Paper Titles

Effects of the Window Size and Feature Extraction Approach for Arrhythmia Classification
p.1

Clustering Algorithm in Possibilistic Exponential Fuzzy C-Mean Segmenting Medical Images
p.12

Delivery of Amphotericin B to Candida albicans by Using Biomachined Lab-on-a-Chip
p.24

Dynamic Balance Analysis under Different Lower Extremities Tortuosity
p.31

Microstructure of Hydroxyapatite/Collagen Coating on AZ31 Magnesium Alloy by a Solution Treatment
p.38

Novel Nanocrystal Clay Materials with Potential Bone Cells Growth Enhancement or Inhibition Characteristics In Vitro
p.45

Characterization and Multi-Response Morphological Optimization for Preparation of Defect-Free Electrospun Nanofibers Using the Taguchi Method
p.61

Synthesis and Characterization of Bacterial Cellulose - Garcinia mangostana Extract as Anti Breast Cancer Biofilm Candidate
p.76

Effect of Nitrogen Oxide on the Gums Lamina propria Structure and Function in the Experimental Gastritis, Duodenitis and Pharmacological Correction
p.86

HomeJournal of Biomimetics, Biomaterials and...Journal of Biomimetics, Biomaterials and...Effects of the Window Size and Feature Extraction...

Effects of the Window Size and Feature Extraction Approach for Arrhythmia Classification

Article Preview

Abstract:

Arrhythmia, a common form of heart disease, can be detected from an electrocardiogram (ECG) signal. This research work presents a comparative study between five feature extraction methods applied separately on two window sizes for detecting three ECG pulse types, namely normal and two arrhythmia variations. The library support vector machine (LIBSVM) was used to classify the three classes of the ECG pulses. The ECG signals were obtained from MIT-BIH database. The ECG dataset was normalized and filtered to remove any noise and after that the signals were windowed into two window sizes (long window and short window). Five approaches were used to extract the features from the ECG signals. These approaches are scalar Autoregressive model coefficients, Haar discrete wavelet transform (DWT), Daubechies (db) DWT, Biorthogonal (bior) DWT, and principal components analysis (PCA). Each approach was applied separately on the two window sizes. The results of the classification show that scalar Autoregressive model coefficients, Haar, db, and bior are better approaches to catch the ECG features for short window than the long window. However, PCA gave the closest and highest results for the two window sizes than other approaches. That mean the PCA is the better feature extraction approach for both window sizes.

You might also be interested in these eBooks

Journal of Biomimetics, Biomaterials and Biomedical Engineering Vol. 30

Info:

Periodical:

Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 30)

Pages:

1-11

DOI:

https://doi.org/10.4028/www.scientific.net/JBBBE.30.1

Citation:

Cite this paper

Online since:

January 2017

Authors:

Khudhur A. Alfarhan*, Mohd Yusoff Mashor, Abdul Rahman Mohd Saad, Hayder A. Azeez, Mustafa M. Sabry

Keywords:

Arrhythmia, Autoregressive Model (AR), Discrete Wavelet Transform (DWT), Electrocardiogram (ECG), Libsvm, Principal Component Analysis (PCA)

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

[1] NHLBI, What Is an Arrhythmia, National Heart Lung and Blood Institute, (2011). https: /www. nhlbi. nih. gov/health/health-topics/topics/arr.

[2] D. Ge, N. Srinivasas, and S. M Krishnan, Cardiac arrhythmia classification using autoregressive modeling, BioMedical Engineering OnLine, 12 (2002) 1–12.

DOI: 10.1186/1475-925x-1-5

[3] B. Abibullaev, W. Kang, S. H. Lee, and Jinung An, Classification of Cardiac Arrhythmias using Biorthogonal Wavelets and Support Vector Machines, Int. J. Adv. Comput. Technol., 2 (2010) 24–34.

[4] A. Rabee and I. Barhumi, ECG signal classification using support vector machine based on wavelet multiresolution analysis, in 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), 2 (2012).

DOI: 10.1109/isspa.2012.6310497

[5] S. -N. Yu and Y. -H. Chen, Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network, Pattern Recognit. Lett., 28 (2007) 1142–1150.

DOI: 10.1016/j.patrec.2007.01.017

[6] K. Polat and S. Gunes, Detection of ECG Arrhythmia using a differential expert system approach based on principal component analysis and least square support vector machine, Appl. Math. Comput., 186 (2007) 898–906.

DOI: 10.1016/j.amc.2006.08.020

[7] MIT-BIH, MIT-BIH ECG database, physionet, (2016) https: /www. physionet. org/physiobank/database.

DOI: 10.7717/peerj-cs.226/table-1

[8] M. Kaur, B. Singh, and Seema, Comparisons of Different Approaches for Removal of Baseline Wander from ECG Signal, in 2nd International Conference and workshop on Emerging Trends in Technology (ICWET), (2011) 30–36.

DOI: 10.1145/1980022.1980307

[9] B. S. Raghavendra, D. Bera, A. S. Bopardikar, and R. Narayanan, Cardiac arrhythmia detection using dynamic time warping of ECG beats in e-healthcare systems, in 2011 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM , (2011).

