Classification of atrial fibrillation with pretrained convolutional neural network models
Atrial Fibrillation (AF) is the most common chronic arrhythmia. Effective detection of the AF would avoid serious consequences like stroke. Conventional AF detection methods need heuristic or hand-crafted features extraction. Recently, deep learning (DL) techniques with massive data have been used o...
| Main Authors: | Qayyum, A., Meriaudeau, F., Chan, G.C.Y. |
|---|---|
| Format: | Conference or Workshop Item |
| Institution: | Universiti Teknologi Petronas |
| Record Id / ISBN-0: | utp-eprints.23542 / |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2019
|
| Online Access: |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062798021&doi=10.1109%2fIECBES.2018.8626624&partnerID=40&md5=2690246934319c896f1a609ca447f2bc http://eprints.utp.edu.my/23542/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
utp-eprints.23542 |
|---|---|
| recordtype |
eprints |
| spelling |
utp-eprints.235422021-08-19T07:57:19Z Classification of atrial fibrillation with pretrained convolutional neural network models Qayyum, A. Meriaudeau, F. Chan, G.C.Y. Atrial Fibrillation (AF) is the most common chronic arrhythmia. Effective detection of the AF would avoid serious consequences like stroke. Conventional AF detection methods need heuristic or hand-crafted features extraction. Recently, deep learning (DL) techniques with massive data have been used on image, voice and other field widely with impressive results. The ECG rhythms such as AF, normal, Noisy and other rhythms have been segmented into 3 segments per rhythm, converted into 2D images using short time Fourier transform (STFT) and fed into pretrained models. The pre-trained CNN models are used for transfer learning or are fine tuned for the detection and classification of the AF rhythm. The features extracted from the last layer of the pre-trained models are used as input to classical classification algorithms such as Ensemble classifier and support vector machine (SVM) for AF detection. The proposed approach would be have great potential on real-time monitoring of atrial fibrillation signal in electrocardiogram. Overall, our approaches achieved accuracy, sensitivity and specificity as of 97.89, 97.12 and 96.99 similar to the latest state of the art techniques but with more flexibility. © 2018 IEEE Institute of Electrical and Electronics Engineers Inc. 2019 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062798021&doi=10.1109%2fIECBES.2018.8626624&partnerID=40&md5=2690246934319c896f1a609ca447f2bc Qayyum, A. and Meriaudeau, F. and Chan, G.C.Y. (2019) Classification of atrial fibrillation with pretrained convolutional neural network models. In: UNSPECIFIED. http://eprints.utp.edu.my/23542/ |
| institution |
Universiti Teknologi Petronas |
| collection |
UTP Institutional Repository |
| description |
Atrial Fibrillation (AF) is the most common chronic arrhythmia. Effective detection of the AF would avoid serious consequences like stroke. Conventional AF detection methods need heuristic or hand-crafted features extraction. Recently, deep learning (DL) techniques with massive data have been used on image, voice and other field widely with impressive results. The ECG rhythms such as AF, normal, Noisy and other rhythms have been segmented into 3 segments per rhythm, converted into 2D images using short time Fourier transform (STFT) and fed into pretrained models. The pre-trained CNN models are used for transfer learning or are fine tuned for the detection and classification of the AF rhythm. The features extracted from the last layer of the pre-trained models are used as input to classical classification algorithms such as Ensemble classifier and support vector machine (SVM) for AF detection. The proposed approach would be have great potential on real-time monitoring of atrial fibrillation signal in electrocardiogram. Overall, our approaches achieved accuracy, sensitivity and specificity as of 97.89, 97.12 and 96.99 similar to the latest state of the art techniques but with more flexibility. © 2018 IEEE |
| format |
Conference or Workshop Item |
| author |
Qayyum, A. Meriaudeau, F. Chan, G.C.Y. |
| spellingShingle |
Qayyum, A. Meriaudeau, F. Chan, G.C.Y. Classification of atrial fibrillation with pretrained convolutional neural network models |
| author_sort |
Qayyum, A. |
| title |
Classification of atrial fibrillation with pretrained convolutional neural network models |
| title_short |
Classification of atrial fibrillation with pretrained convolutional neural network models |
| title_full |
Classification of atrial fibrillation with pretrained convolutional neural network models |
| title_fullStr |
Classification of atrial fibrillation with pretrained convolutional neural network models |
| title_full_unstemmed |
Classification of atrial fibrillation with pretrained convolutional neural network models |
| title_sort |
classification of atrial fibrillation with pretrained convolutional neural network models |
| publisher |
Institute of Electrical and Electronics Engineers Inc. |
| publishDate |
2019 |
| url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062798021&doi=10.1109%2fIECBES.2018.8626624&partnerID=40&md5=2690246934319c896f1a609ca447f2bc http://eprints.utp.edu.my/23542/ |
| _version_ |
1741196692405878784 |
| score |
11.62408 |