Skip to main content
SpringerLink
Log in

Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Accurate classification of electrocardiogram (ECG) signals is of significant importance for automatic diagnosis of heart diseases. In order to enable intelligent classification of arrhythmias with high accuracy, an accurate classification method based intelligent ECG classifier using the fast compression residual convolutional neural networks (FCResNet) is proposed. In the proposed method, the maximal overlap wavelet packet transform (MOWPT), which provides a comprehensive time-scale paving pattern and possesses the time-invariance property, was utilized for decomposing the original ECG signals into sub-signal samples of different scales. Subsequently, the samples of the five arrhythmia types were utilized as input to the FCResNet such that the ECG arrhythmia types were identified and classified. In the proposed FCResNet model, a fast down-sampling module and several residual block structural units were incorporated. The proposed deep learning classifier can substantially alleviate the problems of low computational efficiency, difficult convergence and model degradation. Parameter optimizations of the FCResNet were investigated via single-factor experiments. The datasets from MIT-BIH arrhythmia database were employed to test the performance of the proposed deep learning classifier. An averaged accuracy of 98.79% was achieved when the number of the wide-stride convolution in fast down-sampling module was set as 2, the batch size parameter was set as 20 and wavelet subspaces of low frequency bands in MOWPT were selected as input of the classifier. These analysis results were compared with those generated by some comparison methods to validate the superiorities and enhancements of the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  • Afonso VX, Tompkins WJ, Nguyen TQ et al (1995) Filter bank-based processing of the stress ECG. In: Proceedings of IEEE 17th international conference of the engineering in medicine and biology society, vol 2. IEEE, pp 887–888

  • Alickovic E, Subasi A (2015) Effect of multiscale PCA de-noising in ECG beat classification for diagnosis of cardiovascular diseases. Circuits Syst Signal Process 34(2):513–533

    Google Scholar 

  • Alves DK, Costa FB, Ribeiro RL et al (2016) Real-time power measurement using the maximal overlap discrete wavelet-packet transform. IEEE Trans Ind Electron 64(4):3177–3187

    Google Scholar 

  • Andersen RS, Peimankar A, Puthusserypady S (2019) A deep learning approach for real-time detection of atrial fibrillation. Expert Syst Appl 115:465–473

    Google Scholar 

  • Banerjee S, Mitra M (2010) ECG feature extraction and classification of anteroseptal myocardial infarction and normal subjects using discrete wavelet transform. In: International conference on systems in medicine and biology. IEEE, pp 55–60

  • Cao XC, Chen BQ, Yao B et al (2019) Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification. Comput Ind 106:71–84

    Google Scholar 

  • Cao XC, Yao B, Chen BQ (2019) Atrial fibrillation detection using an improved multi-Scale decomposition enhanced residual convolutional neural network. IEEE Access 7:89152–89161

    Google Scholar 

  • Chang KM, Liu SH (2011) Gaussian noise filtering from ecg by wiener filter and ensemble empirical mode decomposition. J Signal Process Syst 64(2):249–264

    Google Scholar 

  • De Albuquerque VHC, Nunes TM, Pereira DR et al (2016) Robust automated cardiac arrhythmia detection in ECG beat signals. Neural Comput Appl 29:679–693

    Google Scholar 

  • Diker A, Avci D, Avci E et al (2019) A new technique for ECG signal classification genetic algorithm Wavelet Kernel extreme learning machine. Optik 180:46–55

    Google Scholar 

  • Dutta S, Chatterjee A, Munshi S (2010) Correlation technique and least square support vector machine combine for frequency domain based ECG beat classification. Med Eng Phys 32(10):1161–1169

    Google Scholar 

  • Elhaj FA, Salim N, Harris AR et al (2016) Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals. Comput Methods Programs Biomed 127:52–63

    Google Scholar 

  • Erdenebayar U, Kim H, Park JU et al (2019) Automatic prediction of atrial fibrillation based on convolutional neural network using a short-term normal electrocardiogram signal. J Korean Med Sci 34(7):64–74

    Google Scholar 

  • Faust O, Shenfield A, Kareem M et al (2018) Automated detection of atrial fibrillation using long short-term memory network with RR interval signals. Comput Biol Med 102:327–335

    Google Scholar 

  • Güler İ, Übeylı ED (2005) ECG beat classifier designed by combined neural network model. Pattern Recognit 38(2):199–208

    Google Scholar 

  • He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 770–778

  • Hong J, Cheng H, Zhang YD et al (2019) Detecting cerebral microbleeds with transfer learning. Mach Vis Appl 30(7–8):1123–1133

