CAB: Classifying Arrhythmias based on Imbalanced Sensor Data = CAB: Classifying Arrhythmias based on Imbalanced Sensor Data

다국어 초록 (Multilingual Abstract)

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.
Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

참고문헌 (Reference)

1 S. S. Xu, "Towards end-to-end ECG classification with raw signal extraction and deep neural networks" 23 (23): 1574-1584, 2018

2 G. B. Moody, "The impact of the MIT-BIH arrhythmia database" 20 (20): 45-50, 2001

3 AAMI, "Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms" 1998

4 Z. Zhao, "Spectro-temporal ECG analysis for atrial fibrillation detection" IEEE 1-6, 2018

5 T. Golany, "Simgans : Simulator-based generative adversarial networks for ecg synthesis to improve deep ecg classification" 3597-3606, 2020

6 D. Kim, "Secure sharing scheme of sensitive data in the precision medicine system" 64 (64): 1527-1553, 2020

7 T. Golany, "Pgans : Personalized generative adversarial networks for ECG synthesis to improve patient-specific deep ECG classification" 33 (33): 557-564, 2019

8 Y. Li, "Patient-specific ecg classification by deeper cnn from generic to dedicated" 314 : 336-346, 2018

9 X. Fan, "Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings" 22 (22): 1744-1753, 2018

10 K. N. Wang, "Medications and prescribing patterns as factors associated with hospitalizations from long-term care facilities : a systematic review" 35 (35): 423-457, 2018

11 F. A. Gers, "Lstm recurrent networks learn simple context-free and contextsensitive languages" 12 (12): 1333-1340, 2001

12 S. Saadatnejad, "LSTM-based ECG classification for continuous monitoring on personal wearable devices" 24 (24): 515-523, 2020

13 R. Li, "Interpretability analysis of heartbeat classification based on heartbeat activity’s global sequence features and Bi-LSTM-attention neural network" 7 : 109870-109883, 2019

14 V. S. Naresh, "Internet of things in healthcare : architecture, applications, challenges, and solutions" 35 (35): 411-421, 2020

15 G. Garcia, "Inter-patient ECG heartbeat classification with temporal VCG optimized by pso" 7 (7): 1-11, 2017

16 J. Niu, "Inter-patient ECG classification with symbolic representations and multi-perspective convolutional neural networks" 24 (24): 1321-1332, 2019

17 S. Mousavi, "Inter-and intra-patient ECG heartbeat classification for arrhythmia detection : a sequence to sequence deep learning approach" IEEE 1308-1312, 2019

18 E. H. Houssein, "Improving twin support vector machine based on hybrid swarm optimizer for heartbeat classification" 28 (28): 243-253, 2018

19 F. A. Elhaj, "Hybrid classification of bayesian and extreme learning machine for heartbeat classification of arrhythmia detection" 1-4, 2017

20 S. Chen, "Heartbeat classification using projected and dynamic features of ecg signal" 31 : 165-173, 2017

21 Z. Li, "Heartbeat classification using deep residual convolutional neural network from 2-lead electrocardiogram" 58 : 105-112, 2020

22 V. Mondéjar-Guerra, "Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers" 47 : 41-48, 2019

23 I. J. Goodfellow, "Generative adversarial networks"

24 Shaker, A. M., "Generalization of convolutional neural networks for ecg classification using generative adversarial networks" 8 : 35592-35605, 2020

25 M. Heusel, "Gans trained by a two time-scale update rule converge to a nash equilibrium"

26 Z. Zhou, "Fully automatic electrocardiogram classification system based on generative adversarial network with auxiliary classifier" 174 : 114809-, 2021

27 T. F. Romdhane, "Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss" 123 : 103866-, 2020

28 S., "Effective and efficient ranking and re-ranking feature selector for healthcare analytics" 26 (26): 261-268, 2020

29 E. J. d. S. Luz, "ECG-based heartbeat classification for arrhythmia detection : A survey" 127 : 144-164, 2016

30 P. Lu, "ECG classification based on long shortterm memory networks" Springer 129-140, 2019

31 P. Wang, "ECG arrhythmias detection using auxiliary classifier generative adversarial network and residual network" 7 : 100910-100922, 2019

32 M. Zabihi, "Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier" IEEE 1-4, 2017

33 T. S. Dillon, "Conjoint knowledge discovery utilizing data and content with applications in business, bio-medicine, transport logistics and electrical power systems" 35 (35): 321-334, 2020

34 K. N. Rajesh, "Classification of imbalanced ECG beats using re-sampling techniques and adaboost ensemble classifier" 41 : 242-254, 2018

35 Z. A. Nazi, "Classification of ECG signals by dot residual lstm network with data augmentation for anomaly detection" 1-5, 2019

36 A. Y. Hannun, "Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network" 25 (25): 65-69, 2019

37 B. H. X. C. Bin Zhou, "Beatgan: Anomalous rhythm detection using adversarially generated time series" 4433-4439, 2019

38 P. De Chazal, "Automatic classification of heartbeats using ECG morphology and heartbeat interval features" 51 (51): 1196-1206, 2004

39 E. K. Wang, "Automatic classification of cad ECG signals with SDAE and bidirectional long short-term network" 7 : 182873-182880, 2019

40 F. Li, "Automated heartbeat classification exploiting convolutional neural network with channel-wise attention" 7 : 122955-122963, 2019

41 X. Zhai, "Automated ECG classification using dual heartbeat coupling based on convolutional neural network" 6 : 27465-27472, 2018

42 M. Limam, "Atrial fibrillation detection and ECG classification based on convolutional recurrent neural network" IEEE 1-4, 2017

43 H. Wang, "An improved convolutional neural network based approach for automated heartbeat classification" 44 (44): 1-9, 2020

44 D. Lai, "An automatic system for real-time identifying atrial fibrillation by using a lightweight convolutional neural network" 7 : 130074-130084, 2019

45 Y. Xia, "An automatic cardiac arrhythmia classification system with wearable electrocardiogram" 6 : 16529-16538, 2018

46 Y. Shen, "Ambulatory atrial fibrillation monitoring using wearable photoplethys mography with deep learning" 1909-1916, 2019

47 A. KingaD, "Adam: a method for stochastic optimization" ICLR 2015

48 K. Jiang, "A two-level attention-based sequence-to-sequence model for accurate inter patient arrhythmia detection" IEEE 1029-1033, 2020

49 X. Wu, "A short-term ecg signal classification method based on residual network and bi-directional lstm" 19-22, 2019

50 A. Sellami, "A robust deep convolutional neural network with batch-weighted loss for heartbeat classification" 122 : 75-84, 2019

51 özal Yildirim, "A novel wavelet sequence based on deep bidirectional LSTM network model for ecg signal classification" 96 : 189-202, 2018

52 Y. Chen, "A novel method of heart failure prediction based on DPCNN-Xgboost model" 65 (65): 495-510, 2020

53 H. Dang, "A novel deep arrhythmia-diagnosis network for atrial fibrillation classification using electrocardiogram signals" 7 : 75577-75590, 2019

54 H. Wang, "A high-precision arrhythmia classification method based on dual fully connected neural network" 58 : 101874-, 2020

55 H. Shi, "A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification" 171 : 1-10, 2019

56 M. Alfaras, "A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection" 7 : 103-, 2019

57 Z. Wu, "A deep learning method to detect atrial fibrillation based on continuous wavelet transform" IEEE 1908-1912, 2019

58 U. R. Acharya, "A deep convolutional neural network model to classify heartbeats" 89 : 389-396, 2017

59 Z. C. Lipton, "A critical review of recurrent neural networks for sequence learning"