021-12-06T19:01:09Z
dc.date.issued2022-03
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Electrical-Electronics Engineeringen_US
dc.description.abstractIn this research work, we propose a one-dimensional Convolutional Neural Network (CNN) based biometric identification system that combines speech and ECG modalities. The aim is to find an effective identification strategy while enhancing both the confidence and the performance of the system. In our first approach, we have developed a voting-based ECG and speech fusion system to improve the overall performance compared to the conventional methods. In the second approach, we have developed a robust rejection algorithm to prevent unauthorized access to the fusion system. We also presented a newly developed ECG spike and inconsistent beats removal algorithm to detect and eliminate the problems caused by portable fingertip ECG devices and patient movements. Furthermore, we have achieved a system that can work with only one authorized user by adding a Universal Background Model to our algorithm. In the first approach, the proposed fusion system achieved a 100% accuracy rate for 90 people by taking the average of 3-fold cross-validation. In the second approach, by using 90 people as genuine classes and 26 people as imposter classes, the proposed system achieved 92% accuracy in identifying genuine classes and 96% accuracy in rejecting imposter classes.en_US
dc.description.sponsorshipThis research work was supported by Coordination Office for Scientific Research Projects, FMV ISIK University (Project Number: 14A203 ) and Scientific Research Projects Unit, Bursa Technical University (Project Number: 181N14 ).en_US
dc.description.sponsorshipUmit Guz received the B.S. degree in Electronics Engineering from the Istanbul University, College of Engineering, Turkey, in 1994, the M.S. and Ph.D. degrees in Electronics Engineering from the Institute of Science, Istanbul University, Turkey, in 1997 and 2002, respectively. He was awarded a post-doctoral research fellowship by the Scientific and Technological Research Council of Turkey (TUBITAK) in 2006. He was accepted as an international research fellow by the SRI (Stanford Research Institute)-International, Speech Technology and Research (STAR) Laboratory, Menlo Park, CA, USA, in 2006. He was awarded a J. William Fulbright post-doctoral research fellowship, USA, in 2007. He was accepted as an international research fellow by the International Computer Science Institute (ICSI), Speech Group at the University of California at Berkeley, Berkeley, CA, USA, in 2007 and 2008. He worked as an Assistant Professor and an Associate Professor in the Department of Electrical-Electronics Engineering, Engineering Faculty at Isik University, Istanbul, from 2008 to 2013 and from 2013 to 2019, respectively. He has been a full-time professor in the Department of Electrical-Electronics Engineering, Faculty of Engineering and Natural Sciences at Isik University, Sile, Istanbul, Turkey, since 2019. His research interest covers speech processing, automatic speech recognition, natural language processing, machine learning, and bio-signal processing.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationGüven, G., Güz, Ü. & Gürkan, H. (2022). A novel biometric identification system based on fingertip electrocardiogram and speech signals. Digital Signal Processing: A Review Journal, 121, 1-13. doi:10.1016/j.dsp.2021.103306en_US
dc.identifier.doi10.1016/j.dsp.2021.103306
dc.identifier.endpage13
dc.identifier.issn1051-2004
dc.identifier.issn1095-4333
dc.identifier.scopus2-s2.0-85120173104
dc.identifier.scopusqualityQ2
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/11729/3312
dc.identifier.urihttp://dx.doi.org/10.1016/j.dsp.2021.103306
dc.identifier.volume121
dc.identifier.wosWOS:000729878700006
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorGüz, Ümiten_US
dc.institutionauthorid0000-0002-4597-0954
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherElsevier Inc.en_US
dc.relation.ispartofDigital Signal Processing: A Review Journalen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectBiometric identificationen_US
dc.subjectBiometric identificationsen_US
dc.subjectBiometric identification systemsen_US
dc.subjectBiometric recognitionen_US
dc.subjectBiometricsen_US
dc.subjectConvolutional neural networken_US
dc.subjectConvolutional neural networksen_US
dc.subjectCNNen_US
dc.subjectElectrocardiographyen_US
dc.subjectElectrocardiogram signalen_US
dc.subjectFingertip ECGen_US
dc.subjectFusion systemsen_US
dc.subjectOne-dimensionalen_US
dc.subjectPerformanceen_US
dc.subjectSpeechen_US
dc.subjectSpeech recognitionen_US
dc.subjectSpeech signalsen_US
dc.subjectECGen_US
dc.titleA novel biometric identification system based on fingertip electrocardiogram and speech signalsen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
11729-3312.pdf
Boyut:
1.77 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

MF - Makale Koleksiyonu | Elektrik-Elektronik Mühendisliği Bölümü / Department of Electrical-Electronics Engineering
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu