Open Access Open Access  Restricted Access Subscription or Fee Access

Semi-Supervised Kohonen Map for Cardiac Anomalies Detection


(*) Corresponding author


Authors' affiliations


DOI: https://doi.org/10.15866/iremos.v12i3.16953

Abstract


Early detection of cardiac arrhythmia is crucial to increase the patient’s survival chance. In this paper, a semi supervised self-organizing map (S3OM) classified as a combination with supervised and unsupervised machine learning is used to classify the electrocardiogram (ECG) signal. This combination can produce a considerable improvement in learning accuracy for the three types of experienced neural approaches Temporal SOM, LVQ and semi-supervised SOM, compared to the regular SOM map. Interesting results attributed mainly to the competitive properties with global consistency of the semi-supervised SOM have been found out. The proposed method is able to classify the ECG data with high accuracy (98.87%) and it exceeds the results of related works, proving its effectiveness in ECG arrhythmias detection.
Copyright © 2019 Praise Worthy Prize - All rights reserved.

Keywords


Electrocardiogram (ECG); MIT-BIH Database; Semi Supervised Learning; Self Organizing Map (SOM); Ventricular Pathology (PVC)

Full Text:

PDF


References


Impact of Technology in Healthcare Industry, 28 Janv. 2017, http://learntechx.com/blog/impact-of-technology-in-healthcare-industry#

T. Kohonen, The self-organizing map, Proceedings IEEE, (Page: 1464-1480 Year of Publication: 1990).

MIT BIH Arrhythmia database directory, Third edition, Harvard MIT Division of Health Sciences and technology, Biomed. Eng. Center, 1992.

A. Badnjevic, IFMBE Proceedings, Proceedings of the International Conference on Medical and Biological Engineering, (Page: 802 Year of Publication: 2017 ISBN: 978-981-10-4166-2).

J. Park, M. Kang, J. Gao, Y. Kim, K. Kang, Cascade Classification with Adaptive Feature Extraction for Arrhythmia Detection, Journal of Medical Systems (Springer), 41 (1), pp.1-12, 2017.
https://doi.org/10.1007/s10916-016-0660-9

R. Chang, H. Chen, C. Lin, K. Lin, Design of a Low-Complexity Real-Time Arrhythmia Detection System, Journal of Signal Processing System (Springer), pp.1-12, 2017.
https://doi.org/10.1007/s11265-017-1221-2

G. Smaoui, A. Young, M. Abid, Single Scale CWT Algorithm for ECG Beat Detection for a Portable Monitoring System, Journal of Medical and Biological Engineering (Springer), 37(1), pp.132-139, 2017.
https://doi.org/10.1007/s40846-016-0212-2

C. K. Jha, M. H. Kolekar, ECG data compression algorithm for tele-monitoring of cardiac patients, International Journal of Telemedicine and Clinical Practices, 2(1),pp. 31-41, 2017.
https://doi.org/10.1504/ijtmcp.2017.10003014

M. L. Talbi, Analysis and treatment of the electrocardiographic signal (ECG), Ph.D. dissertation, Dept. Elect. Eng., Mentouri Univ., Constantine, Algerie, 2011.

https://fr.wikipedia.org/wiki/Rythme_sinusal#/media/Fichier:SinusRhythmLabels.svg

Z. Xiaohong, T. Huiling, D. Yanjun, L. Mengjiao, Z. Zhidong, Electrocardiogram Human Identification System Based on Block Sparse Bayesian Decomposition, Journal of Medical Imaging and Health Informatics, 7(1), pp. 264-272, 2017.
https://doi.org/10.1166/jmihi.2017.2017

P. Huang, Study on a Low Complexity ECG Compression Scheme with Multiple Sensors, Cornell university company, Computer Science, 2017.
https://arxiv.org/abs/1704.01612

A. A. Zaidi, M. M. Ahmed, A. S. M. Bakibillah, Feature extraction and characterization of cardiovascular arrhythmia and normal sinus rhythm from ECG signals using LabVIEW, IEEE International Conference on Imaging, Vision & Pattern Recognition (ICIVPR), pp. 1-6, 2017.
https://doi.org/10.1109/icivpr.2017.7890871

Lukose, B., Vijendran, A., Image Noise Removal Using Rao-Blackwellized Particle Filter with Maximum Likelihood Estimation, (2014) International Review on Computers and Software (IRECOS), 9 (5), pp. 784-792.

