Arrhythmia Classification Using Local Hölder Exponents and Support Vector Machine

  • Aniruddha Joshi
  • Rajshekhar
  • Sharat Chandran
  • Sanjay Phadke
  • V. K. Jayaraman
  • B. D. Kulkarni
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3776)


We propose a novel hybrid Hölder-SVM detection algorithm for arrhythmia classification. The Hölder exponents are computed efficiently using the wavelet transform modulus maxima (WTMM) method.

The hybrid system performance is evaluated using the benchmark MIT-BIH arrhythmia database. The implemented model classifies 160 of Normal sinus rhythm, 25 of Ventricular bigeminy, 155 of Atrial fibrillation and 146 of Nodal (A-V junctional) rhythm with 96.94% accuracy. The distinct scaling properties of different types of heart rhythms may be of clinical importance.


Support Vector Machine Wavelet Transformation Normal Sinus Rhythm Multifractal Formalism Multiclass Support Vector Machine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Morchen, F.: Time series feature extraction for data mining using DWT and DFT. Technical Report 33, Dept. of Mathematics and Computer Science, Philipps-University Marburg., Germany (2003)Google Scholar
  2. 2.
    Owis, M., Abou-Zied, A., Youssef, A.B., Kadah, Y.: Robust feature extraction from ECG signals based on nonlinear dynamical modeling. In: 23rd Annual Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC 2001), vol. 2, pp. 1585–1588 (2001)Google Scholar
  3. 3.
    Scafetta, N., Griffin, L., West, B.J.: Hölder exponent spectra for human gait. Physica A: Statistical Mechanics and its Applications 328, 561–583 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Struzik, Z.R., Siebes, A.P.J.M.: Outlier detection and localisation with wavelet based multifractal formalism. Technical Report INS-R0008, CWI (2000)Google Scholar
  5. 5.
    Struzik, Z.R.: Revealing local variability properties of human heartbeat intervals with the local effective Hö lder exponent. Fractals 9, 77–93 (2001)CrossRefGoogle Scholar
  6. 6.
    Muzy, J., Bacry, E., Arneodo, A.: The multifractal formalism revisited with wavelets. International Journal of Bifurcation and Chaos 4, 245–302 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Hwang, W.L., Mallat, S.: Characterization of self-similar multifractals with wavelet maxima. Applied and Computational Harmonic Analysis 1, 316–328 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Arneodo, A., Bacry, E., Muzy, J.: The thermodynamics of fractals revisited with wavelets. Physica A: Statistical and Theoretical Physics 213, 232–275 (1995)CrossRefGoogle Scholar
  9. 9.
    Struzik, Z.R.: Removing divergences in the negative moments of the multi-fractal partition function with the wavelet transform. Technical Report INS-R9803, CWI (1998)Google Scholar
  10. 10.
    Struzik, Z.R.: Determining local singularity strengths and their spectra with the wavelet transform. Fractals 8 (2000)Google Scholar
  11. 11.
    Vapnik, V.: The nature of statistical learning theory. Springer, New York (1995)zbMATHGoogle Scholar
  12. 12.
    Kulkarni, A., Jayaraman, V.K., Kulkarni, B.D.: Support vector classification with parameter tuning assisted by agent based techniques. Computers and Chemical Engineering 28, 311–318 (2004)CrossRefGoogle Scholar
  13. 13.
    Mitra, P., Uma Shankar, B., Sankar, K.P.: Segmentation of multispectral remote sensing images using active support vector machines. Pattern recognition letters 25, 1067–1074 (2004)CrossRefGoogle Scholar
  14. 14.
    Hsu, C.W., Lin, C.J.: A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  15. 15.
    Novak, D., Cuesta-Frau, D., Eck, V., Perez-Cortes, J., Andreu-Garcia, G.: Denoising electrocardiographic signals using adaptive wavelets. Biosignal, 18–20 (2000)Google Scholar
  16. 16.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Aniruddha Joshi
    • 1
  • Rajshekhar
    • 2
  • Sharat Chandran
    • 1
  • Sanjay Phadke
    • 3
  • V. K. Jayaraman
    • 2
  • B. D. Kulkarni
    • 2
  1. 1.Computer Science and Engg. Dept.IIT BombayPowai, MumbaiIndia
  2. 2.Chemical Engineering DivisionNational Chemical LaboratoryPuneIndia
  3. 3.Consultant, Jahangir HospitalPuneIndia

Personalised recommendations