    Google Scholar 

  • Huang C, Ye S, Chen H et al (2010) A novel method for detection of the transition between atrial fibrillation and sinus rhythm. IEEE Trans Biomed Eng 58(4):1113–1119

    Google Scholar 

  • Huang J, Chen B, Yao B et al (2019) ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network. IEEE Access 7:92871–92880

    Google Scholar 

  • Islam MZ, Sajjad GMS, Rahman MH et al (2012) Performance comparison of modified LMS and RLS algorithms in de-noising of ECG signals. Int J Eng Technol 2(3):466–468

    Google Scholar 

  • Ji H (2006) Research on key technologies of automatic analysis of ECG signals. National University of Defense Technology, Changsha

    Google Scholar 

  • Ji T (2019) Research on remote sensing image scene classification based on convolutional neural network. Henan University, Kaifeng

    Google Scholar 

  • Jiang X, Zhang YD (2019) Chinese sign language fingerspelling via six-layer convolutional neural network with leaky rectified linear units for therapy and rehabilitation. J Med Imaging Health Inform 9(9):2031–2090

    Google Scholar 

  • Jolliffe IT (1986) Principal component analysis

  • Kallas M, Francis C, Kanaan L, Merheb D, Honeine P, Amoud H (2012) Multi-class SVM classification combined with kernel PCA feature extraction of ECG signals. In: International conference telecommunication, pp 1–5

  • Kaur H, Rajni H (2017) A Novel approach for denoising electrocardiogram signal using hybrid technique. J Eng Sci Technol 12:1780–1791

    Google Scholar 

  • Kiranyaz S, Ince T, Gabbouj M (2015) Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng 63(3):664–675

    Google Scholar 

  • Kumar RG, Kumaraswamy YS (2012) Investigating cardiac arrhythmia in ECG using random forest classification. Int J Comput Appl 37(4):31–34

    Google Scholar 

  • Kumar M, Pachori R, Acharya U (2017) Automated diagnosis of myocardial infarction ECG signals using sample entropy in flexible analytic wavelet transform framework. Entropy 19(9):488

    Google Scholar 

  • Labati RD, Mu OE, Piuri V et al (2018) Deep-ECG: convolultional neural networks for ECG biometric recognition. Pattern Recognit Lett 126:78–85

    Google Scholar 

  • Lawhern V, Hairston WD, Mcdowell K et al (2012) Detection and classification of subject-generated artifacts in EEG signals using autoregressive models. J Neurosci Methods 208(2):181–189

    Google Scholar 

  • Li T, Min Z (2016) ECG classification using wavelet packet entropy and random forests. Entropy 18(8):285

    Google Scholar 

  • Li W, Jiang X, Sun W et al (2019) Gingivitis identification via multichannel gray-level co-occurrence matrix and particle swarm optimization neural network. Int J Imaging Syst Technol 30(2):401–411

    Google Scholar 

  • Liu C (2018) Research and design of handwritten digit recognition based on convolutional neural network. Chengdu University of Technology, Chengdu

    Google Scholar 

  • Lv Q (2018) Research on classification and recognition of cardiovascular diseases based on deep learning. Zhengzhou University, Zhengzhou

    Google Scholar 

  • Mallat S (1999) A wavelet tour of signal processing. Elsevier, New York

    MATH  Google Scholar 

  • Martis RJ, Acharya UR, Lim CM et al (2013) Application of higher order cumulant features for cardiac health diagnosis using ECG signals. Int J Neural Syst 23(04):1350014

    Google Scholar 

  • McDarby G, Celler BG, Lovell NH (1998) Characterising the discrete wavelet transform of an ECG signal with simple parameters for use in automated diagnosis. In: Proceedings of the 2nd international conference on bioelectromagnetism (Cat. No. 98TH8269). IEEE, pp 31–32

  • Melgani F, Bazi Y (2008) Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inf Technol Biomed 12(5):667–677

    Google Scholar 

  • Moody GB (2001) The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag 20(3):45–50

    Google Scholar 

  • Mostayed A, Luo J, Shu X, et al (2018) Classification of 12-lead ECG signals with Bi-directional LSTM network. arXiv preprint arXiv:1811.02090

  • Muhsin NK (2011) Noise removal of ECG signal using recursive least square algorithms. Al-Khwarizmi Eng J 7(1):13–21

    Google Scholar 

  • Müller K-R, Mika S, Rätsch G et al (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12(2):181

