A New Recongnition System Based on Gabor Wavelet Transform for Shockable Electrocardiograms

Main Article Content

Takayuki Okai
Shonosuke Akimoto
Hidetoshi Oya
Kazushi Nakano
Hiroshi Miyauchi
Yoshikatsu Hoshi

Abstract

This paper presents a new recognition system for shockable arrhythmias for patients suffering from sudden cardiac arrest. In order to develop the recognition system, lots of electrocardiogram (ECGs) have been analyzed by using gabor wavelet transform (GWT). Although, there is a huge number of spectrum feature parameters, recognition performance for all combinations for spectrum feature parameters are evaluated, and on the basis of the evaluation results, useful and effective spectrum features for ECGs are extracted. As a result, the proposed recognition system based on the selected effective spectrum feature parameters can achieved good performance comparing with the existing results.

Keywords:
Recognition system, shockable ECGs, effective spectrum feature parameters, improvement of recognition performance, wavelet transform

Article Details

How to Cite
Okai, T., Akimoto, S., Oya, H., Nakano, K., Miyauchi, H., & Hoshi, Y. (2020). A New Recongnition System Based on Gabor Wavelet Transform for Shockable Electrocardiograms. Journal of Applied Life Sciences International, 23(12), 40-51. https://doi.org/10.9734/jalsi/2020/v23i1230203
Section
Original Research Article

References

American Heart Association (AHA). Available:https://www.heart.org/en/healthtopics/cardiac-arrest/about-cardiac-arrest (Accessed on 15 August 2020)

Ibrahim WH. Recent advances and controversies in adult cardiopulmonary resuscitation. Postgrad. Med. J. Postgraduate Medical Journal. 2007;83(984):649-654.

Kuo S, Dillman R. Computer detection of ventricular fibrillation. Proc. of Computers in Cardiology. IEEE Comupter Society. 1978;347-349.

Amann A, Tratnig R, Unterkofle K. A new ventricular fibrillation detection algorithm for automated external defibrillators. Proc. of Computers in Cardiology, IEEE Comupter Society. 2005;559-562.

Dicarlo LA, Thorone RD, Jenkins JM. A time-domain analysis of intracardiac electrograms for arrhythmias detection. PACE. 1991;14:329-336. [6] Sawada S, Oyama T, Mizushina S, Kimura T, Harada Y, Sugiura T. A preliminary study of automatic discrimination of cardiac arrhythmia (in Japanese). Technical Report of IEICE, MBE. 1995;95-121.

Ming Y, Guang Z, Taihu W, Biao G, Liangzhe L, Chunchen W, Dan W, Feng C. Detection of shockable rhythm using multi-parameter fusion identification and BP neural network. Proc. of the 2nd IEEE Int. Conf. on Computer and Communications. 2016;798- 802.

Oya H, Hagino K, Yamaguchi Y, Miyauchi H, Okai T, Kirioka S. An extraction system based on analyzing the electrocardiogram during CPR. Proc. of the 35th IASTED International Conference on Biomedical Engineering (BioMed2012), Innsbruck, AUSTRIA. 2012;98-102.

Ohnishi Y, Oya H, Tanaka K, Nishida Y, Ogino Y, Nakano K, Yamaguchi Y, Yamauchi H, Okai T. An wavelet transform-based discrimination algorithm for electrocardiogram. Proc. of AsiaPacific Signal and Information Processing Association Annual Summit and Conference 2014 (APSIPA ASC 2014), Siem Reap, CAMBODIA, USB (ID:1107); 2014.

Okai T, Hirata S, Oya H, Hoshi Y, Nakano K, Yamaguchi Y, Igarashi T, Miyauchi H. A new recognition algorithm for shockable arrhythmias and its performance analysis. Proc. of the 44th Annual Conf. of the IEEE Industrial Electronics Society (IECON2018) Washington DC, USA. 2018;2671-2676.

Okai T, Oya H, Hirata S, Hoshi Y, Nakano K, Yamaguchi Y, Igarashi T, Miyauchi H. Extraction of Effective Feature Parameters for Recognition of Shockable Arrhythmias. Proc. of the IEE International Workshop on Sensing, Actuation, Motion Control and Optimization 2019 (SAMCON2019), Chiba, Japan. 2019;1-6.

Okai T, Hirata S, Oya H, Hoshi Y, Nakano K, Yamaguchi Y, Igarashi T, Miyauchi H. Detailed performance analysis of recognition algorithm based on spectrum feature parameters for electrocardiogram. Proc of the 13th Int. Conf. on Signal Processing and Communication Systems (ICSPCS2019) Gold Coast, Australia. 2019;327-332.

Larsen MP, Eisenberg MS, Cummins RO, Hallstrom AP. Predicting survival from outof-hospital cardiac arrest: A graphic model. Ann. Emerg. Med. 1993;22(11):1652-1658.

Massachusetts Institute of Technology (MIT). MIT-BIH Arrhythmia Database. Available:http://physionet.org/physiobank/- database/mitdb (Accessed on 15 August 2020)

Massachusetts Institute of Technology (MIT). MIT-BIH Arrhythmia Database. Available:http://physionet.org/physiobank/- database/mitdb (Accessed on 15 August 2020)

Massachusetts Institute of Technology (MIT). MIT-BIH Arrhythmia Database. Available:http://physionet.org/physiobank/- database/mitdb (Accessed on 15 August 2020)

Bengio Y, Grandvalet Y. Unbiased estimator of the variance of ∥-fold cross-validation. J. of Machine Learning Research. 2004;5:1089-1105.

Hirata S, Okai T, Oya H, Hoshi Y. A neural network-based discrimination system for electrocardiogram (in Japanese). Proc. of the 62nd Annual Conf. of the Institute of Systems (ISCIE 2018) kyoto, Japan; 2018