ECG Signal Classification Technique Based on Deep Features Using Differential Evolution Algorithm Extreme Learning Machine (DEA-ELM)

Year 2020, , 1364 - 1376, 26.09.2020

Aykut Diker , Engin Avcı

https://doi.org/10.17798/bitlisfen.649315

Abstract

The movements of electrocardiogram
(ECG) signals are very important in the diagnosis of heart disorders. Machine
learning methods are widely used to classify ECG signals. The aim of this work
is to contribute to the classification of ECG signals using the Differential
Evolution Algorithm Extreme Learning Machine (DGA-ELM). In this paper, a public
heart records in Physionet was utilized to classify ECG signals. The
pre-processing was applied to eliminate the ECG signals from noise. Then, the
ECG signals were converted to spectrograms for the feature extraction stage. A
method was used originated on Convolutional Neural Network (CNN) to obtain the
attributes of ECG signals. The DGA-ELM algorithm was used to select the best
activation function. In this context, the best cost value 79.37% with a sigmoid activation function and 750 iteration in the
classification made with DGA-ELM was achieved.

Keywords

Differential Evolution Algorithm, Electrocardiogram

Diferansiyel Evrim Algoritması Uç Öğrenme Makinesi (DGA-UÖM) Kullanarak Derin Özelliklere Dayalı EKG İşareti Sınıflandırma Tekniği

Abstract

Elektrokardiyogram (EKG) işaretlerinin
hareketleri kalp hastalıklarının teşhisinde çok önemlidir. Makine öğrenme
yöntemleri, EKG işaretlerini sınıflandırmak için yaygın olarak
kullanılmaktadır. Bu çalışmanın amacı, Diferansiyel Evrim Algoritması Uç
Öğrenme Makinesinin (DGA-UÖM) kullanarak EKG işaretlerinin sınıflandırılmasına
katkıda bulunmaktır. Bu çalışmada, EKG iaşretlerini sınıflandırmak için
Physionet'teki açık erişimli kalp kayıtları kullanılmıştır. EKG işaretlerini
gürültüden arındımak için  ön işlem
süreci uygulanmıştır. Daha sonra, özellik çıkarımı aşaması için EKG işaretleri
spektogramlara dönüştürülmüştür. EKG işaretlerinin özelliklerini elde etmek
için Konvolüsyonel Sinir Ağına (KSA) dayanan bir yöntem kullanılmıştır. DGA-UÖM
algoritması en iyi aktivasyon fonksiyonun seçmek için kullanılmıştır. Bu
bağlamda, DGA-UÖM ile yapılan sınıflandırmada 
sigmoid aktivasyon fonksiyonu ve 750 iterasyon  ile %
79.37 en iyi maliyet değerine ulaşılmıştır.

