Analysis of ECG Signals

International Journal of Electronics and Communication Engineering

© 2016 by SSRG - IJECE Journal

Volume 3 Issue 4

Year of Publication : 2016

Authors : Apurva Kulkarni, Snehal Lale, Pranali Ingole and Sayali Gengaje

10.14445/23488549/IJECE-V3I4P104

How to Cite?

Apurva Kulkarni, Snehal Lale, Pranali Ingole and Sayali Gengaje, "Analysis of ECG Signals," SSRG International Journal of Electronics and Communication Engineering, vol. 3,  no. 4, pp. 15-17, 2016. Crossref, https://doi.org/10.14445/23488549/IJECE-V3I4P104

Abstract:

Electrocardiogram (ECG) Feature Extraction plays a significant role in diagnosing most of the cardiac diseases. ECG is a non-linear, non-stationary signal. It is used for the primary diagnosis of heart abnormalities. The ECG signals were taken from MIT-BIH arrhythmias database for analysis. Noises in the ECG signal such as powerline interference, baseline wandering and muscle noises were removed using bandpass filter. Different statistical and morphological features were extracted for both normal as well as abnormal cases. These features include R-R interval, heart rate arithmetic mean, median, variance, skewness, kurtosis etc. The values of the feature vector reveal the information regarding status of cardiac health. Platform used for implementation is MATLAB. This paper includes comparative analysis of various transform-based techniques. For differentiating normal and abnormal signals, we have used KNN classifier. We have achieved an accuracy of 86.95%, sensitivity of 87.09% and specificity of 86.66% for 60% training dataset using this classifier.

Keywords:

  Electrocardiogram (ECG), Discrete Wavelet Transform (DWT), KNN Classifier.

References:

[1] www.physionet.org
[2] Dangi, Vikramaditya, Amol Parab, and Kshitij Pawar. "Analysis of Transform Based ECG Compression Techniques." Proc. of the International Conference on Advances in Electronics and Electrical Engineering–AEEE. 2012.
[3] Shetty, Prashanth, and Somashekhara Bhat. "Analysis of Various Filter Configurations on Noise Reduction in ECG Waveform." International Journal of Computing, Communications and Instrumentation Engg., Vol. 1, Issue 1 (2014).
[4] Saritha, C., V. Sukanya, and Y. Narasimha Murthy. "ECG signal analysis using wavelet transforms." Bulg. J. Phys 35.1 (2008): 68-77.
[5] Rai, Hari Mohan, and Anurag Trivedi. "De-noising of ECG Waveforms based on Multi-resolution Wavelet Transform." International Journal of Computer Applications (0975–8887) Volume (2012).
[6] Pan, Jiapu, and Willis J. Tompkins. "A real-time QRS detection algorithm" Biomedical Engineering, IEEE Transactions on 3 (1985): 230-236.
[7] Saini, Indu, Dilbag Singh, and Arun Khosla. “QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases” Journal of advanced research 4.4 (2013): 331-344.
[8] Robi Polikar, “The Wavelet Tutorial”
[9] Minakshi Chaudhary, D.V.Saini, Sukhvinder Kaur. “Entropic method of measurement of heart rate in 12 lead ECG using Artificial Neural Network” SSRG International Journal of Electronics and Communication Engineeering – EFES April 2015