Neural Computing and Applications

, Volume 21, Issue 8, pp 2065–2070 | Cite as

Adaptive neuro-fuzzy estimation of autonomic nervous system parameters effect on heart rate variability

  • D. PetkovićEmail author
  • Ž. Ćojbašić
Original Article


Heart rate signal can be used as certain indicator of heart disease. Spectral analysis of heart rate variability (HRV) signal makes it possible to partly separate the low-frequency (LF) sympathetic component, from the high-frequency (HF) vagal component of autonomic cardiac control. Here, we used two important features to characterize the nonlinear fluctuations in the heart variability signal (HRV): cardiac vagal index (CVI) and cardiac sympathetic index (CSI) which indicates vagal and sympathetic function separately. This article presents a methodology for analyzing the influence of CVI and CSI on heart rate variability spectral patterns—low-frequency (LF) and high-frequency (HF) spectral bands and LF/HF ratio. An adaptive neuro-fuzzy network is used to approximate correlation between these two features and spectral patterns. This system is capable to find any change in ratio of features and spectral patterns of heart rate variability signal (HRV) and thus indicates state of both parasympathetic and sympathetic functions in newly diagnosed patients with heart diseases.


Heart rate Neuro-fuzzy Nervous system Poincare plot Spectral frequency 


  1. 1.
    Zhong Y, Wang H, Ju KH, Jan KM, Chon KH (2004) Nonlinear analysis of the separate contributions of autonomic nervous systems to heart rate variability using principal dynamic modes. IEEE Trans Biomed Eng 51:255–262CrossRefGoogle Scholar
  2. 2.
    Pan J, Tompkins JW (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 32:230–255CrossRefGoogle Scholar
  3. 3.
    Malik M (1996) Heart rate variability: standards of measurement, physiological interpretation, and clinical use. Eur Heart J 17:354–381CrossRefGoogle Scholar
  4. 4.
    Berntson GG, Bigger JT et al (1997) Heart rate variability: origins, methods, and interpretative caveats. Psychophysiology 34:623–648CrossRefGoogle Scholar
  5. 5.
    Pincus MS (1991) Approximate entropy as a measure of system complexity. Proc Nat Acad Sci 88:2297–2301MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Xinbao N, Chunhua B, Jun W, Ying C (2006) Research progress in nonlinear analysis of heart electric activities. Chin Sci Bull 51:385–393CrossRefGoogle Scholar
  7. 7.
    Chunhua B, Xinbao N (2004) Nonlinearity degree of short-term heart rate variability signal. Chin Sci Bull 49:530–534Google Scholar
  8. 8.
    Mourot L, Bouhaddi M, Perrey S et al (2004) Quantitative Poincare plot analysis of heart rate variability: effect of endurance training. Eur J Appl Physiol 91:79–87CrossRefGoogle Scholar
  9. 9.
    Lerma C, Infante I, Groves HP, Jose MV (2003) Poincare plot indexes of heart rate variability capture dynamic adaptations after haemodialysis in chronic renal failure patients. Clin Physiol Func Im 23:72–80CrossRefGoogle Scholar
  10. 10.
    Addio GD, Pinna GD, Rovere MTL, Maestri R et al (2001) Prognostic value of Poincare plot indexes in chronic heart failure patients. Comput Cardiol 28:57–60Google Scholar
  11. 11.
    Chiu HW, Wang TH, Huang LC et al (2003) The influence of mean heart rate on measures of heart rate variability as markers of autonomic function: a model study. Med Eng Phys 25:475–481CrossRefGoogle Scholar
  12. 12.
    Basano L, Canepa F, Ottonello P (1998) Real-time spectral analysis of HRV signals: an interactive and user-friendly PC system. Comput Methods Programs Biomed 55:69–76CrossRefGoogle Scholar
  13. 13.
    Wu GQ, Arzeno MN, Shen LL et al (2009) Chaotic signatures of heart rate variability and its power spectrum in health, aging and heart failure. PLoS One Public Library Sci 4:2Google Scholar
  14. 14.
    Busek P, Vankova J, Opavsky J et al (2005) Spectral analysis of heart rate variability in sleep. Physiol Res 54:369–376Google Scholar
  15. 15.
    Groome JL, Mooney MD, Bentz SL, Singh PK (1994) Spectral analysis of heart rate variability during quiet slep in normal human fetuses between 36 and 40 weeks of gestation. Early Hum Dev 38:1–10CrossRefGoogle Scholar
  16. 16.
    Colak HO (2009) Preprocessing effects in time-frequency distributions and spectral analysis of heart rate variability. Dig Sig Proc 19:731–739CrossRefGoogle Scholar
  17. 17.