Keywords

Elektrokardiyogram, Diferansiyel Gelişim Algoritması

References

• 1. Teodoro F. G. S., Peres S. M., and Lima C. A. M. 2017. Feature selection for biometric recognition based on electrocardiogram signals, Int. Jt. Conf. Neural Networks, no. mV, pp. 2911–2920.2. Diker A., Avcı E., and Gedikpınar M. 2017. Determination of R-peaks in ECG Signal Using Hilbert Transform and Pan-Tompkins Algorithms, 25th Signal Process. Commun. Appl. Conf. (SIU), 2017 3. Ojha D. K. and Subashini M. 2014. Analysis of Electrocardiograph (ECG ) Signal for the Detection of Abnormalities Using MATLAB, Int. J. Medical, Heal. Biomed. Pharm. Eng., vol. 8, no. 2, pp. 114–117.4. Sadhukhan D. and Mitra M. 2012. Detection of ECG characteristic features using slope thresholding and relative magnitude comparison, in 3rd International Conference on Emerging Applications of Information Technology, EAIT, pp. 122–126.5. Kulkarni S. P. 2015. DWT and ANN Based Heart Arrhythmia Disease Diagnosis from MIT-BIH ECG Signal Data, Int. J. Recent Innov. Trends Comput. Commun., no. January, pp. 276–279.6. Escalona-Morán M. A., Soriano M. C., Fischer I., and Mirasso C. R. 2015. Electrocardiogram classification using reservoir computing with logistic regression, IEEE J. Biomed. Heal. Informatics, vol. 19, no. 3, pp. 892–898.7. Mannurmath J. C. and Raveendra M. 2014. MATLAB Based ECG Signal Classification, Int. J. Sci. Eng. Technol. Res., vol. 3, no. 7, pp. 1946–1951.8. Pasolli E. and Melgani F. 2015. Genetic algorithm-based method for mitigating label noise issue in ECG signal classification, Biomed. Signal Process. Control, vol. 19, pp. 130–136.9. Rai H. M., Trivedi A., and Shukla S. 2013. ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier, Measurement, vol. 46, no. 9, pp. 3238–3246.10. Koruürek M. and Doğan B. 2010. ECG beat classification using particle swarm optimization and radial basis function neural network, Expert Syst. Appl., vol. 37, no. 12, pp. 7563–7569.11. Khorrami H. and Moavenian M. 2010. A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification, Expert Syst. Appl., vol. 37, no. 8, pp. 5751–5757.12. Karpagachelvi S. 2011. Classification of Electrocardiogram Signals With Extreme Learning Machine and Relevance Vector Machine,” J. Comput. Sci., vol. 8, no. 1.13. Wu J. F., Bao Y. L., Chan S. C., Wu H. C., Zhang L., and Wei X. G.2017. Myocardial infarction detection and classification-A new multi-scale deep feature learning approach, Int. Conf. Digit. Signal Process. DSP, pp. 309–313.14. Liu D., Jiang Y., Pei M., and Liu S. 2018. Emotional image color transfer via deep learning, Pattern Recognit. Lett., vol. 110, pp. 16–22.15. Cao C., Liu F., Tan H., Song D., Shu W., Li W., Zhou Y., Bo X., and Xie Z. 2018. Deep Learning and Its Applications in Biomedicine, Genomics, Proteomics Bioinforma., vol. 16, no. 1, pp. 17–32.16. Labati R. Donida, Muñoz E., Piuri V., Sassi R., and Scotti F. 2018. Deep-ECG: Convolutional Neural Networks for ECG biometric recognition, Pattern Recognit. Lett., vol. 0, pp. 1–8.17. Kamilaris A. and Prenafeta-Boldú F. X. 2018. Deep learning in agriculture: A survey, Comput. Electron. Agric., vol. 147, no. July 2017, pp. 70–90.18. Cengil E. and Çınar A. 2016. A New Approach for Image Classification: Convolutional Neural Network, Eur. J. Tech. EJT, vol. 6, no. 2.19. Dogan R. O. and Kayikcioglu T. 2018. R-peaks detection with convolutional neural network in electrocardiogram signal, in 2018 26th Signal Processing and Communications Applications Conference (SIU), no. 2, pp. 1–4.20. Traore B. B., Kamsu-Foguem B., and Tangara F. 2018. Deep convolution neural network for image recognition, Ecol. Inform., vol. 48, no. September, pp. 257–268.21. Harangi B. 2018. Skin lesion classification with ensembles of deep convolutional neural networks, J. Biomed. Inform., vol. 86, no. January, pp. 25–32.22. Vinícius dos Santos Ferreira M., Oseas de Carvalho Filho, A. Dalília de Sousa A., Corrêa Silva A., and Gattass, M. 2018.Convolutional neural network and texture descriptor-based automatic detection and diagnosis of glaucoma, Expert Syst. Appl., vol. 110, pp. 250–263.23. Huang G.-B., Zhu Q.-Y., and Siew C.-K. 2006. Extreme learning machine: Theory and applications, Neurocomputing, vol. 70, no. 1, pp. 489–501.24. Huang G.-B., Zhou H., Ding X., and Zhang R. 2012. Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man. Cybern. B. Cybern., vol. 42, no. 2, pp. 513–29.25. Tavares L. D., Saldanha R. R., and Vieira D. a. G. 2015. Extreme learning machine with parallel layer perceptrons, Neurocomputing, vol. 166, pp. 164–171.26. Avci E. and Coteli R. 2012. A new automatic target recognition system based on wavelet extreme learning machine, Expert Syst. Appl., vol. 39, no. 16, pp. 12340–12348.27. Singh R. and Balasundaram S. 2007. Application of Extreme Learning Machine Method for Time Series Analysis, Int. J. Intell. Technol., vol. 2, no. 4, pp. 256–262.28. Villarreal-cervantes M. G., Rodr A., and Garc C.2017. Multi-objective On-line Optimization Approach for the DC Motor Controller Tuning Using Differential Evolution, vol. XX, no. X, pp. 1–15.29. Hu,J. Wang C., Liu C., and Ye Z.2017. Fly Optimization and Differential Evolution, no. Iccse, pp. 464–467.30. Melgani F. and Bazi Y.2008. Classification of electrocardiogram signals with support vector machines and particle swarm optimization, IEEE Trans. Inf. Technol. Biomed., vol. 12, no. 5, pp. 667–677.31. Avci E.2013. A new method for expert target recognition system: Genetic wavelet extreme learning machine (GAWELM), Expert Syst. Appl.32. Chen X., Zhang P., Du G., and Li F.2018. Ant Colony Optimization Based Memetic Algorithm to Solve Bi-Objective Multiple Traveling Salesmen Problem for Multi-Robot Systems, IEEE Access, vol. 6, pp. 21745–21757.33. Farahani H. F. and Rashidi F.2017. Optimal allocation of plug-in electric vehicle capacity to produce active, reactive and distorted powers using differential evolution based artificial bee colony algorithm, IET Sci. Meas. Technol., vol. 11, no. 8, pp. 1058–1070.34. Goldberger A. L., Amaral L. A. N., Glass L., Hausdorff J. M., Ivanov P. C., Mark R. G., Mietus J. E., Moody G. B., Peng C., and Stanley H. E. 2000. PhysioBank, PhysioToolkit, and PhysioNet Components of a New Research Resource for Complex Physiologic Signals.35. Berkaya S. Kaplan, Uysal A. K., Sora Gunal E., Ergin S., Gunal S., and Gulmezoglu M. B. 2018. A Survey on ECG Analysis, Biomed. Signal Process. Control, vol. 43, pp. 216–235.36. Vozda M. C. M., Peterek T. 2014. Novel Method for Deriving Vectorcardiographic Leads Based on Artificial Neural Networks, FEECS , Department of Cybernetics and Biomedical Engineering , VSB – Technical University of Ostrava , Ostrava – Poruba , Czech Rep,” pp. 61–64.37. “PhysioBank ATM. 2018. Available: https://physionet.org/cgi-bin/atm/ATM. (Accessed: 10-Jul-2018).38. Cömert Z. and Fatih Kocamaz A. 2015. Determination of QT interval on synthetic electrocardiogram, in Signal Processing and Communications Applications Conference (SIU), 23th, 2015, pp. 1–4.39. Diker A., Cömert Z., and Avcı E. 2017. A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals, Bitlis Eren Univ. J. Sci. Technol., vol. 7, no. 2, pp. 132–139.40. Cömert Z. 2018. Fetal Hypoxia Detection Based on Deep Convolutional Neural Network with Transfer Learning Approach, in Cybernetics and Algorithms in Intelligent Systems, vol. 765, pp. 239–248.41. Note O.2017. Deep Convolutional Neural Network for ECG-Based Human Identification, pp. 7–10.42. Nwankpa C. E., Ijomah W., Gachagan A., and Marshall S. 2018. Activation Functions : Comparison of Trends in Practice and Research for Deep Learning, arXiv, pp. 1–20.43. Huang G., Zhu Q., and Siew C. 2004. Extreme learning machine: a new learning scheme of feedforward neural networks, Neural Networks, vol. 2, pp. 985–990 vol.2.44. Huang G., Chen L., and Siew C. K. 2006. Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Trans. Neural Networks, vol. 17, no. 4, pp. 879–892.45. Huang G., Zhu Q., and Siew C. 2004. Extreme Learning Machine : A New Learning Scheme of Feedforward Neural Networks, IEEE Int. Jt. Conf. Neural Networks, vol. 2, pp. 985–990.46. Kim J., Shin H., Shin K., and Lee M. 2009. Robust algorithm for arrhythmia classification in ECG using extreme learning machine, Biomed. Eng. Online, vol. 8, no. 1, p. 31.47. Keskintürk T. 2006. Differential Evolution Algorithm, İstanbul Ticaret Üniversitesi Fen Bilim. Derg., vol. 5, no. 9, pp. 85–99.48. Z Q.. & Wen-An Yang K.-L. T. 2016. Differential evolution-based feature selection and parameter optimisation for extreme learning machine in tool wear estimation, Int. J. Prod. Res., vol. 54, no. 15, pp. 4703–4721.49. Engelbrecht A. 2007. An Introduction Differential Evolution, Comput. Intell.50. Qin A. K., V. Huang L., and Suganthan P. N. 2009. Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization, IEEE Trans. Evol. Comput., vol. 13, no. 2, pp. 398–417.51. Karci A. 2017. Differential Evolution Algorithm and Its Variants, Anatol. J. Comput. Sci., vol. 2, no. 1, pp. 10–14.52. Karaboğa N. and Koyuncu C. A. 2005. Diferansiyel Gelişim Algoritması Kullanılarak Adaptif Lineer Toplayıcı Tasarımı, in EMO, III. Otomasyon Sempozyumu,Denizli, pp. 216–220.