Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics
This paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/4/935 |
| _version_ | 1811264080489480192 |
|---|---|
| author | Yeong-Hyeon Byeon Sung-Bum Pan Keun-Chang Kwak |
| author_facet | Yeong-Hyeon Byeon Sung-Bum Pan Keun-Chang Kwak |
| author_sort | Yeong-Hyeon Byeon |
| collection | DOAJ |
| description | This paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted by transforming signals into a frequency domain that is efficient for analyzing noisy signals. By transforming the signal from the time domain to the frequency domain using the wavelet, the 1-D signal becomes a 2-D matrix, and it could be analyzed at multiresolution. However, this process makes signal analysis morphologically complex. This means that existing simple classifiers could perform poorly. We investigate the possibility of using the scalogram of ECG as input to deep convolutional neural networks of deep learning, which exhibit optimal performance for the classification of morphological imagery. When training data is small or hardware is insufficient for training, transfer learning can be used with pretrained deep models to reduce learning time, and classify it well enough. In this paper, AlexNet, GoogLeNet, and ResNet are considered as deep models of convolutional neural network. The experiments are performed on two databases for performance evaluation. Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, while Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The ResNet was 0.73%—0.27% higher than AlexNet or GoogLeNet on PTB-ECG—and the ResNet was 0.94%—0.12% higher than AlexNet or GoogLeNet on CU-ECG. |
| first_indexed | 2024-04-12T19:57:53Z |
| format | Article |
| id | doaj.art-849a33e3f43940828225c00d1db372ef |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-12T19:57:53Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-849a33e3f43940828225c00d1db372ef2022-12-22T03:18:37ZengMDPI AGSensors1424-82202019-02-0119493510.3390/s19040935s19040935Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for BiometricsYeong-Hyeon Byeon0Sung-Bum Pan1Keun-Chang Kwak2Department of Control and Instrumentation Engineering, Chosun University, Gwangju 61452, KoreaDepartment of Control and Instrumentation Engineering, Chosun University, Gwangju 61452, KoreaDepartment of Control and Instrumentation Engineering, Chosun University, Gwangju 61452, KoreaThis paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted by transforming signals into a frequency domain that is efficient for analyzing noisy signals. By transforming the signal from the time domain to the frequency domain using the wavelet, the 1-D signal becomes a 2-D matrix, and it could be analyzed at multiresolution. However, this process makes signal analysis morphologically complex. This means that existing simple classifiers could perform poorly. We investigate the possibility of using the scalogram of ECG as input to deep convolutional neural networks of deep learning, which exhibit optimal performance for the classification of morphological imagery. When training data is small or hardware is insufficient for training, transfer learning can be used with pretrained deep models to reduce learning time, and classify it well enough. In this paper, AlexNet, GoogLeNet, and ResNet are considered as deep models of convolutional neural network. The experiments are performed on two databases for performance evaluation. Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, while Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The ResNet was 0.73%—0.27% higher than AlexNet or GoogLeNet on PTB-ECG—and the ResNet was 0.94%—0.12% higher than AlexNet or GoogLeNet on CU-ECG.https://www.mdpi.com/1424-8220/19/4/935biometricdeep learningelectrocardiogramcomparative analysisscalogram |
| spellingShingle | Yeong-Hyeon Byeon Sung-Bum Pan Keun-Chang Kwak Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics Sensors biometric deep learning electrocardiogram comparative analysis scalogram |
| title | Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics |
| title_full | Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics |
| title_fullStr | Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics |
| title_full_unstemmed | Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics |
| title_short | Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics |
| title_sort | intelligent deep models based on scalograms of electrocardiogram signals for biometrics |
| topic | biometric deep learning electrocardiogram comparative analysis scalogram |
| url | https://www.mdpi.com/1424-8220/19/4/935 |
| work_keys_str_mv | AT yeonghyeonbyeon intelligentdeepmodelsbasedonscalogramsofelectrocardiogramsignalsforbiometrics AT sungbumpan intelligentdeepmodelsbasedonscalogramsofelectrocardiogramsignalsforbiometrics AT keunchangkwak intelligentdeepmodelsbasedonscalogramsofelectrocardiogramsignalsforbiometrics |