    Google Scholar 

  • Özbay Y, Ceylan R, Karlik B (2011) Integration of type-2 fuzzy clustering and wavelet transform in a neural network based ECG classifier. Expert Syst Appl 38(1):1004–1010

    Google Scholar 

  • Park J, Lee K, Kang K (2013) Arrhythmia detection from heartbeat using k-nearest neighbor classifier. In: IEEE international conference on bioinformatics and biomedicine, IEEE Computer Society, pp 15–22

  • Percival DB, Walden AT (2000) Wavelet methods for time series analysis. Cambridge University Press, Cambridge

    MATH  Google Scholar 

  • Poungponsri S, Yu XH (2013) An adaptive filtering approach for electrocardiogram (ECG) signal noise reduction using neural networks. Neurocomputing 117:206–213

    Google Scholar 

  • Qin S (2019) Research on handwritten digit recognition based on deep residual network. Xidian University of Electronic Science and Technology, Xi’an

    Google Scholar 

  • Raman P, Ghosh S (2016) Classification of heart diseases based on ECG analysis using FCM and SVM methods. Int J Eng Sci 2016:6739–6744

    Google Scholar 

  • Rashmi N, Begum G, Singh V (2017) ECG denoising using wavelet transform and filters. In: International conference on wireless communications, signal processing and networking (WiSPNET), pp 2395–2400

  • Salem M, Taheri S, Yuan JS (2018) ECG arrhythmia classification using transfer learning from 2-dimensional deep CNN features. In: IEEE biomedical circuits and systems conference (BioCAS), pp 1–4

  • Salloum R, Kuo CCJ (2017) ECG-based biometrics using recurrent neural networks. In: International conference on acoustics, speech and signal processing (ICASSP), pp 2062–2066

  • Sayadi O, Shamsollahi MB (2008) ECG denoising and compression using a modified extended Kalman filter structure. IEEE Trans Biomed Eng 55(9):2240–2248

    Google Scholar 

  • Sellami A, Hwang H (2019) A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Expert Syst Appl 122:75–84

    Google Scholar 

  • Shen Y, Shen Z (2010) A nonlinear non-stationary adaptive signal processing method—a review of Hilbert-Huang transform: development and application. Autom Technol Appl 29(5):1–5

    Google Scholar 

  • Singh P, Shahnawazuddin S, Pradhan G (2018) An efficient ECG denoising technique based on non-local means estimation and modified empirical mode decomposition. Circuits Syst Signal Process 37(5):1–21

    Google Scholar 

  • Slonim TYM, Slonim MA, Ovsyscher EA (1993) The use of simple FIR filters for filtering of ECG signals and a new method for post-filter signal reconstruction. In: Computers in cardiology conference, pp 871–873

  • Smital L, Vitek M, Kozumplík J et al (2012) Adaptive wavelet wiener filtering of ECG signals. IEEE Trans Biomed Eng 60(2):437–445

    Google Scholar 

  • Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. Comput Sci 1505:387–392

    Google Scholar 

  • Thakor NV, Zhu YS (1991) Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection. IEEE Trans Biomed Eng 38(8):785–794

    Google Scholar 

  • Thomas M, Das MK, Ari S (2015) Automatic ECG arrhythmia classification using dual tree complex wavelet based features. AEU Int J Electron Commun 69(4):715–721

    Google Scholar 

  • Tripathy RK, Dandapat S (2016) Detection of cardiac abnormalities from multilead ECG using multiscale phase alternation features. J Med Syst 40(6):143

    Google Scholar 

  • Übeyli ED (2009) Combining recurrent neural networks with eigenvector methods for classification of ECG beats. Digital Signal Process 19(2):320–329

    Google Scholar 

  • Varatharajan R, Manogaran G, Priyan MK (2018) A big data classification approach using LDA with an enhanced SVM method for ECG signals in cloud computing. Multimed Tools Appl 77(8):10195–10215

    Google Scholar 

  • Wang Y, He Z, Zi Y (2010) Enhancement of signal denoising and multiple fault signatures detecting in rotating machinery using dual-tree complex wavelet transform. Mech Syst Signal Process 24(1):119–137

    Google Scholar 

  • Wang Y, Zhou T, Lu H et al (2017) Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network. Sheng wu yi xue gong cheng xue za zhi Journal of biomedical engineering Shengwu yixue gongchengxue zazhi 34(4):543–551

    Google Scholar 

  • Wang SH, Xie S, Chen X et al (2019a) Alcoholism identification based on an AlexNet transfer learning model. Front Psychiatry 10:205

