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

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.

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

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 theclassification 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 wasapplied to eliminate the ECG signals from noise. Then, the ECG signals were converted to spectrograms for thefeature extraction stage. A method was used originated on Convolutional Neural Network (CNN) to obtain theattributes 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 withDGA-ELM was achieved.

PDF

___

[1] Teodoro F.G.S., Peres S.M., Lima C.A. 2017. Feature selection for biometric recognition based on electrocardiogram signals. In 2017 International Joint Conference on Neural Networks (IJCNN), IEEE, 2911-2920.
[2] Diker A., Avci E., Gedikpinar M. 2017. Determination of R-peaks in ECG signal using Hilbert Transform and Pan-Tompkins Algorithms. In 2017 25th Signal Processing and Communications Applications Conference (SIU), IEEE, 1-4.
[3] Ojha D.K., Subashini M. 2014. Analysis of electrocardiograph (ecg) signal for the detection of abnormalities using matlab. World Academy of Science, Engineering and Technology, International Journal of Medical, Health, Pharmaceutical and Biomedical Engineering, 8 (2): 114- 117.
[4] Sadhukhan D., Mitra M. 2012. Detection of ECG characteristic features using slope thresholding and relative magnitude comparison. In 2012 Third International Conference on Emerging Applications of Information Technology, IEEE, 122-126.
[5] Kulkarni S.P. 2015. DWT and ANN Based Heart Arrhythmia Disease Diagnosis from MIT-BIH ECG Signal Data. International Journal on Recent and Innovation Trends in Computing and Communication, 3 (1): 276-279.
[6] Escalona-Morán M.A., Soriano M.C., Fischer I., Mirasso C.R. 2014. Electrocardiogram classification using reservoir computing with logistic regression. IEEE Journal of Biomedical and health Informatics, 19 (3): 892-898.
[7] Mannurmath J.C., Raveendra M. 2014. MATLAB based ECG signal classification. International Journal of Science, Engineering and Technology Research (IJSETR), 3 (7): 1946-1950.
[8] Pasolli E., Melgani F. 2015. Genetic algorithm-based method for mitigating label noise issue in ECG signal classification. Biomedical Signal Processing and Control, 19: 130-136.
[9] Rai H.M., Trivedi A., Shukla S. 2013. ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier. Measurement, 46 (9): 3238-3246.
[10] Korürek M., Doğan B. 2010. ECG beat classification using particle swarm optimization and radial basis function neural network. Expert systems with Applications, 37 (12): 7563-7569.
[11] Khorrami H., Moavenian M. 2010. A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification. Expert systems with Applications, 37 (8): 5751-5757.
[12] Karpagachelvi S., Arthanari M., Sivakumar M. 2011. Classification of Electrocardiogram signals with extreme learning machine and relevance vector machine. International Journal of Computer Science Issues (IJCSI), 8 (1): 338.
[13] Wu J.F., Bao Y.L., Chan S.C., Wu H.C., Zhang L., Wei X.G. 2016. Myocardial infarction detection and classification—A new multi-scale deep feature learning approach. In 2016 IEEE International Conference on Digital Signal Processing (DSP), IEEE, 309-313.
[14] Liu D., Jiang Y., Pei M., Liu S. 2018. Emotional image color transfer via deep learning. Pattern Recognition Letters, 110: 16-22.
[15] Cao C., Liu F., Tan H., Song D., Shu W., Li W., Xie Z. 2018. Deep learning and its applications in biomedicine. Genomics, proteomics & bioinformatics, 16 (1): 17-32.
[16] Labati R.D., Muñoz E., Piuri V., Sassi R., Scotti F. 2019. Deep-ECG: Convolutional neural networks for ECG biometric recognition. Pattern Recognition Letters, 126: 78-85.
[17] Kamilaris A., Prenafeta-Boldú F.X. 2018. Deep learning in agriculture: A survey. Computers and electronics in agriculture, 147: 70-90.
[18] Cengil E., Çınar A. 2016. A New Approach for Image Classification: Convolutional Neural Network. European Journal of Technique, 6 (2): 96-103.
[19] Doğan R.Ö., Kayikçioğlu T. 2018. R-peaks detection with convolutional neural network in electrocardiogram signal. In 2018 26th Signal Processing and Communications Applications Conference (SIU), IEEE, 1-4.
[20] Traore B.B., Kamsu-Foguem B., Tangara F. 2018. Deep convolution neural network for image recognition. Ecological informatics, 48: 257-268.
