Show simple item record

AuthorIbtehaz N.
AuthorChowdhury M.E.H.
AuthorKhandakar A.
AuthorKiranyaz, Mustafa Serkan
AuthorRahman M.S.
AuthorTahir A.
AuthorQiblawey Y.
AuthorRahman T.
Available date2022-04-26T12:31:19Z
Publication Date2021
Publication NameIEEE Transactions on Emerging Topics in Computational Intelligence
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/TETCI.2021.3131374
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85110936234&doi=10.1109%2fTETCI.2021.3131374&partnerID=40&md5=3bb87b7723ecebaae10a861b53cce7fb
URIhttp://hdl.handle.net/10576/30597
AbstractIn recent years, physiological signal-based authentication has shown great promises, for its inherent robustness against forgery. Electrocardiogram (ECG) signal, being the most widely studied biosignal, has also received the highest level of attention in this regard. It has been proven with numerous studies that by analyzing ECG signals from different persons, it is possible to identify them, with acceptable accuracy. In this work, we present, EDITH, a deep learning-based framework for ECG biometrics authentication system. Moreover, we hypothesize and demonstrate that Siamese architectures can be used over typical distance metrics for improved performance. We have evaluated EDITH using 4 commonly used datasets and outperformed the prior works using a fewer number of beats. EDITH performs competitively using just a single heartbeat (96<formula><tex>$\sim$</tex></formula>99.75&#x0025; accuracy) and can be further enhanced by fusing multiple beats (100&#x0025; accuracy from 3 to 6 beats). Furthermore, the proposed Siamese architecture manages to reduce the identity verification Equal Error Rate (EER) to 1.29 &#x0025;. A limited case study of EDITH with real-world experimental data also suggests its potential as a practical authentication system
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectAuthentication
Biological systems
Deep learning
Electrocardiography
Network architecture
1d convolutional network
1d siamese network
Biological system modeling
Biometric (access control)
Convolutional networks
Deep learning
Electrocardiogram signal
Electrocardiogram-ID
Heart beats
Task analysis
Biometrics
TitleEDITH : ECG Biometrics Aided by Deep Learning for Reliable Individual Authentication
TypeArticle
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record