Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

Diagnosis of Different Electrocardiographic Signals using Recurrent Neural Network and Power Spectrum Analysis

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2022
Islam A. Fouad

Islam A Fouad. Diagnosis of Different Electrocardiographic Signals using Recurrent Neural Network and Power Spectrum Analysis. International Journal of Computer Applications 183(48):27-31, January 2022. BibTeX

	author = {Islam A. Fouad},
	title = {Diagnosis of Different Electrocardiographic Signals using Recurrent Neural Network and Power Spectrum Analysis},
	journal = {International Journal of Computer Applications},
	issue_date = {January 2022},
	volume = {183},
	number = {48},
	month = {Jan},
	year = {2022},
	issn = {0975-8887},
	pages = {27-31},
	numpages = {5},
	url = {},
	doi = {10.5120/ijca2022921887},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Among the leading causes of death that affect people today are heart problems. It is possible to prevent sudden death by early detection and treatment of heart conditions. Electrical signals from the heart are recorded as electrocardiograms (ECGs). Deaths due to heart diseases comprise a great deal of human mortality. Signals obtained from the ECG, which are easily obtained without damaging the patient, can serve as good indicators of the type of disorder occurring while the heart is operating. Five different abnormal signals have been classified in this study: Atrial fibrillation (AFIB), Atrial premature beats (APB), Pacemaker rhythm (PR), Left bundle branch block (LBBB), and Bigeminy. The classification performances have also been evaluated. Signals are analyzed using time-frequency analysis and signal features are determined by spectral entropy. The applied deep learning algorithm is the Long Short-Term Memory "LSTM" network. With a dataset from twenty eight participants composed of five different categories, a trained Network method achieved an overall accuracy of 97.574%. In the automatic diagnosis of multiple ECG abnormalities, the performance evaluations of the suggested technique convey its robustness and reliability.


  1. Z. Dokur, “Classification of ECG Pulses Using Artificial Neural Networks and Genetic Algorithms,” Istanbul Technical University, 1999.
  2. G. Bortolan, I. Jekova, and I. Christov, “Comparison of four methods for premature ventricular contraction and normal beat clustering,” in Computers in Cardiology, 2005, 2005, pp. 921–924.
  3. M. Engin, “ECG beat classification using neuro-fuzzy network,” Pattern Recognit. Lett., vol. 25, no. 15, p. 1715–1722, Nov. 2004.
  4. P. Erdoğmuş and A. Pekçakar, “Feature extraction of ECG signals with wavelet transform and classification with artificial neural networks,” pp. 13–15, 2009.
  5. S. Yu and K. Chou, “Integration of independent component analysis and neural networks for ECG beat classification,” Expert Syst. Appl., vol. 34, pp. 2841–2846, 2008.
  6. Güler and E. D. Übeylı˙, “ECG beat classifier designed by combined neural network model,” Pattern Recognit., vol. 38, no. 2, p. 199–208, Feb. 2005.
  7. and
  8. E. Yazgan and M. Korurek, Medical Electronics, 1st Ed. Istanbul: Istanbul Technical University Offset Printing Workshop, 1996.
  9. Shannon, C. E. (1948). Communication theory of secrecy systems. Bell system technical journal, 28(4):656-715.
  10. Sabeti, M., Katebi, S. ve Boostani, R. (2009). Entropy and complexity measures for EEG signal classification of schizophrenic and control participants. Artificial Intelligence in Medicine, 47: 263-274
  11. Andre Esteva, Brett Krupel and Sebastian Thrun, Deep Networks for Early Stage Skin Disease and Skin Cancer Classification, Stanford University, 2015.
  12. Masood A., Al-Jumaily A.A., Adnan T., Development of Automated Diagnostic System for Skin Cancer: Performance Analysis of Neural Network Learning Algorithms for Classification, Wermter S. et al. (eds) Artificial Neural Networks and Machine Learning - ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham
  13. Sepp Hochreiter, Jürgen Schmidhuber, “Long Short-term Memory", Neural Computation 9(8):1735-80, December 1997.
  14. Hu, Y.H., Palreddy, S., Tompkins, W.J., 1997. A patient-adaptable ecg beat classifier using a mixture of experts approach. IEEE transactions on biomedical engineering 44, 891–900.
  15. 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, 1196–1206.
  16. 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, 2535–2543.
  17. Park, K., Cho, B., Lee, D., Song, S., Lee, J., Chee, Y., Kim, I., Kim, S., 2008. Hierarchical support vector machine based heartbeat classification using higher order statistics and hermite basis function, in: 2008 Computers in Cardiology, IEEE. pp. 229–232.
  18. Islam A. Fouad, Hany Elnashar, “An Efficient and High-Performance System for Skin Cancer Multi-Classification Using Machine Learning”, Annals of RSCB, vol. 25, no. 6, pp. 20931–20945, Nov. 2021.


Electrocardiogram ECG, Signal Analysis, Extracting Features,  long short-term memory (LSTM) networks, and Classification