Nothing Special   »   [go: up one dir, main page]

Skip to main content
Log in

ECG signal classification to detect heart arrhythmia using ELM and CNN

  • Track 2: Medical Applications of Multimedia
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The cardiovascular disease is the one of the major cause of death in the today’s world. The Holter recorder is used to monitor the Electrocardiogram (ECG) signal to record the heart activity which is a popular method to detect the disease. Unfortunately, finding professionals to examine a big volume of ECG data takes up far too much medical time and money. The machine learning-based methods for recognising ECG characteristics have important role for extraction of features and ECG signal classification for Arrhythmia detection. The traditional processed used for the cardiac treatment have certain disadvantages, such as the need to understand the exact cardiac problem to recognize the disease and long learning curve to study the arrhythmia process manually. In this study twelve different heartbeat micro-classes are used with MIT-BIH Arrhythmia database for the classification. An efficient and robust virtually 12-layer deep traditionally one-dimensional CNN (convolutional neural network) is used with ELM (Extreme learning Machine) is used to propose the classification procedure. In the experiment different heart beat characteristics are identified, and the wavelet self-adaptive threshold denoising approach is applied by a combined algorithm using ELM and CNN. The results reveal that the model described in this paper performing better than the random forest, BP neural network, and other GA networks in terms of accuracy, sensitivity, resilience, and anti-noise capabilities. In this work ELM based classification on Convolutional Neural Network is developed for arrhythmia detection from the ECG signal. Its precise classification effectively conserves medical resources, which benefits clinical practise. In this study the classification result produces 98.82% accuracy which is quite satisfactory with compared with other similar types of algorithms used classification results.

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

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M (2017) Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci 415:190–198

    Article  Google Scholar 

  2. Amrani M, Hammad M, Jiang F, Wang K, Amrani A (2018) Very deep feature extraction and fusion for arrhythmias detection.  Neural Comput Appl 30(7):2047–2057

    Article  Google Scholar 

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

    Article  Google Scholar 

  4. Atal DK, Singh M (2020) Arrhythmia classification with ECG signals based on the optimization-enabled deep convolutional neural network. Comput Methods Prog Biomed 196:105607

    Article  Google Scholar 

  5. Bhagyalakshmi V, Pujeri RV, Devanagavi GD (2018) GB-SVNN: genetic BAT assisted support vector neural network for arrhythmia classification using ECG signals. J King Saud Univ Comput Inf Sci 33(1):54–67

  6. Chen T, Mazomenos EB, Maharatna K (2013) Design of a low-power on-body ECG classifier for remote cardiovascular monitoring systems. IEEE J Emerg Sel Top Circuits Syst 3(1):75–85

    Article  Google Scholar 

  7. Chen K, Franko K, Sang R (2021) Structured model pruning of convolutional networks on tensor processing units. In: International Conference on Machine Learning 2021 Workshop on Over parameterization: Pitfalls & Opportunities. arXiv:2107.04191v2

  8. Coast DA, Stern RM, Cano GG, Briller SA (1990) An approach to cardiac arrhythmia analysis using hidden Markov models. IEEE Trans Biomed Eng 37(9):826–836

    Article  Google Scholar 

  9. Dikera A, Avcib E, Tanyildizib E, Gedikpinarc M (2020) A novel ECG signal classification method using DEA-ELM. Elsevier. Med Hypotheses 136(2020):109515

    Article  Google Scholar 

  10. Ding X, He Q (2017) Energy-fluctuated multiscale feature learning with deep convnet for intelligent spindle bearing fault diagnosis. IEEE Trans Instrum Meas 66(8):1926–1935

    Article  Google Scholar 

  11. Ertam F, Avcı E (2017) A new approach for internet traffic classification: GA-WK-ELM. Measurement. 95:135–142

    Article  Google Scholar 

  12. Fan X, Yao Q, Cai Y, Miao F, Sun F (2018) Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings. IEEE J Biomed Health Inf 22(6):1744–1753