El Hanine, M., Abdelmounim, E., Haddadi, R., Belaguid, A., An Alternative Application of the Wavelet Packet Transform to Remove Noises in the ECG Signals, (2015) International Review on Computers and Software (IRECOS), 10 (8), pp. 838-844.
https://doi.org/10.15866/irecos.v10i8.6843

O.El B'charri, R. Latif, K. Elmansouri, A. Benaou, W. Jenkal, ECG signal performance de-noising assessment based on threshold tuning of dual-tree wavelet transform, BioMedical Engineering OnLine, 16 (1), 2017.
https://doi.org/10.1186/s12938-017-0315-1

M. Rakshit, S. Das, An efficient wavelet-based automated R-peaks detection method using Hilbert transform, Biocybernetics and BiomedicalEngineering,(Elsevier),2017.
https://doi.org/10.1016/j.bbe.2017.02.002

Jenkal, W., Latif, R., Toumanari, A., Dliou, A., El B’charri, O., Bsiss, M., QRS Detection Using an Efficient Algorithm Based on Wavelet Coefficients, (2016) International Review on Computers and Software (IRECOS), 11 (6), pp. 479-488.
https://doi.org/10.15866/irecos.v11i6.9232

Mantravadi, N., Prasad, S., Rahman, M., Efficient Cardiac Signal Enhancement Techniques Based on Variable Step Size and Data Normalized Hybrid Signed Adaptive Algorithms, (2016) International Review on Computers and Software (IRECOS), 11 (10), pp. 872-883.
https://doi.org/10.15866/irecos.v11i10.10251

Ramli, S., Ahmad, R., Abdollah, M., Hybrid Authentication Protocol Framework Using Wireless Body Area Network (WBAN) for Multiple Concurrent Health Monitoring, (2014) International Review on Computers and Software (IRECOS), 9 (12), pp. 1971-1976.
https://doi.org/10.15866/irecos.v9i12.4642

Ramli, S., Ahmad, R., Abdollah, M., A Secure Data Authentication in Wireless Body Area Network for Health Monitoring Using Electrocardiogram-Based Key Agreement, (2016) International Review on Computers and Software (IRECOS), 11 (7), pp. 622-630.
https://doi.org/10.15866/irecos.v11i7.9591

Najeh, M., Bouzid, A., Ellouze, N., QRS Detection with Multiscale Product Using Wavelets with One and Two Vanishing Moments, (2016) International Review on Computers and Software (IRECOS), 11 (4), pp. 284-289.
https://doi.org/10.15866/irecos.v11i4.8411

J. Kim, H. Shin, Simple and robust real-time QRS detection algorithm based on spatiotemporal characteristic of the QRS complex, Journal PLOS One, 11 (3), 2016.
https://doi.org/10.1371/journal.pone.0150144

M. Elgendi, A. Mohamed, R. Ward, Efficient compression technique based on temporal modelling of ECG signal using principle component analysis.

S.Hamdi, A.Ben Abdallah, M. H. Bedoui, Real time QRS complex detection using DFA and regular grammar, BioMedical Engineering on Line, 2017.
https://doi.org/10.1186/s12938-017-0322-2

S. Nikan, F. G. Sridhar, M. Bauer, Pattern Recognition Application in ECG Arrhythmia Classification, Proceedings of the International Conference on Medical and Biological Engineering, (Pages: 48–56 Year of Publication: 2017 ISBN: 978-989-758-213-4).
https://doi.org/10.5220/0006116300480056

L. Mesin, Heartbeat monitoring from adaptively down-sampled electrocardiogram, Computers in biology and medicine, 84, pp. 217-225, 2017.
https://doi.org/10.1016/j.compbiomed.2017.03.023

Sumathi, R., Kirubakaran, E., Krishnamoorthi, R., Multi Class Multi Label Based Fuzzy Associative Classifier with Genetic Rule Selection for Coronary Heart Disease Risk Level Prediction, (2014) International Review on Computers and Software (IRECOS), 9 (3), pp. 533-540.

S. Chen, W. Hua, Z. Li, J Li, X. Gao, Heartbeat classification using projected and dynamic features of ECG signal , Biomedical Signal Processing and Control (Elsevier) , 31, pp. 165-173, 2017.
https://doi.org/10.1016/j.bspc.2016.07.010

C. L. Herry, M. Frasch, A. J. Seely, H. Wu, Heart beat classification from single-lead ECG using the synchrosqueezing transform, Physiological Measurement, 38 (2), 2017.
https://doi.org/10.1088/1361-6579/aa5070

Hendel, M., Benyettou, A., Hendel, F., Heartbeats Arrhythmia Classification Using Quadratic Loss Multi-Class Support Vector Machines, (2016) International Review on Computers and Software (IRECOS), 11 (1), pp. 49-55.
https://doi.org/10.15866/irecos.v11i1.8280

T. Li, J. Ma, X. Pan, Y. Zhai, Classification of Arrhythmia using Multi-Class Support Vector Machine, Proceedings of the International MultiConference of Engineers and Computer Scientists (IMECS) (Pages: 710–713 Year of Publication:2017 ISBN: 978-988-14047-7-0).

