Biomedical Applications of Radial Basis Function Networks

  • A. Saastamoinen
  • M. Lehtokangas
  • A. Värri
  • J. Saarinen
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 67)


An important and interesting group of applications of Radial Basis Function (RBF) networks lies on the field of biomedical engineering. These applications include intelligent signal and image analysis techniques ranging from classification and waveform detection methods to decision making and decision support systems. This chapter begins with a review on the biomedical applications of radial basis function networks. After that, we discuss some general design considerations based on our experiences on the field. Finally, as an example on the design process in general, we present our recent contribution on biomedical waveform detection.


Radial Basis Function Hide Neuron Input Pattern Radial Basis Function Network Normalize Mean Square Error 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Barlow, J.S. (1986), “Artefact processing (rejection and minimization) in EEG data processing,” in Lopes da Silva, F.H., Storm van Leeuven, W., and Rémond, A. (Eds.), Handbook of Electroencephalography and Clinical Neurophysiology, Volume 2, Clinical Applications of Computer Analysis of EEG and other Neuro-physiological Signals, Elsevier Science Publishers, pp. 15–62.Google Scholar
  2. [2]
    Bortolan, G., Silipo, R., and Marchesi, C. (1997), “Fuzzy pattern classification and the connectionist approach,” Pattern Recognition Letters, vol. 17, pp. 661–670.CrossRefGoogle Scholar
  3. [3]
    Bounds, D.G., Lloyd, P.J., and Mathew, B.G. (1990), “A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders,” Neural Networks, vol. 3, pp. 583–591.CrossRefGoogle Scholar
  4. [4]
    Bronzino, J.D. (1986), Biomedical Engineering and Instrumentation: Basic Concepts and Applications, PWS Engineering, Boston.Google Scholar
  5. [5]
    Chen, S., Cowan, C.F., and Grant, P.M. (1991), “Orthogonal least squares learning algorithm for radial basis function networks,” IEEE Trans. Neural Networks, vol. 2, pp. 302–309.CrossRefGoogle Scholar
  6. [6]
    Chen, S., Grant, P., and Cowan, C. (1992), “Orthogonal least squares algorithm for training multioutput radial basis function networks,” IEE Proceedings-F, vol. 139, no. 6, pp. 378–384.Google Scholar
  7. [7]
    Davis, M.H., Khotanzad, A., and Flamig, D.P. (1996), “3D image matching using a radial basis function neural network,” WCNN’96, World Congress on Neural Networks, International Neural Network 1996 Annual Meeting, San Diego, CA, USA, pp. 1174–1179.Google Scholar
  8. [8]
    Downes, P. (1994) “QRS complex recognition using nld and neural networks,” World Congress on Neural Networks, International Neural Network Society Annual Meeting, San Diego, CA, USA, vol. 1, pp. I-138–142.Google Scholar
  9. [9]
    Elo, P., Saarinen, J., Värri, A., Nieminen, H., and Kaski, K. (1992), “Classification of epileptic EEG by using self-organized maps,” in Aleksander, I. and Taylor, J. (Eds.), Artificial Neural Networks, 2nd ed, Proceedings of International Conference on Artificial Neural Networks (ICANN 92), Brighton, United Kingdom, Elsevier Science Publishers, pp. 1147–1150.Google Scholar
  10. [10]
    Fraser, H.S., Pugh, R., Kennedy, R.L., Ross, P., and Harrison, R.F. (1994) “A comparison of back propagation and radial basis functions, in the diagnosis of myocardial infarction,” Proceedings of the International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, Plymouth, UK, pp. 76–84.Google Scholar
  11. [11]
    Gori, M. and Scarselli, F. (1998), “Are multilayer perceptrons adequate for pattern recognition and verification?” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1121–1132.CrossRefGoogle Scholar