  • Wang SH, Zhang YD, Yang M et al (2019b) Unilateral sensorineural hearing loss identification based on double-density dual-tree complex wavelet transform and multinomial logistic regression. Integr Comput Aided Eng 26(4):411–426

    Google Scholar 

  • Wang S, Tang C, Sun J, et al (2019c) Cerebral micro-bleeding detection based on densely connected neural network. Front Neurosci 13

  • Wang S, Sun J, Mehmood I et al (2020) Cerebral micro-bleeding identification based on a nine-layer convolutional neural network with stochastic pooling. Concurr Comput Pract Exp 32(1):5130–5145

    Google Scholar 

  • Wang Q (2008) Multivariate ECG information database. China Union Medical University

  • World Health Organization (2017) Cardiovascular diseases (CVDs). https://www.who.int/mediacentre/factsheets/fs317/en/. Accessed 18 Apr 2018

  • Yao C (2012) Research on key technologies of intelligent analysis of ECG signals. Jilin University, Changchun

    Google Scholar 

  • Yeh YC, Chiou CW, Lin HJ (2012) Analyzing ECG for cardiac arrhythmia using cluster analysis. Expert Syst Appl 39(1):1000–1010

    Google Scholar 

  • Yildirim Ö (2018) A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput Biol Med 96:189–202

    Google Scholar 

  • Yin W, Yang X, Zhang L et al (2016) ECG monitoring system integrated with IR-UWB radar based on CNN. IEEE Access 4:6344–6351

    Google Scholar 

  • Yu SN, Chou KT (2008) Integration of independent component analysis and neural networks for ECG beat classification. Expert Syst Appl 34(4):2841–2846

    Google Scholar 

  • Yu L, Chen H, Dou Q et al (2016) Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging 36(4):994–1004

    Google Scholar 

  • Zeng N, Wang Z, Zhang H, Kim KE, Li Y, Liu X (2019) An improved particle filter with a novel hybrid proposal distribution for quantitative analysis of gold immune chromate graphic strips. IEEE Trans Nanotechnol 18(1):819–829

    Google Scholar 

  • Zhai X, Tin C (2018) Automated ECG Classification using dual heartbeat coupling based on convolutional neural network. IEEE Access 1:1

    Google Scholar 

  • Zhang J, Lin JL, Li XL, et al (2017) ECG signals denoising method based on improved wavelet threshold algorithm. In: Advanced information management, communicates, electronic and automation control conference, IEEE, pp 1779–1784

  • Zhang X, Liu Z, Miao Q et al (2018) Bearing fault diagnosis using a whale optimization algorithm-optimized orthogonal matching pursuit with a combined time–frequency atom dictionary. Mech Syst Signal Process 107:29–42

    Google Scholar 

  • Zhang YD, Govindaraj VV, Tang C et al (2019) High performance multiple sclerosis classification by data augmentation and AlexNet transfer learning model. J Med Imaging Health Inform 9(9):2012–2021

    Google Scholar 

  • Zhao Y (2015) Research on classification of abnormal ECG signals based on wavelet analysis and neural network. Taiyuan University of Technology, Taiyuan

    Google Scholar 

  • Zhao Q, Zhang L (2015) ECG feature extraction and classification using wavelet transform and support vector machines. In: International conference on neural networks & brain, pp 1089–1092

  • Zhou H (2018) Linear system parameter identification based on improved maximum overlapping discrete wavelet packet transform. Nanjing University of Aeronautics and Astronautics, Nanjing

    Google Scholar 

  • Zhu HH (2013) Research on ECG recognition critical methods and development on remote multi-bod-characteristic-signal monito-ring system. University of Chinese Academy of Sciences, Beijing

    Google Scholar 

Download references

Acknowledgements

This research is supported financially by National Natural Science Foundation of China (no. 51605403), the Fundamental Research Funds for the Central Universities under Grant 20720190009, International Science and Technology Cooperation Project of Fujian Province of China under Grant 2019I0003.

Author information

Authors and Affiliations

  1. School of Aerospace Engineering, Xiamen University, Xiamen, 361005, Fujian, People’s Republic of China

    Jing-Shan Huang, Bin-Qiang Chen, Nian-Yin Zeng, Xin-Cheng Cao & Yang Li

Authors
  1. Jing-Shan Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bin-Qiang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nian-Yin Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xin-Cheng Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bin-Qiang Chen.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, JS., Chen, BQ., Zeng, NY. et al. Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks. J Ambient Intell Human Comput 14, 5703–5720 (2023). https://doi.org/10.1007/s12652-020-02110-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-020-02110-y

Keywords

Search

Navigation