DOI: 10.1109/wowmom.2011.5986196

[10] M. M. Tawfik, H. Selim, and T. Kamal, Human identification using time normalized QT signal and the QRS complex of the ECG, in Communication Systems Networks and Digital Signal Processing (CSNDSP), 7th International Symposium, (2010) 755–759.

DOI: 10.1109/csndsp16145.2010.5580317

[11] V. S. Chouhan and S. S. Mehta, Detection of QRS Complexes in 12-lead ECG using Adaptive Quantized Threshold, Int. J. Comput. Sci. Netw. Secur., 8 (2008) p.155–163.

[12] B. Vuksanovic, Analysis of Human Electrocardiogram for Biometric Recognition Using Analytic and AR Modeling Extracted Parameters, Int. J. Inf. Electron. Eng., 4 (2014) 25–42.

DOI: 10.7763/ijiee.2014.v4.478

[13] A. A. Sinica, Study of Feature Extraction Based on Autoregressive Modeling in ECG Automatic Diagnosis, 33 (2007).

[14] Q. U. Xiao, C. Wei, and G. D. Fei, ECG Signal Classification Based on BPNN, in Electric Information and Control Engineering (ICEICE), 2011 International Conference on, (2011) p.1362–1364.

DOI: 10.1109/iceice.2011.5777902

[15] H. Khorrami and M. Moavenian, A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification, Expert Syst. Appl., 37 (2010) p.5751–5757.

DOI: 10.1016/j.eswa.2010.02.033

[16] E. M. Tamil, N. H. Kamarudin, R. Salleh, M. Y. I. Idris, M. Noor, and A. M. Tamil, Heartbeat Electrocardiogram (ECG) signal feature extraction using Discrete Wavelet Transforms (DWT), Cspa, (2008) p.1112–1117.

[17] M. Kania, M. Fereniec, and R. Maniewski, Wavelet Denoising for Multi-lead High Resolution ECG Signals, Meas. Sci. Rev., 7 (2007) 30–33.

[18] C. Gargour, M. Gabrea, V. Ramachandran, and J. M. Lina, A short introduction to wavelets and their applications, IEEE Circuits Syst. Mag., 9 (2009) p.57–68.

DOI: 10.1109/mcas.2009.932556

[19] Wikipedia, Discrete wavelet transform, Wikipedia the free Encyclopedia, (2016). https: /en. wikipedia. org/wiki/Discrete_wavelet_transform.

[20] R. J. Martis, U. R. Acharya, K. M. Mandana, A. K. Ray, and C. Chakraborty, Application of principal component analysis to ECG signals for automated diagnosis of cardiac health, Expert Syst. Appl., 39 (2012) 11792–11800.

DOI: 10.1016/j.eswa.2012.04.072

[21] I. T. Jolliffe, Principal Component Analysis, (2002).

[22] L. I. Smith, A tutorial on Principal Components Analysis Introduction, (2002).

[23] A. Ghodsi, Dimensionality reduction a short tutorial. Waterloo, Ontario: Univ. of Waterloo, Ontario, Canada, (2006).

[24] P. Langley, E. J. Bowers, and A. Murray, Principal component analysis as a tool for analyzing beat-to-beat changes in ECG features: Application to ECG-derived respiration, IEEE Trans. Biomed. Eng., 57 (2010) 821–829.

DOI: 10.1109/tbme.2009.2018297

[25] L. She, Y. Song, S. Zhang, and Z. Xu, A precise ambulatory ECG arrhythmia intelligent analysis algorithm based on support vector machine classifiers, in 2010 3rd International Conference on Biomedical Engineering and Informatics, BMEI, 2 (2010).

DOI: 10.1109/bmei.2010.5640071

[26] S. W. Fei, Diagnostic study on arrhythmia cordis based on particle swarm optimization-based support vector machine, "Expert Syst. Appl., 37 (2010) p.6748–6752.

DOI: 10.1016/j.eswa.2010.02.126

[27] S. N. Yu and K. T. Chou, Selection of significant independent components for ECG beat classification, Expert Syst. Appl., 36 (2009) 2088–(2096).

DOI: 10.1016/j.eswa.2007.12.016

[28] C. Chang and C. Lin, LIBSVM: A Library for Support Vector Machines, ACM Trans. Intell. Syst. Technol., 2 (2013) 1–39.

DOI: 10.1145/1961189.1961199

[29] M. Zavar, S. Rahati, M. -R. Akbarzadeh-T, and H. Ghasemifard, Evolutionary model selection in a wavelet-based support vector machine for automated seizure detection, Expert Syst. Appl., 38 (2011) p.10751–10758.

DOI: 10.1016/j.eswa.2011.01.087

[30] Q. Li, C. Rajagopalan, and G. D. Clifford, A machine learning approach to multi-level ECG signal quality classification, Comput. Methods Programs Biomed., 117 (2014) 435–447.

DOI: 10.1016/j.cmpb.2014.09.002

[31] S. Chen, W. Hua, Z. Li, J. Li, and X. Gao, Heartbeat classification using projected and dynamic features of ECG signal, Biomed. Signal Process. Control, 31 (2017) 165–173.

DOI: 10.1016/j.bspc.2016.07.010