نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی دکتری، دانشکده‌ی برق و کامپیوتر، واحد کازرون، دانشگاه آزاد اسلامی، کازرون، ایران

2 استادیار، دانشکده‌ی برق و کامپیوتر، واحد کازرون، دانشگاه آزاد اسلامی، کازرون، ایران

3 استادیار، دانشکده‌ی برق و کامپیوتر، دانشگاه ارومیه، ارومیه، ایران

10.22041/ijbme.2022.554427.1776

چکیده

تشخیص خودکار آریتمی­های قلبی برای درمان موفق بیماری­های قلبی از اهمیت زیادی برخوردار است و یادگیری ماشین برای این منظور مورد استفاده قرار می­گیرد. برای طبقه‌بندی صحیح کلاس‌های آریتمی، استخراج ویژگی­های مناسب جهت ایجاد تمایز بین کلاس­های مختلف، اهمیت زیادی دارد. در این مقاله از یک شبکه‌ی عصبی پیچشی عمیق برای استخراج ویژگی استفاده شده است. با توجه به این که ضربان‌های قلبی بیماران مختلف دارای تفاوت زیادی هستند، کلاس­های آریتمی دارای تغییرات درون‌کلاسی زیادی خواهند بود. برای کاهش تغییرات درون‌کلاسی، ضربان‌های قلبی هر بیمار با یک تابع اختصاصی به نحوی نگاشت داده شده است که شباهت آن به ضربان­های قلبی یکی از بیماران آموزشی افزایش یابد. نگاشت اختصاصی پیشنهادی سبب کاهش تغییرات درون‌کلاسی شده و دقت طبقه‌بندی آریتمی­های قلبی را به میزان قابل ملاحظه­ای افزایش داده است. برای اثبات کارایی روش پیشنهادی، نتایج آن با چندین تحقیق جدید بر اساس سه معیار ارزیابی دقت، حساسیت و اختصاصیت و روی مجموعه‌ی داده‌ی یکسان مقایسه شده است. دقت به دست آمده حدود 24/96 درصد بوده که نشان دهنده‌ی کارایی بهتر روش پیشنهادی در مقایسه با سایر کارها است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Arrhythmia Classification Improvement by Individually Mapping the Feature Space of each patient

نویسندگان [English]

  • Hamid Shafaatfar 1
  • Mehdi Taghizadeh 2
  • Morteza Valizadeh 3
  • Mohamad Hossein Fatehi 2

1 Ph.D. Student, Department of Electrical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran

2 Assistant Professor, Department of Electrical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran

3 Assistant Professor, Department of Electrical Engineering, Urmia University, Urmia, Iran

چکیده [English]

Automatic detection of cardiac arrhythmias is very important for the successful treatment of heart disease and machine learning is used for this purpose. To correctly classify arrhythmic classes, it is important to extract the appropriate features to distinguish between different classes. In this paper, a deep convolutional neural network is used to extract the feature. Due to the fact that the heart rates of different patients are very different, arrhythmia classes will have many intra-class changes. To reduce intra-class changes, each patient’s heart rate is mapped with a dedicated function to increase its resemblance to the heart rate of one of the training patient data’s. The proposed specific mapping reduces intra-class changes and significantly increases the classification accuracy of cardiac arrhythmias. To prove the effectiveness of the proposed method, its results were compared with several new studies based on three criteria for accuracy, sensitivity and specificity and on the same data set. The accuracy obtained is about 96.24%, which shows the better performance of the proposed method compared to other works.

کلیدواژه‌ها [English]