Gurram, D., Narasinga Rao, M., A Decision Support System for Predicting Heart Disease Using Multilayer Perceptron and Factor Analysis, (2015) International Review on Computers and Software (IRECOS), 10 (8), pp. 799-804.
https://doi.org/10.15866/irecos.v10i8.6177

Elsayyad, A., Nassef, A., Baareh, A., Cardiac Arrhythmia Classification Using Boosted Decision Trees, (2015) International Review on Computers and Software (IRECOS), 10 (3), pp. 280-289.
https://doi.org/10.15866/irecos.v10i3.5359

H. Li, D. Yuan, X. Ma, D. Cui, L. Cao. Genetic algorithm for the optimization of features and neural networks in ECG signals classification, Scientific Reports.
https://doi.org/10.1038/srep41011

S.L. Chen , J. F. Villaverde, H.Y. Lee, W.Y. Chung, T.L. Lin, C. H. Tseng, K.A. Lo, A Power-Efficient Mixed-Signal Smart ADC Design with Adaptive Resolution and Variable Sampling Rate for Low-Power Applications, IEEE Sensors Journal, PP (99), 2017.
https://doi.org/10.1109/jsen.2017.2680472

V. K. Sudarshan, U. R. Acharya, S. L. Oh, M. Adam, J. H. Tan, C. K. Chua, K. P. Chua, R. S. Tan, Automated diagnosis of congestive heart failure using dual tree complex wavelet transform and statistical features extracted from 2 s of ECG signals, Computers in Biology and Medicine, 83, pp. 48-58, 2017
https://doi.org/10.1016/j.compbiomed.2017.01.019

B. Subramanian, A. Ramasamy, Investigation on the Compression of Electrocardiogram Signals Using Dual Tree Complex Wavelet, Journal IETE Journal of Research, pp.1-11, 2017.
https://doi.org/10.1080/03772063.2016.1275988

X. Dong, C. Wang, W. SI, ECG beat classification via deterministic learning, Neurocomputing (Elsevier), 240, pp. 1-12, 2017
https://doi.org/10.1016/j.neucom.2017.02.056

K. Bhanot, R.K. Nigam, Deterministic risk analysis smart health model for heart ailments using neural networks, International Journal of Telemedicine and Clinical Practices, 2 (1), 2017.
https://doi.org/10.1504/ijtmcp.2017.10003016

C. Zhang, G. Wang, J. Zhao, Patient-specific ECG classification based on recurrent neural networks and clustering technique, Biomedical Engineering (BioMed), pp. 63-67, 2017.
https://doi.org/10.2316/p.2017.852-029

J. Amezcua, P. Melin, Classification of Arrhythmias Using Modular Architecture of LVQ Neural Network and Type 2 Fuzzy Logic, Part of the Studies in Computational Intelligence, 667 pp. 187-194, 2016.
https://doi.org/10.1007/978-3-319-47054-2_12

P. Dhar, S. Dutta , P. Das, ECG beat classification using crosswavelet and LVQ, The 5th International Conference on recent trends in engineering science and management electronic science, pp. 810-818, 2016.

J. Pan, W.J. Tompkins, A real time QRS detection algorithm, IEEE Transactions on Biomedical Engineering, 32 (3), pp. 230-236, 1985.
https://doi.org/10.1109/tbme.1985.325532

B. Triqui, O. Behadada, A. Benyettou, The detection of cardiac arrhythmias by hidden Markov chains, (Editions Universitaires Européennes, 2012), ISBN 978-3-8417-9540-3.

J. A. Gutiérrez-Gnecchia, R. Morfin-Magañaa, D. Lorias-Espinozab, A. Tellez-Anguianoa,E. Reyes-Archundiaa, A. Méndez-Patiño, DSP-based arrhythmialmlk classification using wavelet transform and probabilistic neural network, Biomedical Signal Processing and Control, 32, pp. 44-56, 2017.
https://doi.org/10.1016/j.bspc.2016.10.005

R. Tan, M. Perkowski, Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach, Sensors, 17(2), 410,2017.
https://doi.org/10.3390/s17020410


Refbacks

  • There are currently no refbacks.


Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2024 Praise Worthy Prize