Combining deep learning features and frequency domain features for detection of premature ventricular contraction arrhythmia

Authors

  • Reza Nasiri * Department of Electrical Engineering, Ra.C., Islamic Azad University, Rasht, Iran.
  • Azadeh Kiani Sarkaleh Department of Electrical Engineering, Ra.C., Islamic Azad University, Rasht, Iran. https://orcid.org/0000-0003-0143-1892

https://doi.org/10.22105/thi.v2i3.58

Abstract

With the help of signal processing and image processing science, matters that were not analyzable in medical science or were not easily diagnosable are converted into high-resolution images. Furthermore, in many cases, tasks have been transformed into automatic and operator-independent mechanized processes. This can be highly beneficial in third-world countries where medical facilities cannot adequately respond to the large number of patients. Perhaps one of the most essential devices used in every hospital is the equipment for diagnosing vital body signs. In this thesis, a new method is proposed for detecting cardiac diseases to classify normal and abnormal heart function. In the proposed method, first, appropriate preprocessing is performed to remove noise from the electrocardiography (ECG) signal. Then, various temporal and wavelet features are extracted from the noise-free signal. Subsequently, the proposed hybrid structures of deep learning networks are trained for proper classification of arrhythmias, and their performance is evaluated. The results obtained from implementation on the labeled data of the MIT-BIH database demonstrate the superior efficiency of the proposed method compared to previous methods in detecting cardiac arrhythmias.

Keywords:

Signal processing, Cardiac diseases, Cardiac arrhythmias, Deep learning, Wavelet

References

  1. [1] Moody, G. B., & Mark, R. G. (2001). The impact of the MIT-BIH arrhythmia database. IEEE engineering in medicine and biology magazine, 20(3), 45–50. https://doi.org/10.1109/51.932724
  2. [2] De Chazal, P., O’Dwyer, M., & Reilly, R. B. (2004). Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE transactions on biomedical engineering, 51(7), 1196–1206. https://doi.org/10.1109/TBME.2004.827359
  3. [3] Prisco, A. R., Castro, J. R., Roukoz, H., & Tholakanahalli, V. N. (2023). Premature ventricular complexes: Benign versus malignant–how to approach? Indian pacing and electrophysiology journal, 23(6), 189–195. https://doi.org/10.1016/j.ipej.2023.09.004
  4. [4] Pan, J., & Tompkins, W. J. (1985). A real-time QRS detection algorithm. IEEE transactions on biomedical engineering, BME-32(3), 230–236. https://doi.org/10.1109/TBME.1985.325532
  5. [5] De Chazal, P., & Reilly, R. B. (2006). A patient-adapting heartbeat classifier using ECG morphology and heartbeat interval features. IEEE transactions on biomedical engineering, 53(12), 2535–2543. https://doi.org/10.1109/TBME.2006.883802
  6. [6] Addison, P. S. (2005). Wavelet transforms and the ECG: A review. Physiological measurement, 26(5), R155–R199. https://doi.org/10.1088/0967-3334/26/5/R01
  7. [7] Khadra, L., Al-Fahoum, A. S., & Al-Nashash, H. (1997). Detection of life-threatening cardiac arrhythmias using the wavelet transformation. Medical and biological engineering and computing, 35(6), 626–632. https://doi.org/10.1007/BF02510970
  8. [8] Kiranyaz, S., Ince, T., & Gabbouj, M. (2015). Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE transactions on biomedical engineering, 63(3), 664–675. https://doi.org/10.1109/TBME.2015.2468589
  9. [9] Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., Adam, M., Gertych, A., & San Tan, R. (2017). A deep convolutional neural network model to classify heartbeats. Computers in biology and medicine, 89, 389–396. https://doi.org/10.1016/j.compbiomed.2017.08.022
  10. [10] Murat, F., Yildirim, O., Talo, M., Baloglu, U. B., Demir, Y., & Acharya, U. R. (20220). Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review. Computers in biology and medicine, 120, 103726. https://doi.org/10.1016/j.compbiomed.2020.103726
  11. [11] Hong, S., Zhou, Y., Shang, J., Xiao, C., & Sun, J. (2020). Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review. Computers in biology and medicine, 122, 103801. https://doi.org/10.1016/j.compbiomed.2020.103801
  12. [12] Pandey, S. K., Shukla, A., Bhatia, S., Gadekallu, T. R., Kumar, A., Mashat, A., … & Janghel, R. R. (2023). Detection of arrhythmia heartbeats from ECG signal using wavelet transform-based CNN model. International journal of computational intelligence systems, 16(1), 80. https://doi.org/10.1007/s44196-023-00256-z
  13. [13] Zhang, Y., Yi, J., Chen, A., & Cheng, L. (2023). Cardiac arrhythmia classification by time--frequency features inputted to the designed convolutional neural networks. Biomedical signal processing and control, 79, 104224. https://doi.org/10.1016/j.bspc.2022.104224
  14. [14] Kim, N., Seo, W., Kim, J., Choi, S. Y., & Park, S. M. (2023). WavelNet: A novel convolutional neural network architecture for arrhythmia classification from electrocardiograms. Computer methods and programs in biomedicine, 231, 107375. https://doi.org/10.1016/j.cmpb.2023.107375
  15. [15] Wang, Z., Wang, K., Chen, X., Zheng, Y., & Wu, X. (2024). A deep learning approach for inter-patient classification of premature ventricular contraction from electrocardiogram. Biomedical signal processing and control, 94, 106265. https://doi.org/10.1016/j.bspc.2024.106265
  16. [16] Kumar Sahu, N., Ayub, S., & JP, S. (2013). Detection of normal ECG and Arrhythmia using adaptive neuro-fuzzy interface system. International journal of advanced research in computer science and software engineering, 925–932. https://api.semanticscholar.org/CorpusID:18459537
  17. [17] Gowri, T., Kumar, P. R., Reddy, D. V. R. K., & Rahman, M. Z. U. (2015). Denoising artifacts from cardiac signal using normalized variable step size LMS algorithm. Sensors & transducers, 187(4), 138–145. https://sensorsportal.com/HTML/DIGEST/april_2015/Vol_187/P_RP_0200.pdf
  18. [18] Kraft, D., Bieber, G., Jokisch, P., & Rumm, P. (2023). End-to-end premature ventricular contraction detection using deep neural networks. Sensors, 23(20), 8573. https://doi.org/10.3390/s23208573
  19. [19] De Marco, F., Ferrucci, F., Risi, M., & Tortora, G. (2022). Classification of QRS complexes to detect Premature Ventricular Contraction using machine learning techniques. Plos one, 17(8), e0268555. https://doi.org/10.1371/journal.pone.0268555

Published

2025-09-18

Issue

Vol. 2 No. 3 (2025): Trends in Health Informatics

Section

Articles

License

Copyright (c) 2026 Trends in Health Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Nasiri, R. ., & Kiani Sarkaleh, A. . (2025). Combining deep learning features and frequency domain features for detection of premature ventricular contraction arrhythmia. Trends in Health Informatics, 2(3), 171-180. https://doi.org/10.22105/thi.v2i3.58

Similar Articles

1-10 of 16

You may also start an advanced similarity search for this article.