Skip to main content
SpringerLink
Log in

A new BAT optimization algorithm based feature selection method for electrocardiogram heartbeat classification using empirical wavelet transform and Fisher ratio

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

In this paper, a novel feature selection method is proposed for the categorization of electrocardiogram (ECG) heartbeats. The proposed technique uses the Fisher ratio and BAT optimization algorithm to obtain the best feature set for ECG classification. The MIT-BIH arrhythmia database contains sixteen classes of the ECG heartbeats. The MIT-BIH ECG arrhythmia database divided into intra-patient and inter-patient schemes to be used in this study. The proposed feature selection methodology works in following steps: firstly, features are extracted using empirical wavelet transform (EWT) and then higher-order statistics, as well as symbolic features, are computed for each decomposed mode of EWT. Thereafter, the complete feature vector is obtained by the conjunction of EWT based features and RR interval features. Secondly, for feature selection, the Fisher ratio is utilized. It is optimized by using BAT algorithm so as to have maximal discrimination of the between classes. Finally, in the classification step, the k-nearest neighbor classifier is used to classify the heartbeats. The performance measures i.e., accuracy, sensitivity, positive predictivity, specificity for intra-patient scheme are 99.80%, 99.80%, 99.80%, 99.987% and for inter-patient scheme are 97.59%, 97.589%, 97.589%, 99.196% respectively. The proposed feature selection technique outperforms the other state of art feature selection methods.

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

Similar content being viewed by others

References

  1. Sidney S, Rosamond WD, Howard VJ, Luepker RV (2013) The heart disease and stroke statistics-2013 update and the need for a national cardiovascular surveillance system. Circulation 127:21–23. https://doi.org/10.1161/CIRCULATIONAHA.112.155911

    Article  Google Scholar 

  2. Rahman MZU, Karthik GVS, Fathima SY, Lay-Ekuakille A (2013) An efficient cardiac signal enhancement using time–frequency realization of leaky adaptive noise cancelers for remote health monitoring systems. Measurement 46:3815–3835

    Google Scholar 

  3. Rai HM, Trivedi A, Shukla S (2013) ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier. Measurement 46:3238–3246

    Google Scholar 

  4. Kutlu Y, Kuntalp D (2012) Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients. Comput Methods Programs Biomed 105:257–267. https://doi.org/10.1016/j.cmpb.2011.10.002

    Article  Google Scholar 

  5. Mert A (2016) ECG feature extraction based on the bandwidth properties of variational mode decomposition. Physiol Meas 37:530–543. https://doi.org/10.1088/0967-3334/37/4/530

    Article  Google Scholar 

  6. Zadeh AE, Khazaee A, Ranaee V (2010) Classification of the electrocardiogram signals using supervised classifiers and efficient features. Comput Methods Programs Biomed 99:179–194. https://doi.org/10.1016/j.cmpb.2010.04.013

    Article  Google Scholar 

  7. Xiao QU, Wei C, Fei GD (2011) ECG signal classification based on BPNN. In: international conference on electric information and control engineering, pp 1362–1364

  8. Chen S, Hua W, Li Z et al (2017) Heartbeat classification using projected and dynamic features of ECG signal. Biomed Signal Process Control 31:165–173. https://doi.org/10.1016/j.bspc.2016.07.010

    Article  Google Scholar 

  9. Joy R, Acharya UR, Mandana KM et al (2013) Biomedical signal processing and control cardiac decision making using higher order spectra. Biomed Signal Process Control 8:193–203. https://doi.org/10.1016/j.bspc.2012.08.004

    Article  Google Scholar 

  10. Afkhami RG, Azarnia G, Tinati MA (2015) Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals. Pattern Recognit Lett 70:45–51. https://doi.org/10.1016/j.patrec.2015.11.018

    Article  Google Scholar 

  11. Khazaee A, Ebrahimzadeh A (2010) Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features. Biomed Signal Process Control 5:252–263. https://doi.org/10.1016/j.bspc.2010.07.006