[21] Harangi B. 2018. Skin lesion classification with ensembles of deep convolutional neural networks. Journal of biomedical informatics, 86: 25-32.
[22] Dos Santos Ferreira M.V., de Carvalho Filho A.O., de Sousa A.D., Silva A.C., Gattass M. 2018. Convolutional neural network and texture descriptor-based automatic detection and diagnosis of glaucoma. Expert Systems with Applications, 110: 250-263.
[23] Huang G.B., Zhu Q.Y., Siew C.K. 2006. Extreme learning machine: theory and applications. Neurocomputing, 70 (1-3): 489-501.
[24] Huang G.B., Zhou H., Ding X., Zhang R. 2011. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42 (2): 513-529.
[25] Villarreal-Cervantes M.G., Rodríguez-Molina A., García-Mendoza C.V., Penaloza-Mejia O., Sepúlveda-Cervantes G. 2017. Multi-objective on-line optimization approach for the DC motor controller tuning using differential evolution. IEEE Access, 5: 20393-20407.
[26] Hu J., Wang C., Liu C., Ye Z. 2017. Improved K-means algorithm based on hybrid fruit fly optimization and differential evolution. In 2017 12th International Conference on Computer Science and Education (ICCSE), IEEE, 464-467.
[27] Melgani F., Bazi Y. 2008. Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE transactions on information technology in biomedicine, 12 (5): 667-677.
[28] Avci E. 2013. A new method for expert target recognition system: Genetic wavelet extreme learning machine (GAWELM). Expert Systems with Applications, 40 (10): 3984-3993.
[29] Chen X., Zhang P., Du G., Li F. 2018. Ant colony optimization based memetic algorithm to solve bi-objective multiple traveling salesmen problem for multi-robot systems. IEEE Access, 6: 21745-21757.
[30] Farahani H.F., 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 Science, Measurement & Technology, 11 (8): 1058-1070.
[31] Goldberger A.L., Amaral L.A., Glass L., Hausdorff J.M., Ivanov P.C., Mark R.G., Stanley H.E. 2000. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101 (23): e215-e220.
[32] Berkaya S.K., Uysal A.K., Gunal E.S., Ergin S., Gunal S., Gulmezoglu M.B. 2018. A survey on ECG analysis. Biomedical Signal Processing and Control, 43: 216-235.
[33] Vozda M., Peterek T., Cerny M. 2014. Novel Method for Deriving Vectorcardiographic Leads Based on Artificial Neural Networks.
[34] PhysioBank ATM. 2018. https://physionet.org/cgi-bin/atm/ATM. (Accessed: 10.07.2018).
[35] Cömert Z., Kocamaz A.F. 2015. Determination of QT interval on synthetic electrocardiogram. In 2015 23nd Signal Processing and Communications Applications Conference (SIU), IEEE, 2569- 2572.
[36] Diker A., Cömert Z., Avcı E. 2017. A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals. Bitlis Eren University Journal of Science and Technology, 7 (2): 132-139.
[37] Cömert Z., Kocamaz A.F. 2018. Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach. In Computer Science On-line Conference, Springer, Cham., 239-248.
[38] Note O. 2017. Deep Convolutional Neural Network for ECG-Based Human Identification, 7-10.
[39] Nwankpa C., Ijomah W., Gachagan A., Marshall S. 2018. Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378.
[40] Huang G.B., Zhu Q.Y., Siew C.K. 2004. Extreme learning machine: a new learning scheme of feedforward neural networks. Neural networks, 2: 985-990.
[41] Huang G.B., Chen L., Siew C.K. 2006. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Networks, 17 (4): 879- 892.
[42] Huang G.B., Zhu Q.Y., Siew C.K. 2004. Extreme learning machine: a new learning scheme of feedforward neural networks. Neural networks, 2: 985-990.
[43] Kim J., Shin H.S., Shin K., Lee M. 2009. Robust algorithm for arrhythmia classification in ECG using extreme learning machine. Biomedical engineering online, 8 (1): 31.
[44] Keskintürk T. 2006. Differential evolution algorithm. Istanbul Commerce University Journal of Science, 9: 85-99.
[45] Yang W.A., Zhou Q., Tsui K.L. 2016. Differential evolution-based feature selection and parameter optimisation for extreme learning machine in tool wear estimation. International Journal of Production Research, 54 (15): 4703-4721.
[46] Engelbrecht A.P. 2007. Computational intelligence: an introduction. John Wiley & Sons.
[47] Qin A.K., Huang V.L., Suganthan P.N. 2008. Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE transactions on Evolutionary Computation, 13 (2): 398-417.
[48] Karcı A. 2017. Differential Evolution Algorithm and Its Variants. Anatolian Science-Bilgisayar Bilimleri Dergisi, 2 (1): 10-14.
[49] Karaboğa N., Koyuncu C. 2005. A. Diferansiyel Gelişim Algoritmasi Kullanilarak Adaptif Lineer Toplayıcı Tasarımı.