In this paper, an ECG biometric identification method, based on a two-dimensional convolutional neural network, is introduced for biometric applications. The proposed model includes two-dimensional convolutional neural networks that work parallel and receive two different sets of 2-dimensional features as input. First, ACDCT features and cepstral properties are extracted from overlapping ECG signals. Then, these features are transformed from one-dimensional representation to two-dimensional representation by matrix manipulations. For feature learning purposes, these two-dimensional features are given to the inputs of the proposed model, separately. Finally, score level fusion is applied to identify the user. Our experimental results show that the proposed biometric identification method achieves an accuracy of %88.57 and an identification rate of 90.48% for 42 persons.
Birincil Dil | en |
---|---|
Konular | Mühendislik |
Bölüm | Research Articles |
Yazarlar |
|
Destekleyen Kurum | Bursa Technical University |
Proje Numarası | 181N14 |
Tarihler |
Yayımlanma Tarihi : 24 Haziran 2019 |
Bibtex | @araştırma makalesi { jise559236,
journal = {Journal of Innovative Science and Engineering},
issn = {},
eissn = {2602-4217},
address = {ursa Technical University, Mimar Sinan Campus, Mimar Sinan Mah. Mimar Sinan Blv. Eflak Cad. No:177 16310 Yıldırım, Bursa / Turkey},
publisher = {Bursa Teknik Üniversitesi},
year = {2019},
volume = {3},
pages = {11 - 22},
doi = {10.38088/jise.559236},
title = {ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks},
key = {cite},
author = {Hanılcı, Ayca and Gürkan, Hakan}
} |
APA | Hanılcı, A , Gürkan, H . (2019). ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks . Journal of Innovative Science and Engineering , 3 (1) , 11-22 . DOI: 10.38088/jise.559236 |
MLA | Hanılcı, A , Gürkan, H . "ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks" . Journal of Innovative Science and Engineering 3 (2019 ): 11-22 <http://jise.btu.edu.tr/tr/pub/issue/44666/559236> |
Chicago | Hanılcı, A , Gürkan, H . "ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks". Journal of Innovative Science and Engineering 3 (2019 ): 11-22 |
RIS | TY - JOUR T1 - ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks AU - Ayca Hanılcı , Hakan Gürkan Y1 - 2019 PY - 2019 N1 - doi: 10.38088/jise.559236 DO - 10.38088/jise.559236 T2 - Journal of Innovative Science and Engineering JF - Journal JO - JOR SP - 11 EP - 22 VL - 3 IS - 1 SN - -2602-4217 M3 - doi: 10.38088/jise.559236 UR - https://doi.org/10.38088/jise.559236 Y2 - 2019 ER - |
EndNote | %0 Journal of Innovative Science and Engineering ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks %A Ayca Hanılcı , Hakan Gürkan %T ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks %D 2019 %J Journal of Innovative Science and Engineering %P -2602-4217 %V 3 %N 1 %R doi: 10.38088/jise.559236 %U 10.38088/jise.559236 |
ISNAD | Hanılcı, Ayca , Gürkan, Hakan . "ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks". Journal of Innovative Science and Engineering 3 / 1 (Haziran 2019): 11-22 . https://doi.org/10.38088/jise.559236 |
AMA | Hanılcı A , Gürkan H . ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks. JISE. 2019; 3(1): 11-22. |
Vancouver | Hanılcı A , Gürkan H . ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks. Journal of Innovative Science and Engineering. 2019; 3(1): 11-22. |
IEEE | A. Hanılcı ve H. Gürkan , "ECG Biometric Identification Method based on Parallel 2-D Convolutional Neural Networks", Journal of Innovative Science and Engineering, c. 3, sayı. 1, ss. 11-22, Haz. 2019, doi:10.38088/jise.559236 |