Total views : 187

Optimization of ECG Peaks (Amplitude and Duration) in Predicting ECG Abnormality using Artificial Neural Network


  • Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Pertahanan Nasional Malaysia, Kuala Lumpur, Malaysia


Artificial Neural Networks (ANN) adapted from neuron concept's, generally applied in various applications especially the fields of biomedical engineering. ANN techniques have been applied in order to provide educated solutions to assist in decision making for the medical purpose. The study was conducted for the purpose of determining the suitability and implementation of ANN to detect ECG abnormalities by using six features from ECG signal, both amplitude and duration of P, QRS and T peaks and used as input vector for ANN. In this study, Multilayer Perceptron (MLP) network is trained by using three different training/learning algorithms. The network is trained by using Bayesian Regularization (BR) algorithm has provided the highest accuracy performance (93.19%), followed by Levenberg Marquardt (LM) (92.88%) and Backpropagation (BP) (88.63%).


Amplitude, Duration, ECG Abnormality, Multilayer Perceptron Network.

Full Text:

 |  (PDF views: 121)


  • Barker RL, Burton BJ, Zieve PD. Principles of Ambulatory Medicine. 6th ed. Philadelphia: Lippincott, Wilkins and Williams; 2003.
  • Custer JW, Rue RE. The Harriet Lane Handbook. 18th ed. Philadelphia: Mosby Elsevier Inc; 2008.
  • Mark JB. Atlas cardiovascular monitoring. New York: Churchill Livingstone; 1998.
  • Houghton AR, Gray D. Making Sense of the ECG. 3rd ed. Hodder Education; 2012. p. 214.
  • Plesnik E,Malgina O, Tasic JF, Zajc M. ECG signal acquisition and analysis for telemonitoring.15th IEEE Mediterranean Electrotechnical Conference (MELECON); 2010. Crossref
  • Sonali SO, Sunkaria RK. ECG signal denoising based on Empirical Mode Decomposition and moving average filter. IEEE International Conference on Signal Processing, Computing and Control (ISPCC); 2013. Crossref
  • Haykin S. Neural network: A comprehensive foundation. New Jersey: Prentice Hall; 1994.
  • Payal A, Rai CS, Reddy BVR. Comparative analysis of Bayesian regularization and Levenberg-Marquardt training algorithm for localization in wireless sensor network. 15th International Conference on Advanced Communication Technology (ICACT); 2013.
  • Kaensar C. Analysis on the parameter of back propagation algorithm with three weight adjustment structure for hand written digit recognition.10th International Conference on Service Systems and Service Management (ICSSSM); 2013. Crossref
  • Gas B. Self-organizing multilayer perceptron. IEEE Transactions on Neural Networks. 2013; 21(11):1766–79. PMid:20858579. Crossref
  • Sivaram GSVS, Hermansky H. Multilayer perceptron with sparse hidden outputs for phoneme recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2011. Crossref
  • Isa NAM, Hashim FR, Mei FW, Ramli DA, Omar WMW, Zamli KZ. Predicting quality of river’s water based on algae composition using artificial neural network. 2006 IEEE International Conference on Industrial Informatics; 2006. p. 1340–5.
  • Ramli DA, Saleh JM, Hashim FR, Isa NAM. Multilayered Perceptron (MLP) network trained by recursive least squares algorithm. International Conference on Computers, Communications, and Signal Processing with Special Track on Biomedical Engineering; 1st CCSP 2005; 2005. p. 288–91. Crossref
  • MIT-BIH Arrhythmia Database – PhysioNet.
  • Mat Isa NA, Mashor MY, Othman NH. Classification of cervical cancer using HMLP network with confident level analysis. International Journal of Computer, the Internet and Management. 2003; 11(1):7–29.
  • Mitra P, Mitra S, Pal SK. Staging of cervical cancer with soft computing. IEEE Transaction on Biomedical Engineering. 2000; 47(7):934–40. PMid:10916265. Crossref


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.