A Novel Approach for Different Morphological Characterization of ECG Signal

  • R. Harikumar
  • S. N. Shivappriya
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 221)


The earlier detection of Cardiac arrhythmia of ECG waves is important to prevent cardiac disorders. A good system depends heavily upon the precise and consistent estimate of ECG signal morphology i.e. QRS complex, T and P wave. From the benchmark data bases: MIT-BIH Arrhythmia, QT and European ST-T database the ECG is fetched then the noise is removed from the digitized ECG signal. To analyze various power spectrum of ECG signal Stationary Wavelet Transform (SWT) is applied to the de-noised signal. Based upon the spectrum QRS complex T and P waves are detected and also delineated using different amplitude threshold values. This gives simple and reliable method for the detection and delineation of the constituent waves from a given ECG signal has been the fundamental goal of automatic cardiac arrhythmia detection. This algorithm allows delineation of different morphologies of QRS complex P and T wave.


ECG Wavelet transform Cardiac arrhythmia 



The authors thank the Management and the Principal of Bannari Amman Institute of Technology, Sathyamangalam and Kumaraguru college of Technology, Coimbatore for providing excellent computing facilities and encouragement.


  1. 1.
    Laguna P, Jan´e R, Caminal P (1994) Automatic detection of wave boundaries in multi lead ECG signals: Validation with the CSE database. Comput Biomed Res 27(1):45–60CrossRefGoogle Scholar
  2. 2.
    Chouhan VS, Mehta SS (2008) Threshold-based detection of P and T-wave in ECG using new feature signal. Int J Comput Sci Net Secur 8(2):144–152Google Scholar
  3. 3.
    Weng B, Wang JJ, Michaud F, Blanco-Velasco M (2008) Atrial fibrillation detection using stationary wavelet transform analysis. Conf Proc IEEE Eng Med Biol Soc. 2008:1128–1131Google Scholar
  4. 4.
    Clayton R, Murray A, Campell I (1994) Recognition of ventricular fibrillation using neural network. Med Biol Eng Comput 35: 611–626Google Scholar
  5. 5.
    Coast DA, Stern RM, Cano G, Briller SA (1990) An approach to cardiac arrhythmia analysis using hidden markov models. IEEE Trans Biomed Eng 37: 826–836Google Scholar
  6. 6.
    Dokur Z, Olmez T, Yazgan E (1999) Comparision of discrete wavelet and fourier transform for ECG beat classification. Electron Lett 35:1502–1504CrossRefGoogle Scholar
  7. 7.
    Li C, Zheng C, Tai C (1995) Detection of ECG characteristic points using wavelet transforms. IEEE Trans Biomed Eng 42:21–28CrossRefGoogle Scholar
  8. 8.
    Alfred L, Endt P, Oeff M, Trahms L (2001) Variability of the QRS Signal in High-Resolution ECG and MCG. IEEE Trans Biomed Eng 38:133–143Google Scholar
  9. 9.
    Martinez JP, Almeida R, Olmos S, Rocha AP, Laguna P A wavelet-based ECG delineator: Evaluation on standard databases. IEEE Trans Biomed Eng 51(4)Google Scholar
  10. 10.
    Pandit SV (1996) ECG Baseline drift removal through STFT. In: 18th annual international conference of the ieee engineering in medicine and biology society, AmsterdamGoogle Scholar
  11. 11.
    Meyer CR, Keiser HN (1977) Electrocardiogram baseline noise estimation and removal using cubic splines and state-space computational techniques. Comput Biomed Res 10:459–470CrossRefGoogle Scholar
  12. 12.
    Minami K, Nakajima H, Toyoshima T (1999) Real-time discrimination of beats of ventricular tachyarrhythmia with Fourier transform neural network. IEEE Trans Biomed Eng 46:179–185CrossRefGoogle Scholar
  13. 13.
    Osowski S, Linh TH (2001) ECG beat recognition using fuzzy hybrid neural. IEEE Trans Biomed Eng 44: 1265–1271Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  • R. Harikumar
    • 1
  • S. N. Shivappriya
    • 2
  1. 1.Bannari Amman Institute of TechnologySathyamangalamIndia
  2. 2.Kumaraguru College of TechnologyCoimbatoreIndia

Personalised recommendations