  12. [12]
    Gotman, J. (1986), “Computer analysis of the EEG in epilepsy,” in Lopes da Silva, F.H., Storm van Leeuven, W. and Rémond, A. (Eds.), Handbook of Electroencephalography and Clinical Neurophysiology, Volume 2, Clinical Applications of Computer Analysis of EEG and other Neurophysiological Signals Elsevier Science Publishers, Amsterdam, pp. 171–204.Google Scholar
  13. [13]
    Gotman, J. (1986), “Computer analysis during intensive monitoring of epileptic patients,” in Gumnit, R.J. (Ed.), Advances in Neurology, Vol. 46, Intensive Neurodiagnostic Monitoring Raven Press, New York, pp. 249–269.Google Scholar
  14. [14]
    Haykin, S. (1999), Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice Hall, New Jersey.MATHGoogle Scholar
  15. [15]
    Hojjatoleslami, A, Sardo, L., and Kittler, J. (1997) “An RBF based classifier for the detection of microcalcifications in mammograms with outlier rejection capability,” 1997 International Conference on Neural Networks, Proceedings, Houston, TX, USA, vol. 3, pp. 1379–1384.Google Scholar
  16. [16]
    Hornik, K. (1991), “Approximation capabilities of multilayer feed-forward networks,” Neural Networks, vol. 4, no. 2, pp. 251–257.CrossRefGoogle Scholar
  17. [17]
    Jemili, K., and Westerkamp, J.J. (1995) “A kernel based system for the estimation of nonstationary signals,” 1995 International Conference on Acoustics, Speech, and Signal Processing, Conference Proceedings, Detroit, MI, USA, Vol. 5, pp. 3423–3426.Google Scholar
  18. [18]
    Kirk, B.P., and LaCourse J.R. (1997) “Performance monitoring from the EEG power spectrum with a radial basis function network,” Proceedings of the IEEE 23rd Northeast Bioengineering Conference, Durham, NH, USA, pp. 19–20.Google Scholar
  19. [19]
    Kittler, J., Hojjatoleslami, A., and Windeatt, T. (1997) “Strategies for combining classifiers employing shared and distinct pattern representations,” Pattern Recognition Letters, Vol. 18, pp. 1373–1377.CrossRefGoogle Scholar
  20. [20]
    Kondraske, G.V. (1986), “Neurophysiological measurements,” in Bronzino, J.D. (Ed.) Biomedical Engineering and Instrumentation: Basic Concepts and Applications, PWS Engineering, Boston, pp. 138–179.Google Scholar
  21. [21]
    Kovacevic, D. and Loncaric, S. (1997) “Radial basis function-based image segmentation using a receptive field,” Proceedings, Tenth IEEE Symposium on Computer-Based Medical Systems, Maribor, Slovenia, pp. 126–130.Google Scholar
  22. [22]
    Krajca, V., Petranek, S., Patakova, I., and Värri, A. (1991), “Automatic identification of significant graphoelements in multichannel EEG recordings by adaptive segmentation and fuzzy clustering,” Int. J. Biomedical Computing, vol. 28, pp. 71–89.CrossRefGoogle Scholar
  23. [23]
    Lehtokangas, M., Saarinen, J., and Kaski, K. (1995), “Accelerating training of radial basis function networks with cascade-correlation algorithm,” Neurocomputing, vol. 9, pp. 207–213.CrossRefGoogle Scholar
  24. [24]
    Malmivuo, J. and Plonsey, R. (1995), Bioelectromagnetism: Principles and Applictions of Bioelectric and Biomagnetic Fields, Oxford University Press, New York.CrossRefGoogle Scholar
  25. [25]
    Moody, J. and Darken, C. (1989), “Fast learning in networks of locally-tuned processing units,” Neural Computation, vol. 1, pp. 281–294.CrossRefGoogle Scholar
  26. [26]
    Nisbet, K.C., McLaughlin, S., and Mulgrew, B. (1991), “Nonlinear time-series prediction,” Second International Conference on Artificial Neural Networks, Bournemouth, UK, pp. 354–358.Google Scholar
  27. [27]