    Article  Google Scholar 

  13. Greff K, Srivastava RK, Koutnik J, Steunebrink BR, Schmidhuber J (2016) LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst 28:2222–2232

    Article  MathSciNet  Google Scholar 

  14. Guo SL, Han LN, Liu HW, Si QJ, Kong DF, Guo FS (2016) The future of remote ECG monitoring systems. J Geriatr Cardiol 13:528

    Google Scholar 

  15. Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541). Budapest, pp 985–990. https://doi.org/10.1109/IJCNN.20041380068

  16. Jadhav SM, Sanjay L, Nalbalwar SL, Ghatol AA (2011) Modular neural network based arrhythmia classification system using ECG signal data. Int J Inf Technol Knowl Manag 4(1):205–209

    Google Scholar 

  17. Jemilehin T, Adu M (2016) Design and simulation of electrocardiogram circuit with automatic analysis of ECG signal. Analele Univ. Eftimie Murgu. Resita 1:155–172

    Google Scholar 

  18. Jiang W, Kong SG (2007) Block-based neural networks for personalized ECG signal classification. IEEE Trans Neural Netw 18:1750–1761

    Article  Google Scholar 

  19. Kachuee M, Fazeli S (2018) Ecg heartbeat classification: a deep transferable representation. In: IEEE International Conference on Healthcare Informatics, pp 443–444. arXiv:1805.00794v2

  20. Karimian N, Guo Z, Tehranipoor M, Forte D (2017) Highly reliable key generation from electrocardiogram (ECG). IEEE Trans Biomed Eng 64(6):1400–1411

    Article  Google Scholar 

  21. Kiranyaz S, Ince T, Gabbouj M (2016) Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng 63(3):664–675

    Article  Google Scholar 

  22. Knee P, Thiagarajan JJ, Ramamurthy KN, Spanias A (2011) SAR target classification using sparse representations and spatial pyramids. IEEE RadarCon (RADAR), Kansas City, pp 294–298

  23. Kuila S, Dhanda N, Joardar S (2019) Feature Extraction and classification of MIT-BIH Arrhythmia Database. 2nd International Conference on Communication, Devices and Computing, Haldia Institute of Technology. Springer Proceed (LNEE) 602:417–427

    Google Scholar 

  24. Kuila S, Dhanda N, Joardar S (2020) Feature extraction of electrocardiogram signal using machine learning classification. Int J Electr Comput Eng (IJECE) 10(6):6598–6605

    Article  Google Scholar 

  25. Kuila S, Dhanda N, Joardar S (2021) ECG signal classification for arrhythmia detection using DEA and ELM. J Theor Appl Inf Technol 99(14):1817–3195

    Google Scholar 

  26. Li W (2019) Wavelets for electrocardiogram: overview and taxonomy. IEEE Access 7:25627–25649

    Article  Google Scholar 

  27. Li Q, Cai W, Wang X, Zhou Y, Feng DD, Chen M (2014) Medical image classification with convolutional neural network. In: 13th International Conference on Control Automation Robotics & Vision (ICARCV). IEEE, Singapore, pp 844–848. https://doi.org/10.1109/ICARCV.2014.7064414

  28. Li C, Hu X, Zhang L (2017) The IoT-based heart disease monitoring system for pervasive Healthcare service. ScienceDirect. Procedia Comput Sci 112:2328–2334

    Article  Google Scholar 

  29. Luo K, Li J, Wang Z, Cuschieri A (2017) Patient-specific deep architectural model for ECG classification. J Healthcare Eng 2017:1–13

  30. Martis RJ, Acharya UR, Lim CM, Mandana K, Ray AK, Chakraborty C (2013) Application of higher order cumulant features for cardiac health diagnosis using ECG signals. Int J Neural Syst 23:1350014

    Article  Google Scholar 

  31. Meng HH, Yue Z (2014) Classification of electrocardiogram signals with deep belief networks. In: IEEE 17th International Conference on Computational Science and Engineering. https://doi.org/10.1109/CSE.2014.3

