ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient
Electrocardiogram (ECG) is a method used by physicians to detect cardiac disease. Requirements for batch processing and accurate recognition of clinical data have led to the applications of deep-learning methods for feature extraction, classification, and denoising of ECGs; however, deep learning re...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8887504/ |
id |
doaj-81a4edf88ee743a3ab98b05f030dbc22 |
---|---|
record_format |
Article |
spelling |
doaj-81a4edf88ee743a3ab98b05f030dbc222021-03-30T00:43:32ZengIEEEIEEE Access2169-35362019-01-01715936915937810.1109/ACCESS.2019.29503838887504ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy GradientFei Ye0Fei Zhu1https://orcid.org/0000-0002-2226-2859Yuchen Fu2Bairong Shen3School of Computer Science and Technology, Soochow University, Suzhou, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou, ChinaSchool of Computer Science and Engineering, Changshu Institute of Technology, Changshu, ChinaInstitutes for Systems Genetics, West China Hospital, Sichuan University, Chengdu, ChinaElectrocardiogram (ECG) is a method used by physicians to detect cardiac disease. Requirements for batch processing and accurate recognition of clinical data have led to the applications of deep-learning methods for feature extraction, classification, and denoising of ECGs; however, deep learning requires large amounts of data and multi-feature integration of datasets, with most available methods used for ECGs incapable of extracting global features or resulting in unstable, low quality training. To address these deficiencies, we proposed a novel generative adversarial architecture called RPSeqGAN using a training process reliant upon a sequence generative adversarial network (SeqGAN) algorithm that adopts the policy gradient (PG) in reinforcement learning. Based on clinical records collected from the MIT-BIH arrhythmia database, we compared our proposed model with three deep generative models to evaluate its stability by observing the variance of their loss curves. Additionally, we generated ECGs with five periods and evaluated them according to six metrics suitable for time series. The results indicate that the proposed model showed the highest stability and data quality.https://ieeexplore.ieee.org/document/8887504/Deep learninggenerative adversarial networkspolicy gradientelectrocardiogramtime series |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fei Ye Fei Zhu Yuchen Fu Bairong Shen |
spellingShingle |
Fei Ye Fei Zhu Yuchen Fu Bairong Shen ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient IEEE Access Deep learning generative adversarial networks policy gradient electrocardiogram time series |
author_facet |
Fei Ye Fei Zhu Yuchen Fu Bairong Shen |
author_sort |
Fei Ye |
title |
ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient |
title_short |
ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient |
title_full |
ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient |
title_fullStr |
ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient |
title_full_unstemmed |
ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient |
title_sort |
ecg generation with sequence generative adversarial nets optimized by policy gradient |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Electrocardiogram (ECG) is a method used by physicians to detect cardiac disease. Requirements for batch processing and accurate recognition of clinical data have led to the applications of deep-learning methods for feature extraction, classification, and denoising of ECGs; however, deep learning requires large amounts of data and multi-feature integration of datasets, with most available methods used for ECGs incapable of extracting global features or resulting in unstable, low quality training. To address these deficiencies, we proposed a novel generative adversarial architecture called RPSeqGAN using a training process reliant upon a sequence generative adversarial network (SeqGAN) algorithm that adopts the policy gradient (PG) in reinforcement learning. Based on clinical records collected from the MIT-BIH arrhythmia database, we compared our proposed model with three deep generative models to evaluate its stability by observing the variance of their loss curves. Additionally, we generated ECGs with five periods and evaluated them according to six metrics suitable for time series. The results indicate that the proposed model showed the highest stability and data quality. |
topic |
Deep learning generative adversarial networks policy gradient electrocardiogram time series |
url |
https://ieeexplore.ieee.org/document/8887504/ |
work_keys_str_mv |
AT feiye ecggenerationwithsequencegenerativeadversarialnetsoptimizedbypolicygradient AT feizhu ecggenerationwithsequencegenerativeadversarialnetsoptimizedbypolicygradient AT yuchenfu ecggenerationwithsequencegenerativeadversarialnetsoptimizedbypolicygradient AT bairongshen ecggenerationwithsequencegenerativeadversarialnetsoptimizedbypolicygradient |
_version_ |
1724187927724949504 |