Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning
Recently, the interest in biometric authentication based on electrocardiograms (ECGs) has increased. Nevertheless, the ECG signal of a person may vary according to factors such as the emotional or physical state, thus hindering authentication. We propose an adaptive ECG-based authentication method t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/5/1568 |
| _version_ | 1827588474608287744 |
|---|---|
| author | Junmo Kim Geunbo Yang Juhyeong Kim Seungmin Lee Ko Keun Kim Cheolsoo Park |
| author_facet | Junmo Kim Geunbo Yang Juhyeong Kim Seungmin Lee Ko Keun Kim Cheolsoo Park |
| author_sort | Junmo Kim |
| collection | DOAJ |
| description | Recently, the interest in biometric authentication based on electrocardiograms (ECGs) has increased. Nevertheless, the ECG signal of a person may vary according to factors such as the emotional or physical state, thus hindering authentication. We propose an adaptive ECG-based authentication method that performs incremental learning to identify ECG signals from a subject under a variety of measurement conditions. An incremental support vector machine (SVM) is adopted for authentication implementing incremental learning. We collected ECG signals from 11 subjects during 10 min over six days and used the data from days 1 to 5 for incremental learning, and those from day 6 for testing. The authentication results show that the proposed system consistently reduces the false acceptance rate from 6.49% to 4.39% and increases the true acceptance rate from 61.32% to 87.61% per single ECG wave after incremental learning using data from the five days. In addition, the authentication results tested using data obtained a day after the latest training show the false acceptance rate being within reliable range (3.5–5.33%) and improvement of the true acceptance rate (70.05–87.61%) over five days. |
| first_indexed | 2024-03-09T00:35:57Z |
| format | Article |
| id | doaj.art-e18e2a51e36a4a80b2652d3b8cc3f2a0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T00:35:57Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e18e2a51e36a4a80b2652d3b8cc3f2a02023-12-11T18:14:11ZengMDPI AGSensors1424-82202021-02-01215156810.3390/s21051568Efficiently Updating ECG-Based Biometric Authentication Based on Incremental LearningJunmo Kim0Geunbo Yang1Juhyeong Kim2Seungmin Lee3Ko Keun Kim4Cheolsoo Park5Department of Computer Engineering, Kwangwoon University, Seoul 01897, KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, KoreaSchool of Electrical Engineering, College of Creative Engineering, Kookmin University, Seoul 02707, KoreaAI Lab, LG Electronics, Seoul 06763, KoreaDepartment of Computer Engineering, Kwangwoon University, Seoul 01897, KoreaRecently, the interest in biometric authentication based on electrocardiograms (ECGs) has increased. Nevertheless, the ECG signal of a person may vary according to factors such as the emotional or physical state, thus hindering authentication. We propose an adaptive ECG-based authentication method that performs incremental learning to identify ECG signals from a subject under a variety of measurement conditions. An incremental support vector machine (SVM) is adopted for authentication implementing incremental learning. We collected ECG signals from 11 subjects during 10 min over six days and used the data from days 1 to 5 for incremental learning, and those from day 6 for testing. The authentication results show that the proposed system consistently reduces the false acceptance rate from 6.49% to 4.39% and increases the true acceptance rate from 61.32% to 87.61% per single ECG wave after incremental learning using data from the five days. In addition, the authentication results tested using data obtained a day after the latest training show the false acceptance rate being within reliable range (3.5–5.33%) and improvement of the true acceptance rate (70.05–87.61%) over five days.https://www.mdpi.com/1424-8220/21/5/1568ECGauthenticationbiometricsincremental learningSVMincremental SVM |
| spellingShingle | Junmo Kim Geunbo Yang Juhyeong Kim Seungmin Lee Ko Keun Kim Cheolsoo Park Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning Sensors ECG authentication biometrics incremental learning SVM incremental SVM |
| title | Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning |
| title_full | Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning |
| title_fullStr | Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning |
| title_full_unstemmed | Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning |
| title_short | Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning |
| title_sort | efficiently updating ecg based biometric authentication based on incremental learning |
| topic | ECG authentication biometrics incremental learning SVM incremental SVM |
| url | https://www.mdpi.com/1424-8220/21/5/1568 |
| work_keys_str_mv | AT junmokim efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning AT geunboyang efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning AT juhyeongkim efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning AT seungminlee efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning AT kokeunkim efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning AT cheolsoopark efficientlyupdatingecgbasedbiometricauthenticationbasedonincrementallearning |