Skip to main content
Log in

Arrhythmia Detection Using ECG-Based Classification with Prioritized Feature Subset Vector-Associated Generative Adversarial Network

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Arrhythmia categorization is an exciting research in the early prevention and detection of cardiovascular illnesses, using Electrocardiogram (ECG). In the case of ECG signals, time series data are obtained by changing the time. This type of signal has the drawback of requiring repeated acquisition of comparison data with the same size as the registration data. Resolving the issue of inconsistent data size is accomplished by the use of an additional classifier-based adversarial neural networks. Adversarial data synthesis using Generative Adversarial Networks (GANs) and the generation of additional training examples solves the basic problem of insufficient data labelling. Recent studies have used the GAN architecture to create synthetic adversarial ECG signals in order to boost the amount of training data already available. The arrhythmia detection system, on the other hand, has a fragmented Convolution Neural Network (CNN) classification architecture. No flexible structural design has yet been suggested that can simultaneously discover and order abnormalities. An exceptional Prioritized Feature Subset Vector-Associated Generative Adversarial Network (PFSV-AGAN) is proposed in this research in order at a time produce ECG indications for multiple classes and sense heart-related problems. Furthermore, the model is based on class-specific ECG signals in order to generate realistic adversarial cases. This research presents a framework for ECG signal abnormality identification that has an unbalanced distribution among classes and achieves high accuracy in abnormalities categorization. After training on datasets, the classification model reliably identifies abnormalities in the proposed model. The proposed model when compared to the traditional model exhibits better performance levels.

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.

Rent this article via DeepDyve

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

Similar content being viewed by others

Availability of Supporting Data

Publicly available dataset, attached as additional supporting files.

References

  1. Al’Aref SJ, Anchouche K, Singh G, et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J. 2019;40(24):1975–86.

    Article  Google Scholar 

  2. Fritsch P, Dalla Pozza R, Ehringer-Schetitska D, et al. Cardiovascular pre-participation screening in young athletes: recommendations of the association of European paediatric cardiology. Cardiol Young. 2017;27(9):1655–60.

    Article  Google Scholar 

  3. Yang Y, Zhang E, Zhang J, et al. Relationship between occupational noise exposure and the risk factors of cardiovascular disease in China: a meta-analysis. Medicine (Baltimore). 2018;97(30): e11720.

    Article  Google Scholar 

  4. Bhatia RS, Dorian P. Screening for cardiovascular disease risk with electrocardiography. JAMA Intern Med. 2018;178(9):1163–4.

    Article  Google Scholar 

  5. Asif IM, Drezner JA. Cardiovascular screening in young athletes: evidence for the electrocardiogram. Curr Sports Med Rep. 2016;15(2):76–80.

    Article  Google Scholar 

  6. Falter M, Budts W, Goetschalckx K, Cornelissen V, Buys R. Accuracy of apple watch measurements for heart rate and energy expenditure in patients with cardiovascular disease: cross-sectional study. JMIR Mhealth Uhealth. 2019;7(3): e11889.

    Article  Google Scholar 

  7. Tracer H, Jadotte YT. Screening for cardiovascular disease risk with electrocardiography. Am Fam Phys. 2018;98(6):375–6.

    Google Scholar 

  8. Xu X, Wei S, Ma C, et al. Atrial fibrillation beat identification using the combination of modified frequency slice wavelet transform and convolutional neural networks. J Healthc Eng. 2018;2102918:8.

    Google Scholar 

  9. Acharya UR, Oh SL, Hagiwara Y, et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med. 2017;89:389–96.

    Article  Google Scholar 

  10. Attia ZI, Noseworthy PA, Lopez-Jimenez F, et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. The Lancet. 2019;394(10201):861–7.

    Article  Google Scholar 

  11. Sodmann P, Vollmer M, Nath N, Kaderali L. A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms. Physiol Meas. 2018;39(10):104005.

    Article  Google Scholar 

  12. Carrara M, Carozzi L, Moss TJ, et al. Classification of cardiac rhythm using heart rate dynamical measures: validation in MIT-BIH databases. J Electrocardiol. 2015;48(6):943–6.

    Article  Google Scholar 

  13. Marsili IA, Biasiolli L, Masè M, et al. Implementation and validation of real-time algorithms for atrial fibrillation detection on a wearable ECG device. Comput Biol Med. 2020;116:103540.

    Article  Google Scholar 

  14. Zhou F-Y, Jin L-P, Dong J. Premature ventricular contraction detection combining deep neural networks and rules inference. Artif Intell Med. 2017;79:42–51.

    Article  Google Scholar 

  15. Asatryan B, Servatius H. Revisiting the approach to diagnosis of arrhythmogenic cardiomyopathy: stick to the arrhythmia criterion! Circ Genom Precis Med. 2019;12(10):455–7.

    Article  Google Scholar 

  16. May RW, Seibert GS, Sanchez-Gonzalez MA, Fincham FD. School burnout and heart rate variability: risk of cardiovascular disease and hypertension in young adult females. Stress. 2018;21(3):211–6.