    Khandoker AH, Jelinek HF, Moritani T, Palaniswami M (2010) Association of cardiac autonomic neuropathy with alteration of sympatho-vagal balance through heart rate variability analysis. Med Eng Phys 32:161–167CrossRefGoogle Scholar
  18. 18.
    Toichi M, Sugiura T, Murai T, Sengoku A (1997) A new method of assessing cardiac autonomic function and its comparision with spectral analysis and coefficient of variation of R-R interval. J Aut Nerv Syst 62:79–84CrossRefGoogle Scholar
  19. 19.
    Lin CW, Wang JS, Chung PC (2010) Mining physiological conditions from heart rate variability analysis. IEEE Comput Intell Mag 5:50–58Google Scholar
  20. 20.
    Apfelbaum JD, Caravati EM, Kerns WP, Bossart PJ, Larsen G (1995) Cardiovascular effects of carbamazepine toxicity. Ann Emerg Med 25:631–635CrossRefGoogle Scholar
  21. 21.
    Meneses ASJ, Moreira HG, Daher MT (2004) Analysis of heart rate variability in hypertensive patients before and after treatment with angiotensin II-converting enzyme inhibitors. Arquivos Brasileros de Cardiologia 83:169–172Google Scholar
  22. 22.
    Lado MJ, Vila XA, Rodrigez LL, Mendez AJ, Olivieri DN, Felix P (2009) Detecting sleep apnea by heart rate variability analysis: assessing the validity of databases and algorithms. J Med Syst 33:1–9Google Scholar
  23. 23.
    Persson H, Ericson M, Tomson T (2007) Heart rate variability in patients with untreated epilepsy. Seizure 16:504–508CrossRefGoogle Scholar
  24. 24.
    Hallioglu O, Ocuyaz C, Mert E, Makharoblidze K (2008) Effects of antiepileptic drug therapy on heart rate variability in children with epilepsy. Epilepsy Res 79:49–54CrossRefGoogle Scholar
  25. 25.
    Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23:665–685CrossRefGoogle Scholar
  26. 26.
    Yardimci A (2009) Soft computing in medicine. Appl Soft Comput 9:1029–1043CrossRefGoogle Scholar
  27. 27.
    Ubeyli ED (2009) Adaptive neuro-fuzzy inference system for classification of ECG signals using Lyapunov exponents. Comput Method Prog Biomed 93:313–321CrossRefGoogle Scholar
  28. 28.
    Nazmy TM, El-Messiry H, Al-Bokhity B (2009) Adaptive neuro-fuzzy inference system for classification of ECG signals. J Theor Appl Inform Tech 12:71–76Google Scholar
  29. 29.
    Rajendra UA, Subbanna PB, Iyengar SS, Rao A, Dua S (2003) Classification of heart rate data using artificial neural network and fuzzy equivalence relation. Pattern Recogn 36:61–68CrossRefzbMATHGoogle Scholar
  30. 30.
    Ubeyli ED (2010) Recurrent neural networks employing Lyapunov exponents for analysis of ECG signals. Exp Syst Appl 37:1192–1199CrossRefGoogle Scholar
  31. 31.
    Maglaveres N, Stamkopolulos T, Diamantaras K, Pappas C, Strintzis M (1998) ECG pattern recognition and classification using non-linear transformations and neural networks: a review. Int J Med Inform 52:191–208CrossRefGoogle Scholar
  32. 32.
    Ozbay Y, Tezel G (2009) A new method for classification of ECG arrhythmias using neural network with adaptive activation function. Digi Sig Proc 20:1040–1049Google Scholar
  33. 33.
    Hosseini HG, Luo D, Reynolds KJ (2006) The comparision of different feed forward neural network architectures for ECG signal diagnosis. Med Eng Phys 28:372–378CrossRefGoogle Scholar
  34. 34.
    Ceylan R, Ozbay Y, Karlik B (2009) A novel approach for classification of ECG arrhythmias: type-2 fuzzy clustering neural network. Exp Syst Appl 36:6721–6726CrossRefGoogle Scholar
  35. 35.
    Osowski S, Markiewicz T, Hoai LT (2009) Recognition and classification system of arrhythmia using ensemble of neural networks. Measurement 41:610–617CrossRefGoogle Scholar
  36. 36.
    Anuradha MB, Reddy VCV (2009) Cardiac arrhythmia classification using fuzzy classifiers. J Theor Appl Inform Tech 4:353–359Google Scholar
  37. 37.
    Mohammadzadeh-Asl B, Setarehdan SK (2006) Neural network based arrhythmia classification using heart rate variability signal. In: 14th European signal processing conferenceGoogle Scholar
  38. 38.
    Patil SB, Kumaraswamy YS (2009) Intelligent and effective heart attack prediction system using data mining and artificial neural network. Eur J Sci Res 31:642–656Google Scholar
  39. 39.
    Annuradha B, Reddy VCV (2008) ANN for classification of cardiac arrhythmias. ARPN J Engin Appl Sci 3:1–6Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.University of Niš, Mechanical Engineering FacultyNišSerbia
  2. 2.Department of Mechatronics and ControlUniversity of NišNisSerbia

Personalised recommendations