Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Feature Selection for ECG Beat Classification using Genetic Algorithms

Genetik Algoritmalar Kullanarak EKG Vuru Sınıflandırması için Öznitelik Seçimi

How to cite: Sarvan , Özkurt N, Karabulut K. Feature selection for ecg beat classification using genetic algorithms. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2018; 1(2): 149-156. DOI: 10.54856/jiswa.201812045

Full Text: PDF, in Turkish.

Total number of downloads: 733

Title: Feature Selection for ECG Beat Classification using Genetic Algorithms

Abstract: In this study, genetic algorithm method was used to select the most suitable set of features for classification of arrhythmia types of heart beats. Normal, right branch block, left branch block and pace rhythm samples of electrocardiography (ECG) signals which obtained from the MIT-BIH cardiac arrhythmia database were used in the classification. Mean, standard deviation, energy and entropy of discrete wavelet transform (DWT) coefficients were proposed as the features for the classification. By using the proposed DWT method, 16 features which have high classification accuracy were obtained among the 208 feature sets constructed from 13 different wavelet types by applying the genetic algorithm method. It was observed that the features that increase accuracy can be detected by the genetic algorithm and the feature set obtained from the coefficients of the different types of wavelets selected at different levels show higher performance than the coefficients obtained from the standard individual wavelet in the ECG arrhythmia classification.

Keywords: ECG heart beat classification; arrythmia; discrete wavelet transform; wavelet features; feature selection; artificial neural networks; genetic algorithm


Başlık: Genetik Algoritmalar Kullanarak EKG Vuru Sınıflandırması için Öznitelik Seçimi

Özet: Bu çalışmada, kalp vurularının aritmi tipine göre sınıflandırılmasında en uygun öznitelik setinin seçilmesi için genetik algoritma yöntemi kullanılmıştır. Sınıflandırmada MIT-BIH kalp aritmi veri tabanından elde edilen elektrokardiyografi (EKG) sinyallerinin normal, sağ dal bloku, sol dal bloku ve pace ritmi örnekleri kullanılmıştır. Yaygın kullanımı olan kesikli dalgacık dönüşümü (KDD) katsayılarının ortalaması, standart sapması, enerjisi ve entropisi sınıflandırmada kullanılabilecek öznitelik ana kümesi olarak önerilmiştir. Önerilen KDD yöntemi ile 13 farklı dalgacık tipi için elde edilen 208 adetlik öznitelik seti içerisinden yüksek sınıflandırma doğruluğu sağlayan 16 adetlik öznitelik seti genetik algoritma yöntemi uygulanarak elde edilmiştir. Genetik algoritma yöntemi ile sınıflandırma doğruluğunu yükselten özniteliklerin tespit edilebildiği ve farklı tip dalgacıkların farklı seviyelerde seçilen katsayılarından elde edilen öznitelik setinin standart olan tek tip dalgacıktan elde edilen katsayılara göre EKG aritmi sınıflandırmasında daha yüksek başarım gösterdiği gözlemlenmiştir.

Anahtar kelimeler: EKG vuru sınıflandırması; aritmi; kesikli dalgacık dönüşümü; dalgacık öznitelikleri; öznitelik seçimi; yapay sinir ağları; genetik algoritmalar


