Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks
Abstract Early heart disease class detection is of great interest to reduce the mortality rate. In this context, computational techniques have been proposed to solve this issue. Thus, here, a deep learning architecture is proposed to automatically classify the patient’s Electrocardiogram (ECG) signa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-03-01
|
| Series: | IET Smart Cities |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/smc2.12003 |
| _version_ | 1811215869213147136 |
|---|---|
| author | Marwa Fradi Lazhar Khriji Mohsen Machhout Abdulnasir Hossen |
| author_facet | Marwa Fradi Lazhar Khriji Mohsen Machhout Abdulnasir Hossen |
| author_sort | Marwa Fradi |
| collection | DOAJ |
| description | Abstract Early heart disease class detection is of great interest to reduce the mortality rate. In this context, computational techniques have been proposed to solve this issue. Thus, here, a deep learning architecture is proposed to automatically classify the patient’s Electrocardiogram (ECG) signal into a specific class according to the ANSI–AAMI standards. The proposed methodology is a multi‐stage technique. The first stage combines an R–R peak extraction with a low‐pass filter applied on the ECG data for noise removal. The second stage shows the proposed convolutional neural network‐based fully connected layers architecture, using different network optimizers. Different ECG databases, including challenging tasks, have been used for validation purpose. The whole system is implemented on both CPU and GPU for complexity analysis. For the predicted improved PTB data set, the classification accuracy results achieve 99.37%, 99.15% and 99.31% for training, validation and testing, respectively. Besides, for the MIT‐BIH‐database, the training, validation and testing accuracies are 99.5%, 99.06% and 99.34%, respectively. A top F1‐score of 0.99 is obtained. Experimental results show a high achievement compared to the state‐of‐the‐art models where the implementation of GPU confirms the low computational complexity of the system. |
| first_indexed | 2024-04-12T06:30:48Z |
| format | Article |
| id | doaj.art-e2b4b6b845624d5d8e4a0eb004f1ce79 |
| institution | Directory Open Access Journal |
| issn | 2631-7680 |
| language | English |
| last_indexed | 2024-04-12T06:30:48Z |
| publishDate | 2021-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Smart Cities |
| spelling | doaj.art-e2b4b6b845624d5d8e4a0eb004f1ce792022-12-22T03:44:02ZengWileyIET Smart Cities2631-76802021-03-013131510.1049/smc2.12003Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networksMarwa Fradi0Lazhar Khriji1Mohsen Machhout2Abdulnasir Hossen3Department of Physics Electronics and Microelectronics Laboratory Faculty of Sciences of Monastir University of Monastir Monastir TunisiaDepartment of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat OmanDepartment of Physics Electronics and Microelectronics Laboratory Faculty of Sciences of Monastir University of Monastir Monastir TunisiaDepartment of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat OmanAbstract Early heart disease class detection is of great interest to reduce the mortality rate. In this context, computational techniques have been proposed to solve this issue. Thus, here, a deep learning architecture is proposed to automatically classify the patient’s Electrocardiogram (ECG) signal into a specific class according to the ANSI–AAMI standards. The proposed methodology is a multi‐stage technique. The first stage combines an R–R peak extraction with a low‐pass filter applied on the ECG data for noise removal. The second stage shows the proposed convolutional neural network‐based fully connected layers architecture, using different network optimizers. Different ECG databases, including challenging tasks, have been used for validation purpose. The whole system is implemented on both CPU and GPU for complexity analysis. For the predicted improved PTB data set, the classification accuracy results achieve 99.37%, 99.15% and 99.31% for training, validation and testing, respectively. Besides, for the MIT‐BIH‐database, the training, validation and testing accuracies are 99.5%, 99.06% and 99.34%, respectively. A top F1‐score of 0.99 is obtained. Experimental results show a high achievement compared to the state‐of‐the‐art models where the implementation of GPU confirms the low computational complexity of the system.https://doi.org/10.1049/smc2.12003diseaseselectrocardiographylearning (artificial intelligence)low‐pass filtersmedical signal detectionsignal classification |
| spellingShingle | Marwa Fradi Lazhar Khriji Mohsen Machhout Abdulnasir Hossen Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks IET Smart Cities diseases electrocardiography learning (artificial intelligence) low‐pass filters medical signal detection signal classification |
| title | Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks |
| title_full | Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks |
| title_fullStr | Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks |
| title_full_unstemmed | Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks |
| title_short | Automatic heart disease class detection using convolutional neural network architecture‐based various optimizers‐networks |
| title_sort | automatic heart disease class detection using convolutional neural network architecture based various optimizers networks |
| topic | diseases electrocardiography learning (artificial intelligence) low‐pass filters medical signal detection signal classification |
| url | https://doi.org/10.1049/smc2.12003 |
| work_keys_str_mv | AT marwafradi automaticheartdiseaseclassdetectionusingconvolutionalneuralnetworkarchitecturebasedvariousoptimizersnetworks AT lazharkhriji automaticheartdiseaseclassdetectionusingconvolutionalneuralnetworkarchitecturebasedvariousoptimizersnetworks AT mohsenmachhout automaticheartdiseaseclassdetectionusingconvolutionalneuralnetworkarchitecturebasedvariousoptimizersnetworks AT abdulnasirhossen automaticheartdiseaseclassdetectionusingconvolutionalneuralnetworkarchitecturebasedvariousoptimizersnetworks |