    Article  Google Scholar 

  12. Zhang Z, Dong J, Luo X et al (2014) Heartbeat classification using disease-specific feature selection. Comput Biol Med 46:79–89

    Google Scholar 

  13. Lin T-S, Meador J (1992) Statistical feature extraction and selection for IC test pattern analysis. In: IEEE international symposium on circuits and systems, pp 391–394

  14. Lisboa PJG, Mehri-Dehnavi R (1996) Sensitivity methods for variable selection using the MLP. In: International workshop on neural networks for identification, control, robotics and signal/image processing, pp 330–338

  15. Mar T, Zaunseder S, Martínez JP et al (2011) Optimization of ECG classification by means of feature selection. IEEE Trans Biomed Eng 58:2168–2177

    Google Scholar 

  16. Doquire G, De Lannoy G, François D, Verleysen M (2011) Feature selection for interpatient supervised heart beat classification. Comput Intell Neurosci 2011:1

    Google Scholar 

  17. Wang X, Yang J, Teng X et al (2007) Feature selection based on rough sets and particle swarm optimization. Pattern Recognit Lett 28:459–471

    Google Scholar 

  18. Biswas R, Goel P, Mukerjee A, Shawky H (2005) The application of genetic algorithms for a three-way optimization of risk-return-tax tradeoff in equity mutual fund portfolios. University at Albany

  19. Yeh Y-C, Wang W-J, Chiou CW (2010) Feature selection algorithm for ECG signals using range-overlaps method. Expert Syst Appl 37:3499–3512. https://doi.org/10.1016/j.eswa.2009.10.037

    Article  Google Scholar 

  20. Lu L, Yan J, de Silva CW (2016) Feature selection for ECG signal processing using improved genetic algorithm and empirical mode decomposition. Measurement 94:372–381. https://doi.org/10.1016/j.measurement.2016.07.043

    Article  Google Scholar 

  21. Alonso-Atienza F, Morgado E, Fernandez-Martinez L et al (2014) Detection of life-threatening arrhythmias using feature selection and support vector machines. IEEE Trans Biomed Eng 61:832–840

    Google Scholar 

  22. Llamedo M, Martínez JP (2011) Heartbeat classification using feature selection driven by database generalization criteria. IEEE Trans Biomed Eng 58:616–625

    Google Scholar 

  23. Ray KC, Sharma P (2016) Efficient methodology for electrocardiogram beat classification. IET Signal Process 10:825–832. https://doi.org/10.1049/iet-spr.2015.0274

    Article  Google Scholar 

  24. Saeys Y, Inza I, Larrañaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23:2507–2517

    Google Scholar 

  25. Dash M, Liu H (1997) Feature selection for classification. Intell data Anal 1:131–156

    Google Scholar 

  26. Pattarin F, Paterlini S, Minerva T (2004) Clustering financial time series: an application to mutual funds style analysis. Comput Stat Data Anal 47:353–372

    MathSciNet  MATH  Google Scholar 

  27. Pudil P, Novovicova J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15:1119–1125

    Google Scholar 

  28. Lin S-W, Ying K-C, Chen S-C, Lee Z-J (2008) Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst Appl 35:1817–1824

    Google Scholar 

  29. Kumar S, Sharma A (2018) A new parameter tuning approach for enhanced motor imagery EEG signal classification. Med Biol Eng Comput 56:1861–1874

    Google Scholar 

  30. Yang J, Honavar V (1998) Feature subset selection using a genetic algorithm. In: Liu H, Motoda H (eds) Feature extraction, construction and selection. The Springer International Series in Engineering and Computer Science, vol 453. Springer, Boston, MA

  31. Oh I-S, Lee J-S, Moon B-R (2004) Hybrid genetic algorithms for feature selection. IEEE Trans Pattern Anal Mach Intell 26:1424–1437