Bibliography:
  • Chazal P, ODwyer M, Reilly RB. Automatic classification of heart beats using ECG morphology and heart beat interval features. IEEE Transactions on Biomedical Engineering 2004; 51(7): 1196-1206.
  • Osowski S, Linh TH. ECG beat recognition using fuzzy hybrid neural network. IEEE Transactions on Biomedical Engineering 2001; 48(11): 1265-1271.
  • Mazomenos EB, Chen T, Acharyya A, Bhattacharya A, Rosengarten J, Maharatna K. A time domain morphology and gradient based algorithm for ECG feature extraction. In 2012 IEEE International Conference on Industrial Technology (ICIT), March 19-21, 2012, Athens, Greece, pp. 117–122.
  • Ince T, Kiranyaz S, Gabbouj M. A generic and robust system for automated patient-specific classification of ECG signals. IEEE Transactions on Biomedical Engineering 2009; 56(5): 1415-1426.
  • Mironovova M, Bila J. Fast fourier transform for feature extraction and neural network for classification of electrocardiogram signals. In 2015 Fourth International Conference on Future Generation Communication Technology (FGCT), July 29-31, 2015, Luton, UK, pp. 1-6.
  • Uslu E, Bilgin G. Arrhythmia classification by local fractional Fourier transform. In 21st Signal Processing and Communications Applications Conference (SIU), April 24-26, 2013, Haspolat, Turkey, pp. 1-4.
  • Uslu E, Bilgin G. Exploiting locality based Fourier transform for ECG signal diagnosis. In 2012 International Conference on Applied Electronics (AE), September 5-7, 2012, Pilsen, Czech Republic, pp. 323-326.
  • Cohen L. The wavelet transform and time-frequency analysis. Book Chapter in Wavelets and Signal Processing (editor: Debnath L), Springer Science & Business Media, 2012.
  • Castro B, Kogan D, Geva AB. ECG feature extraction using optimal mother wavelet. In 21st IEEE Convention of the Electrical and Electronic Engineers in Israel. Proceedings (Cat. No.00EX377), April 11-12, 2000, Tel-Aviv, Israel, pp. 346-350.
  • Gao RX, Yan R. Wavelets: Theory and Applications for Manufacturing. Springer Science & Business Media, 2010.
  • Shufni SA, Mashor MY. ECG signals classification based on discrete wavelet transform, time domain and frequency domain features. In 2015 2nd International Conference on Biomedical Engineering (ICoBE), March 30-31, 2015, Penang, Malaysia, pp. 1-6.
  • Vaneghi FM, Oladazimi M, Shiman F, Kordi A, Safari MJ, Ibrahim F. A comparative approach to ECG feature extraction methods. In 2012 Third International Conference on Intelligent Systems Modelling and Simulation, February 8-10, 2012, Kota Kinabalu, Malaysia, pp. 252-256.
  • Yang J, Honavar V. Feature subset selection using a genetic algorithm. IEEE Intelligent Systems and Their Applications 1998; 13(2): 44-49.
  • Tian D. A multi-objective genetic local search algorithm for optimal feature subset selection. In 2016 International Conference on Computational Science and Computational Intelligence (CSCI), December 15-17, 2016, Las Vegas, NV, USA, pp. 1089-1094.
  • Kim HD, Park CH, Yang HC, Sim K. Genetic algorithm based feature selection method development for pattern recognition. In International Joint Conference SICE-ICASE, October 18-21, 2006, Busan, South Korea, pp. 1020-1025.
  • Oreski S, Oreski G. Genetic algorithm-based heuristic for feature selection in credit risk assessment. Expert Systems with Applications 2014; 41(4): 2052-2064.
  • Huang CL, Wang CJ. A GA-based feature selection and parameters optimization for support vector machines. Expert Systems with Applications 2006; 31(2): 231-240.
  • Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine 2001; 20(3): 45-50.
  • Moody GB, Mark RG, Goldberger AL. PhysioNet: A web-based resource for the study of physiologic signals. IEEE Engineering in Medicine and Biology Magazine 2001; 20(3): 70-75.
  • Physionet. MIT-BIH arrhythmia database. Retrieved from http://www.physionet.org/
  • Addison PS. The Illustrated Wavelet Transform Handbook: Introductory Theory and Applications in Science, Engineering, Medicine and Finance. CRC Press, 2002.
  • Talbi EG. Metaheuristics: From Design to Implementation. John Wiley & Sons, 2009.
  • Sapna S, Tamilarasi A, Kumar MP. Backpropagation learning algorithm based on Levenberg Marquardt algorithm. Computer Science & Information Technology 2012; 2: 393-398.