    Article  Google Scholar 

  17. Jonas DE, Reddy S, Middleton JC, et al. Screening for cardiovascular disease risk with resting or exercise electrocardiography. JAMA. 2018;319(22):2315–28.

    Article  Google Scholar 

  18. Zhang J, Yao R, Ge W, Gao J. Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG. Comput Methods Progr Biomed. 2020;183:105089.

    Article  Google Scholar 

  19. Übeyli ED. Combining recurrent neural networks with eigenvector methods for classification of ECG beats. Digit Signal Process. 2009;19(2):320–9.

    Article  Google Scholar 

  20. Froese T, Hadjiloucas S, Galvão RKH, et al. Comparison of extrasystolic ECG signal classifiers using discrete wavelet transforms. Pattern Recognit Lett. 2006;27(5):393–407.

    Article  Google Scholar 

  21. Kanani P, Padole M. ecg heartbeat arrhythmia classification using time-series augmented signals and deep learning approach. Proc Comput Sci. 2020;171:524–31.

    Article  Google Scholar 

  22. Latif G, Al Anezi FY, Zikria M, et al. EEG-ECG Signals classification for arrhythmia detection using decision trees. In: Proceedingsof the Fourth International Conference on Inventive Systems and Control (ICISC 2020). Coimbatore, 2020; pp. 192–6.

  23. Wu J, Li F, Chen Z, et al. Patient-specific ECG classification with integrated long short-term memory and convolutional neuralnetworks. IEICE Trans Inform Syst. 2020;E103D(5):1153–63.

    Article  Google Scholar 

  24. Zhang J, Tian J, Cao Y, et al. Deep time–frequency representation and progressive decision fusion for ECG classification. Knowl-Based Syst. 2020;190: 105402.

    Article  Google Scholar 

  25. Shankar MG, Babu CG. An exploration of ECG signal feature selection and classification using machine learning techniques. Int J Innov Technol Explor Eng. 2020;9(3):797–804.

    Article  Google Scholar 

  26. Diker A, Avci E, Tanyildizi E, et al. A novel ECG signal classification method using DEA-ELM. Med Hypotheses. 2020;136: 109515.

    Article  Google Scholar 

  27. Rida I, Al-Maadeed N, Al-Maadeed S, et al. A comprehensive overview of feature representation for biometric recognition. Multimed Tools Appl. 2020;79:4867–90.

    Article  Google Scholar 

  28. Fei L, Zhang B, Xu Y, Tian C, Rida I, Zhang D. Jointly heterogeneous palmprint discriminant feature learning. IEEE Trans Neural Netw Learn Syst. 2022;33(9):4979–90.

    Article  Google Scholar 

  29. Boubchir RL, Al-Maadeed N, Al-Maadeed S., Robust model-free gait recognition by statistical dependency feature selection and Globality-Locality Preserving Projections. In: 2016 39th International Conference on Telecommunications and Signal Processing (TSP), Vienna, Austria, 2016; pp. 652–55.

  30. Rida,I. Temporal signals classification. (Classification de signaux temporels) (Doctoral dissertation, Normandy University, France). 2017.

  31. Imad Rida SA, Bouridane A. Gait recognition based on modified phase-only correlation. Signal, Image Video Process. 2016;10:463–70.

    Article  Google Scholar 

  32. Anwar S, Rida I. Data augmentation-based novel deep learning method for deep faked images detection. ACM Trans Multimed Comput Commun Appl. 2023.

  33. Rida I. Feature extraction for temporal signal recognition: an overview. In: Audio and speech processing, arXiv:1812.01780, https://doi.org/10.48550/arXiv.1812.01780.

  34. Parashar A, Ding W, Rida I. Intra-class variations with deep learning-based gait analysis: A comprehensive survey of covariates and methods. Neurocomputing. 2022;505:315–38 (ISSN 0925-2312).

    Article  Google Scholar 

Download references

Acknowledgements

Shaik Janbhasha thanks to Dr Naga Kishore Bhavanam for his complete technical advice and guidance on the preparation of this article, and the anonymous reviewers for their valuable feedback.

Funding

This study was no financial support from any institute or organization.

Author information

Authors and Affiliations

Authors

Contributions

SNKB suggested and guided complete research work, according to his suggestion and guidance SJ did this work. We would like to confirm that all authors were fully involved in the study and preparation of the manuscript.

Corresponding author

Correspondence to Janbhasha Shaik.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflicts of interest.

Ethical Approval and Consent to Participate

Not applicable.

Human and Animal Ethics

Not applicable.

Consent for Publication

Not applicable.

Additional information

Publisher's Note

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

This article is part of the topical collection “Research Trends in Computational Intelligence” guest edited by Anshul Verma, Pradeepika Verma, Vivek Kumar Singh and S. Karthikeyan.

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

Shaik, J., Bhavanam, S.N. Arrhythmia Detection Using ECG-Based Classification with Prioritized Feature Subset Vector-Associated Generative Adversarial Network. SN COMPUT. SCI. 4, 519 (2023). https://doi.org/10.1007/s42979-023-01970-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-01970-3

Keywords

Navigation