    Park, J. and Sandberg, I. (1991), “Universal approximation using radial basis function networks,” Neural Computation, vol. 3, pp. 246–257.CrossRefGoogle Scholar
  28. [28]
    Pietilä, T., Vapaakoski, S., Nousiainen, U., Värri, A., Frey, H., Häkkinen, V., and Neuvo, Y. (1994), “Evaluation of a computerized system for recognition of epileptic activity during longterm EEG monitoring,” Electroencephalography and Clinical Neuro-physiology, vol. 90, pp. 438–443.CrossRefGoogle Scholar
  29. [29]
    Polycarpou, M.M. and Conway, J.Y. (1995) “Modeling and control of drug delivery systems using adaptive neural control methods,” Proceedings of the American Control Conference, Seattle, Washington, pp. 781–785.Google Scholar
  30. [30]
    Saastamoinen, A., Pietilä, T., Värri, A., Lehtokangas, M., and Saarinen J. (1998), “Waveform detection with RBF network — application to automated EEG analysis,” Neurocomputing, vol. 20, pp. 1–13.MATHCrossRefGoogle Scholar
  31. [31]
    Schlang, M., Haft, M., and Abraham-Fuchs, K. (1994) “Neural networks for reconstruction of focal events from bioelectric/biomagnetic potentials,” 1994 IEEE International Conference on Neural Networks, IEEE World Congress on Computational Intelligence, Orlando, FL, U.S.A., vol. 6, pp. 3467–3471.Google Scholar
  32. [32]
    Stamkopoulos, T., Maglaveras, N., Diamantaras, K., and Strintzis, M. (1997) “Ischemia classification techniques using an advanced neural network algorithm,” Computers in Cardiology 1997, Lund, Sweden, pp. 351–354.Google Scholar
  33. [33]
    Tou, J.T. and Gonzales, R.C., (1981), Pattern Recognition Principles, Addison-Wesley, London.Google Scholar
  34. [34]
    Trajanoski, Z. and Wach, P. (1997) “Evaluation of subcutaneous route for closed-loop control of insulin delivery: numerical and experimental studies,” 1995 IEEE Engineering in Medicine and Biology 17th Annual Conference and 21st Canadian Medical and Biological Engineering Conference, New York, NY, U.S.A., vol. 2, pp. 1357–1358.Google Scholar
  35. [35]
    Turner, K., Ramanujam, N., Ghosh, J., and Richards-Kortum, R. (1998) “Ensembles of radial basis function networks for spectroscopic detection of cervical pre-cancer,” IEEE Trans. Biomedical Engineering.Google Scholar
  36. [36]
    Vani, A., Hirvonen, K., Hasan, J., Loula, P., and Häkkinen, V., (1992), “A computerized analysis system for vigilance studies,” Computer Methods and Programs in Biomedicine, vol. 39, pp. 113–124.CrossRefGoogle Scholar
  37. [37]
    Värri, A., Kemp, B, Rosa, A.C., Nielsen, K.D., Gade, J., Penzel, T., Hasan, J., Hirvonen, K., Häkkinen, V., Kamphuizen, A.C., and Mourtazev, M.S. (1995), “Multi-centre comparison of five eye movement detection algorithms,” Journal of Sleep Research, vol. 4, pp. 119–130.CrossRefGoogle Scholar
  38. [38]
    Värri, A., Hirvonen, K., Häkkinen, V., Hasan, J., and Loula, P., (1996), “Nonlinear eye movement detection method for drowsiness studies, Int. J. Biomedical Computing, vol. 43, pp. 227–242.Google Scholar
  39. [39]
    Wu, J., Ifeachor, E.C., Allen, E.M., and Hudson, N.R. (1994), “A neural network based artefact detection system for EEG signal processing,” Proceedings of the International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, Plymouth, UK, pp. 257–266.Google Scholar
  40. [40]
    Zahlmann, G., Scherf, M., and Wegner, A. (1997) “A neuro-fuzzyclassifier for a knowledge-based glaucoma monitor,” Artificial Intelligence in Medicine, 6 th Conference on Artificial Intelligence in Medicine Europe, AIME ‘87, Proceedings, Grenoble, France, pp. 273–284.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • A. Saastamoinen
  • M. Lehtokangas
  • A. Värri
  • J. Saarinen

There are no affiliations available

Personalised recommendations