    Google Scholar 

  32. Zhang Y, Wang Y, Jin J, Wang X (2017) Sparse Bayesian learning for obtaining sparsity of EEG frequency bands based feature vectors in motor imagery classification. Int J Neural Syst 27:1650032

    Google Scholar 

  33. Yang XS (2010) A new metaheuristic bat-inspired algorithm. In: Nature inspired cooperative strategies for optimization (NICSO 2010). Springer, Berlin, pp 65–74

  34. Gilles J (2013) Empirical wavelet transform. IEEE Trans Signal Process 61:3999–4010. https://doi.org/10.1109/TSP.2013.2265222

    Article  MathSciNet  MATH  Google Scholar 

  35. Masetic Z, Subasi A (2016) Congestive heart failure detection using random forest classifier. Comput Methods Programs Biomed 130:54–64. https://doi.org/10.1016/j.cmpb.2016.03.020

    Article  Google Scholar 

  36. (1979) Physiobank Archieve Index, MIT-BIH Arrhythmia Database: http://www.physionet.org/physiobank/database/mitdb/

  37. Mark R, Moody G (1997) MIT-BIH arrhythmia database 1997. http://www.ecgmit.edu/dbinfo.html

  38. Poornachandra S (2008) Wavelet-based denoising using subband dependent threshold for ECG signals. Digit Signal Process A Rev J 18:49–55. https://doi.org/10.1016/j.dsp.2007.09.006

    Article  Google Scholar 

  39. Singh BN, Tiwari AK (2006) Optimal selection of wavelet basis function applied to ECG signal denoising. Digit Signal Process 16:275–287

    Google Scholar 

  40. Addison PS (2005) Wavelet transforms and the ECG: a review. Physiol Meas 26:R155

    Google Scholar 

  41. Kamath C (2016) Assessment of heart rate dynamic characteristics during meditation using symbolic dynamics analysis. 8:249–262. https://doi.org/10.1504/IJMEI.2016.077441

    Article  Google Scholar 

  42. Wang J, Chen J (2010) Symbolic dynamics of ventricular tachycardia and ventricular fibrillation. Phys A Stat Mech Appl 389:2096–2100. https://doi.org/10.1016/j.physa.2010.01.008

    Article  Google Scholar 

  43. Jung W-H, Lee S-G (2017) An arrhythmia classification method in utilizing the weighted KNN and the fitness rule. IRBM 38:138–148

    Google Scholar 

  44. Peterson LE (2009) K-nearest neighbor. Scholarpedia 4:1883

    Google Scholar 

  45. Osowski S, Linh TH (2001) ECG beat recognition using fuzzy hybrid neural network. IEEE Trans Biomed Eng 48:1256–1271

    Google Scholar 

  46. Soria ML, Martinez JP (2009) Analysis of multidomain features for ECG classification. Comput Cardiol 2009:561–564

    Google Scholar 

  47. Yeh Y-C, Chiou CW, Lin H-J (2012) Analyzing ECG for cardiac arrhythmia using cluster analysis. Expert Syst Appl 39:1000–1010

    Google Scholar 

  48. Acır N (2005) Classification of ECG beats by using a fast least square support vector machines with a dynamic programming feature selection algorithm. Neural Comput Appl 14:299–309

    Google Scholar 

  49. Lin L, Yeh Y, Chu T (2014) Feature selection algorithm for ECG signals and its application on heartbeat case determining. Int J Fuzzy Syst 16:483–496

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab, 144011, India

    Atul Kumar Verma, Indu Saini & Barjinder Singh Saini

Authors
  1. Atul Kumar Verma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Indu Saini
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Barjinder Singh Saini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Atul Kumar Verma.

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

Verma, A.K., Saini, I. & Saini, B.S. A new BAT optimization algorithm based feature selection method for electrocardiogram heartbeat classification using empirical wavelet transform and Fisher ratio. Int. J. Mach. Learn. & Cyber. 11, 2439–2452 (2020). https://doi.org/10.1007/s13042-020-01128-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-020-01128-0

Keywords

Search

Navigation