Wavelet-Based Kernel Construction for Heart Disease Classification
Heart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is cons...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
VSB-Technical University of Ostrava
2019-01-01
|
| Series: | Advances in Electrical and Electronic Engineering |
| Subjects: | |
| Online Access: | http://advances.utc.sk/index.php/AEEE/article/view/3270 |
| _version_ | 1797826943323734016 |
|---|---|
| author | Nguyen Thanh Hai Nghia Thanh Nguyen Manh Hung Nguyen Salvatore Livatino |
| author_facet | Nguyen Thanh Hai Nghia Thanh Nguyen Manh Hung Nguyen Salvatore Livatino |
| author_sort | Nguyen Thanh Hai |
| collection | DOAJ |
| description | Heart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is constructed based on wavelet coefficients of heartbeat signals for a classifier with high performance. In particular, a wavelet packet decomposition algorithm is applied to heartbeat signals to obtain the Approximation and Detail coefficients, which are used to calculate the parameters of the kernel. A principal component analysis algorithm with the wavelet-based kernel is employed to choose the main features of the heartbeat signals for the input of the classifier. In addition, a neural network with three hidden layers in the classifier is utilized for classifying five types of heart disease. The electrocardiogram signals in nine patients obtained from the MIT-BIH database are used to test the proposed classifier. In order to evaluate the performance of the classifier, a multi-class confusion matrix is applied to produce the performance indexes, including the Accuracy, Recall, Precision, and F1 score. The experimental results show that the proposed method gives good results for the classification of the five mentioned types of heart disease. |
| first_indexed | 2024-04-09T12:40:22Z |
| format | Article |
| id | doaj.art-00d56c7bfafd44359d315a57a5aff5aa |
| institution | Directory Open Access Journal |
| issn | 1336-1376 1804-3119 |
| language | English |
| last_indexed | 2024-04-09T12:40:22Z |
| publishDate | 2019-01-01 |
| publisher | VSB-Technical University of Ostrava |
| record_format | Article |
| series | Advances in Electrical and Electronic Engineering |
| spelling | doaj.art-00d56c7bfafd44359d315a57a5aff5aa2023-05-14T20:50:13ZengVSB-Technical University of OstravaAdvances in Electrical and Electronic Engineering1336-13761804-31192019-01-0117330631910.15598/aeee.v17i3.32701057Wavelet-Based Kernel Construction for Heart Disease ClassificationNguyen Thanh Hai0Nghia Thanh Nguyen1Manh Hung Nguyen2Salvatore Livatino3Department of Industrial Electronics and Biomedical Engineering, Faculty of Electrical and Electronic Engineering, Ho Chi Minh City University of Technology and Education, 01 Vo Van Ngan Street, Thu Duc District, Ho Chi Minh City, VietnamDepartment: Industrial Electronic-Biomedical Engineering Faculty: Electrical-Electronics Engineering HCMC University of Technology and EducationDepartment of Industrial Electronics and Biomedical Engineering, Faculty of Electrical and Electronic Engineering, Ho Chi Minh City University of Technology and Education, 01 Vo Van Ngan Street, Thu Duc District, Ho Chi Minh City, VietnamSchool of Engineering and Computer Science, University of Hertfordshire, College Lane campus, AL10 9AB Hatfield, United KingdomHeart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is constructed based on wavelet coefficients of heartbeat signals for a classifier with high performance. In particular, a wavelet packet decomposition algorithm is applied to heartbeat signals to obtain the Approximation and Detail coefficients, which are used to calculate the parameters of the kernel. A principal component analysis algorithm with the wavelet-based kernel is employed to choose the main features of the heartbeat signals for the input of the classifier. In addition, a neural network with three hidden layers in the classifier is utilized for classifying five types of heart disease. The electrocardiogram signals in nine patients obtained from the MIT-BIH database are used to test the proposed classifier. In order to evaluate the performance of the classifier, a multi-class confusion matrix is applied to produce the performance indexes, including the Accuracy, Recall, Precision, and F1 score. The experimental results show that the proposed method gives good results for the classification of the five mentioned types of heart disease.http://advances.utc.sk/index.php/AEEE/article/view/3270back-propagation neural networkelectrocardiogram signalsheart disease classificationwavelet-based kernel principal component analysiswavelet coefficients. |
| spellingShingle | Nguyen Thanh Hai Nghia Thanh Nguyen Manh Hung Nguyen Salvatore Livatino Wavelet-Based Kernel Construction for Heart Disease Classification Advances in Electrical and Electronic Engineering back-propagation neural network electrocardiogram signals heart disease classification wavelet-based kernel principal component analysis wavelet coefficients. |
| title | Wavelet-Based Kernel Construction for Heart Disease Classification |
| title_full | Wavelet-Based Kernel Construction for Heart Disease Classification |
| title_fullStr | Wavelet-Based Kernel Construction for Heart Disease Classification |
| title_full_unstemmed | Wavelet-Based Kernel Construction for Heart Disease Classification |
| title_short | Wavelet-Based Kernel Construction for Heart Disease Classification |
| title_sort | wavelet based kernel construction for heart disease classification |
| topic | back-propagation neural network electrocardiogram signals heart disease classification wavelet-based kernel principal component analysis wavelet coefficients. |
| url | http://advances.utc.sk/index.php/AEEE/article/view/3270 |
| work_keys_str_mv | AT nguyenthanhhai waveletbasedkernelconstructionforheartdiseaseclassification AT nghiathanhnguyen waveletbasedkernelconstructionforheartdiseaseclassification AT manhhungnguyen waveletbasedkernelconstructionforheartdiseaseclassification AT salvatorelivatino waveletbasedkernelconstructionforheartdiseaseclassification |