  • Cardiac Arrhythmia
  • Classification
  • Feature Extraction
  • Feature Space Mapping
  1. Sahoo, M. Dash, S. Behera, S. Sabut, “Machine Learning Approach to Detect Cardiac Arrhythmias in ECG Signals: A Survey”, IRBM, Vol 41, Issue 4, pp. 185-194, Jan 2020.
  2. H. Choi, H. Yoon, H. B. Kim, H. S. Kim, H. B. Kwon, S. M., Oh, Y. J., Lee and K. S. ,Park, “Real-time apnea-hypopnea event detection during sleep by convolutional neural networks” Computers in biology and medicine, No. 100, pp. 123-131, 2018.
  3. Moini J. “Cardiopulmonary Pharmacology for Respiratory Care”, Jones & Bartlett
    Learning, Nov 2010.
  4. J. Martis, U. R. Acharya, L. C. Min, “Ecg Beat Classification Using Pca, Lda, Ica and Discrete Wavelet Transform”. Biomedical Signal Processing and Control, Vol. 8, Issue 5, pp. 437-448, 2013.
  5. Conover, B, “Understanding electrocardiography”, Elsevier Health Sciences, 2002.
  6. Mikolov, S. Kombrink, L. Burget, J. Černocký and S. Khudanpur, “Extensions of recurrent neural network language model”, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5528-5531, 2011.
  7. Graves, A. Mohamed and G. Hinton, “Speech recognition with deep recurrent neural networks”, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6645-6649, 2013.
  8. M. Rai, A. Trivedi, and S. Shukla, “ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier”, Measurement, vol. 46, no. 9, pp. 3238 – 3246, May 2013.
  9. Koruürek and B. Doğan, “ECG beat classification using particle swarm optimization and radial basis function neural network”, Expert Systems with Applications, vol. 37, no. 12, pp. 7563-7569, May 2010.
  10. Garcia, G. Moreira, D. Menotti, E. Luz, “Inter-patient ECG heartbeat classification with temporal VCG optimized by PSO”, Scientific Reports, vol. 7, no. 1, pp. 1–11, Sep 2017.
  11. Soleimani, S. Rouhani, “Heart arrhythmia diagnosis by neural networks using chaotic features of HRV signal and generalized discriminant analysis”, Iranian Journal of Biomedical Engineering, vol. 5, no. 2, pp. 89-103. Jun 2011.
  12. Karpagachelvi, M. Arthanari, and M. Sivakumar, “Classification of Electrocardiogram Signal With Extreme Learning Machine and Vector Machine”, Neural Computing and Applications, vol. 8, no. 1, Sep 2011.
  13. Castro, D. Kogan and A. B. Geva, “ECG feature extraction using optimal mother wavelet”, 21st IEEE Convention of the Electrical and Electronic Engineers in Israel. Proceedings (Cat. No.00EX377), pp. 346-350, 2000.
  14. Danandeh Hesar, A. Danandeh Hesar, “An Improved Model-Based Bayesian Framework for ECG Processing in Non-Stationary Environments”, Iranian Journal of Biomedical Engineering, vol. 15, no. 3, pp. 231-240, Jan 2022.
  15. J. Martis, U. R. Acharya, and H. Adeli, “Current Methods in Electrocardiogram Characterization”, Computers in biology and medicine, vol. 48, pp. 133-149, May 2014.
  16. J. Martis, U. R.Acharya, K. Mandana, A.Ray, and C. Chakraborty, “ Cardiac Decision Making Using Higher Order Spectra”,  Biomedical Signal Processing and Control, Vol. 8, Issue 2, pp. 193-203, Mar 2013.
  17. Li, R. Qian, K. Li, “Inter-patient arrhythmia classification with improved deep residual convolutional neural network”, Computer Methods and Programs in Biomedicine, vol. 214, p.106582, Feb 2022.
  18. Chen, Y. Lin, S. Lee, W. Tsai, T. Huang, Y. Liu, M. Cheng, C. Dai, “Automated ECG classification based on 1D deep learning network Methods”, Methods, vol. 202, pp. 127-135, Jun 2022.
  19. Takalo-Mattila, J. Kiljander and J. Soininen, “Inter-Patient ECG Classification Using Deep Convolutional Neural Networks”, 21st Euromicro Conference on Digital System Design (DSD), pp. 421-425, 2018.
  20. Wang, R. Li, B.Fu, C. Xiao, and D.Z. Chen,  “Towards interpretable arrhythmia classification with human-machine collaborative knowledge representation”. IEEE Transactions on Biomedical Engineering, 68(7), pp.2098-2109, 2020.
  21. Zhang, , J. Li, , S. Wei, , F. Zhou, and D. Li, “Heartbeats Classification Using Hybrid Time-Frequency Analysis and Transfer Learning Based on ResNet”. IEEE Journal of Biomedical and Health Informatics, 25(11), pp.4175-4184, 2021.
  22. Sellami, H. Hwang, “A robust deep convolutional neural network with batch-weighted loss for heartbeat classification”, Expert Systems with Applications, Vol. 122, pp. 75–84, May 2019.
  23. https://physionet.org/content/mitdb/1.0.0/
  24. Kiranyaz, T. Ince and M. Gabbouj, “Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks”, IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 664-675, Mar 2016.
  25. Chollet, “Deep Learning with Python”, Manning Publications, 2018. S. Ioffe, C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift”, International Conference on Machine Learning, pp. 448–456, Feb 2015.