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

    Article  Google Scholar 

  33. Nurmaini S, Radiyati Umi P, Muhammad Naufal R, Gani A (2018) Cardiac arrhythmias classification using deep neural networks and principal component analysis algorithm. Int J Adv Soft Comput Appl 10(2):14–32

    Google Scholar 

  34. Oh SL, Ng EYK, Tan RS, Acharya UR (2019) Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types. Comput Biol Med 105:92–101

    Article  Google Scholar 

  35. Osowski S, Hoai LT, Markiewicz T (2004) Support vector machine based expert system for reliable heartbeat recognition. IEEE Trans Biomed Eng 51:582–589

    Article  Google Scholar 

  36. Pandey SK, Janghel RP, Vani V (2020) Patient specific machine learning models for ECG signal classification. Procedia Comput Sci 167:2181–2190

    Article  Google Scholar 

  37. Pasolli E, Melgani F (2015) Genetic algorithm-based method for mitigating label noise issue in ECG signal classification. Biomed Signal Process Control 19:130–136

    Article  Google Scholar 

  38. Patro KK, Kumar PR (2017) Machine learning classification approaches for biometric recognition system using ECG signals. J Eng Sci Technol Rev 10:1–8

    Article  Google Scholar 

  39. Pławiak P, Abdar M, Acharya UR (2019) Application of new deep genetic cascade ensemble of SVM classifiers to predict the Australian credit scoring. Appl Soft Computing 84:105740. Elsevier

  40. Rahhal MMA, Bazi Y, AlHichri H, Alajlan N, Melgani F, Yager RR (2016) Deep learning approach for active classification of electrocardiogram signals. Inf Sci 345:340–354

    Article  Google Scholar 

  41. Sarkaleh MK, Shahbahrami A (2021) Classification of ECG arrhythmias using discrete wavelet transform and neural networks. Int J Comput Sci Eng Appl 2(1):1–13

    Google Scholar 

  42. Scholkopf B, Sung KK, Burges CJC, Girosi F, Niyogi FP, Poggio T, Vapnik V (1997) Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Trans Signal Process 45(11):2758–2765

    Article  Google Scholar 

  43. Sherstinsky A (2020) Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 8:404

    MathSciNet  MATH  Google Scholar 

  44. Singh BN, Tiwari AK (2006) Optimal selection of wavelet basis function applied to ECG signal Fdenoising. Dig Sign Proc 16:275–287

    Article  Google Scholar 

  45. Song GJ, Yuan Y, And Wang K (2014) Simulation of arrhythmia mechanism based on ventricular electrical conduction model. J Harbin Inst Technol 1:8

    Google Scholar 

  46. Wang S, Jiao L, Yang S, Liu H (2016) SAR image target recognition via complementary spatial pyramid coding. Neurocomputing. 196:125–132

    Article  Google Scholar 

  47. Wong SY, Yap KS, Yap HJ (2016) A Constrained optimization based extreme learning machine for noisy data regression. Neurocomputing 171:1431–1443

    Article  Google Scholar 

  48. Yang WA, Zhou Q, Tsui KL (2016) Differential evolution based feature selection and parameter optimization for extreme learning machine in tool wear estimation. Int J Prod Res 54(15):4703–4721

    Article  Google Scholar 

  49. Zhao Z, Liu C, Li Y, Wang J, Lin BS, Li J (2019) Noise rejection for wearable ECGs using modified frequency slice wavelet transform and convolution neural networks. IEEE Access 7:34060–34067

    Article  Google Scholar 

  50. Zubair M, Kim J, Yoon C (2016) An automated ECG beat classification system using convolutional neural networks. In: 6th International Conference on IT Convergence and Security (ICITCS). IEEE, Prague, pp 1–5. https://doi.org/10.1109/ICITCS.2016.7740310

Download references

Funding

Not Applicable.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sumanta Kuila.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest in this research.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kuila, S., Dhanda, N. & Joardar, S. ECG signal classification to detect heart arrhythmia using ELM and CNN. Multimed Tools Appl 82, 29857–29881 (2023). https://doi.org/10.1007/s11042-022-14233-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-14233-9

Keywords

Navigation