Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model
High-risk patients of cardiovascular disease can be provided with computerized electrocardiogram (ECG) devices to detect Arrhythmia. These require long segments of quality ECG which however can lead to missing the episode. To overcome this, we have proposed a deep-learning approach, where the scalog...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | Sensing and Bio-Sensing Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214180422000319 |
| _version_ | 1798036581492195328 |
|---|---|
| author | Shadhon Chandra Mohonta Mohammod Abdul Motin Dinesh Kant Kumar |
| author_facet | Shadhon Chandra Mohonta Mohammod Abdul Motin Dinesh Kant Kumar |
| author_sort | Shadhon Chandra Mohonta |
| collection | DOAJ |
| description | High-risk patients of cardiovascular disease can be provided with computerized electrocardiogram (ECG) devices to detect Arrhythmia. These require long segments of quality ECG which however can lead to missing the episode. To overcome this, we have proposed a deep-learning approach, where the scalogram obtained by continuous wavelet transform (CWT) is classified by the network based on the signature corresponding to arrhythmia. The CWT of the recordings is obtained and used to train the 2D convolutional neural network (CNN) for automatic arrhythmia detection. The proposed model is trained and tested to identify five types of heartbeats such as normal, left bundle branch block, right bundle branch block, atrial premature, and premature ventricular contraction. The model shows an average sensitivity, specificity, and accuracy to be 98.87%, 99.85%, and 99.65%, respectively. The result shows that the proposed model can detect arrhythmia effectively from short segments of ECG and has the potential for being used for personalised and digital healthcare. |
| first_indexed | 2024-04-11T21:14:58Z |
| format | Article |
| id | doaj.art-99a865d4d8584431b8b72cec2994e60d |
| institution | Directory Open Access Journal |
| issn | 2214-1804 |
| language | English |
| last_indexed | 2024-04-11T21:14:58Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Sensing and Bio-Sensing Research |
| spelling | doaj.art-99a865d4d8584431b8b72cec2994e60d2022-12-22T04:02:52ZengElsevierSensing and Bio-Sensing Research2214-18042022-08-0137100502Electrocardiogram based arrhythmia classification using wavelet transform with deep learning modelShadhon Chandra Mohonta0Mohammod Abdul Motin1Dinesh Kant Kumar2Department of Electrical & Electronic Engineering, Rajshahi University of Engineering & Technology, BangladeshDepartment of Electrical & Electronic Engineering, Rajshahi University of Engineering & Technology, BangladeshSchool of Engineering, RMIT University, Melbourne, VIC 3000, Australia; Corresponding author.High-risk patients of cardiovascular disease can be provided with computerized electrocardiogram (ECG) devices to detect Arrhythmia. These require long segments of quality ECG which however can lead to missing the episode. To overcome this, we have proposed a deep-learning approach, where the scalogram obtained by continuous wavelet transform (CWT) is classified by the network based on the signature corresponding to arrhythmia. The CWT of the recordings is obtained and used to train the 2D convolutional neural network (CNN) for automatic arrhythmia detection. The proposed model is trained and tested to identify five types of heartbeats such as normal, left bundle branch block, right bundle branch block, atrial premature, and premature ventricular contraction. The model shows an average sensitivity, specificity, and accuracy to be 98.87%, 99.85%, and 99.65%, respectively. The result shows that the proposed model can detect arrhythmia effectively from short segments of ECG and has the potential for being used for personalised and digital healthcare.http://www.sciencedirect.com/science/article/pii/S2214180422000319ArrhythmiaContinuous wavelet transform (CWT)Convolutional neural network (CNN)Fast Fourier transform (FFT)Short-time Fourier transform (STFT) |
| spellingShingle | Shadhon Chandra Mohonta Mohammod Abdul Motin Dinesh Kant Kumar Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model Sensing and Bio-Sensing Research Arrhythmia Continuous wavelet transform (CWT) Convolutional neural network (CNN) Fast Fourier transform (FFT) Short-time Fourier transform (STFT) |
| title | Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| title_full | Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| title_fullStr | Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| title_full_unstemmed | Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| title_short | Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| title_sort | electrocardiogram based arrhythmia classification using wavelet transform with deep learning model |
| topic | Arrhythmia Continuous wavelet transform (CWT) Convolutional neural network (CNN) Fast Fourier transform (FFT) Short-time Fourier transform (STFT) |
| url | http://www.sciencedirect.com/science/article/pii/S2214180422000319 |
| work_keys_str_mv | AT shadhonchandramohonta electrocardiogrambasedarrhythmiaclassificationusingwavelettransformwithdeeplearningmodel AT mohammodabdulmotin electrocardiogrambasedarrhythmiaclassificationusingwavelettransformwithdeeplearningmodel AT dineshkantkumar electrocardiogrambasedarrhythmiaclassificationusingwavelettransformwithdeeplearningmodel |