Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms
Abstract This article studies modern classification techniques in ECG signals through the transfer learning approach with CNN (Convolutional Neural Network). The proposed pre-trained network combines an Imagenet with huge labeled image datasets and a separate network composed of fully connected laye...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-12-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-024-01197-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559028549812224 |
|---|---|
| author | Pinjala N Malleswari Venkata krishna Odugu T. J. V. Subrahmanyeswara Rao T. V. N. L. Aswini |
| author_facet | Pinjala N Malleswari Venkata krishna Odugu T. J. V. Subrahmanyeswara Rao T. V. N. L. Aswini |
| author_sort | Pinjala N Malleswari |
| collection | DOAJ |
| description | Abstract This article studies modern classification techniques in ECG signals through the transfer learning approach with CNN (Convolutional Neural Network). The proposed pre-trained network combines an Imagenet with huge labeled image datasets and a separate network composed of fully connected layers. This method uses the CWT (Continuous Wavelet Transform) to construct a time-frequency visualization of ECG signals, which are subsequently transformed into RGB images. The developed images are plugged into a pre-trained CNN to retrieve the desired features. We next employ supervised learning to train the neural network on the ECG labeled data using CNN features. To train a Deep Neural Network, three sets of PhysioNet databases are used: MIT-BIH (ARR) Arrhythmia, NSR (Normal Sinus Rhythm), and BIDMC CHF (Congestive Heart Failure). The classification Accuracy, Sensitivity, Specificity, F1-score, Precision, and Detection Error Rate of the CNN classifier are compared to AlexNet, GoogleNet, Vgg16, and SqueezeNet pre-trained networks. Among all these networks, SqueezeNet provides an Acc of 98.7%, Se of 99.1%, Sp of 99.20%, F1-score of 98.33%, Precision of 98.67%, and DER of 0.89%. For further investigation, the technique suggested can be implemented in addition to Bi-LSTM on some real ECG data. |
| format | Article |
| id | doaj-art-c77f90028a2744a5a7854649c02ef1f8 |
| institution | Kabale University |
| issn | 1687-6180 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj-art-c77f90028a2744a5a7854649c02ef1f82025-01-05T12:49:52ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802024-12-012024111510.1186/s13634-024-01197-1Deep learning-assisted arrhythmia classification using 2-D ECG spectrogramsPinjala N Malleswari0Venkata krishna Odugu1T. J. V. Subrahmanyeswara Rao2T. V. N. L. Aswini3Electronics and Communication Technology, Sasi Institute of Technology & EngineeringElectronics and Communication Engineering, CVR College of EngineeringElectronics and Communication Engineering, Sasi Institute of Technology & EngineeringElectronics and Communication Engineering, Sri Vasavi Engineering CollegeAbstract This article studies modern classification techniques in ECG signals through the transfer learning approach with CNN (Convolutional Neural Network). The proposed pre-trained network combines an Imagenet with huge labeled image datasets and a separate network composed of fully connected layers. This method uses the CWT (Continuous Wavelet Transform) to construct a time-frequency visualization of ECG signals, which are subsequently transformed into RGB images. The developed images are plugged into a pre-trained CNN to retrieve the desired features. We next employ supervised learning to train the neural network on the ECG labeled data using CNN features. To train a Deep Neural Network, three sets of PhysioNet databases are used: MIT-BIH (ARR) Arrhythmia, NSR (Normal Sinus Rhythm), and BIDMC CHF (Congestive Heart Failure). The classification Accuracy, Sensitivity, Specificity, F1-score, Precision, and Detection Error Rate of the CNN classifier are compared to AlexNet, GoogleNet, Vgg16, and SqueezeNet pre-trained networks. Among all these networks, SqueezeNet provides an Acc of 98.7%, Se of 99.1%, Sp of 99.20%, F1-score of 98.33%, Precision of 98.67%, and DER of 0.89%. For further investigation, the technique suggested can be implemented in addition to Bi-LSTM on some real ECG data.https://doi.org/10.1186/s13634-024-01197-1ElectrocardiogramConvolutional Neural NetworksClassificationDeep learning |
| spellingShingle | Pinjala N Malleswari Venkata krishna Odugu T. J. V. Subrahmanyeswara Rao T. V. N. L. Aswini Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms EURASIP Journal on Advances in Signal Processing Electrocardiogram Convolutional Neural Networks Classification Deep learning |
| title | Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms |
| title_full | Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms |
| title_fullStr | Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms |
| title_full_unstemmed | Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms |
| title_short | Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms |
| title_sort | deep learning assisted arrhythmia classification using 2 d ecg spectrograms |
| topic | Electrocardiogram Convolutional Neural Networks Classification Deep learning |
| url | https://doi.org/10.1186/s13634-024-01197-1 |
| work_keys_str_mv | AT pinjalanmalleswari deeplearningassistedarrhythmiaclassificationusing2decgspectrograms AT venkatakrishnaodugu deeplearningassistedarrhythmiaclassificationusing2decgspectrograms AT tjvsubrahmanyeswararao deeplearningassistedarrhythmiaclassificationusing2decgspectrograms AT tvnlaswini deeplearningassistedarrhythmiaclassificationusing2decgspectrograms |