Classifying Spinal Measurements Using a Radial Basis Function Network

  • S. J. Langdell
  • J. C. Mason
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

Injuries to the lumbar region of industrial workers’ spines are relatively commonplace, due, for example, to over-exposure to vibrating machinery and inadequate provisions for heavy lifting. In contrast with earlier decades, management is much more likely to be sued in a court of law if an employee suspects bad management practice. Whereas severe damage to an individual’s lumbar region is usually apparent, typically because of immobility, less severe damage is harder to detect. In such cases a court of law calls for an expert witness to gauge the extent of the damage that an employment environment may inflict on an individual’s spine.

Keywords

Europe 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Burton, K., and Tillotson, M. Quantification of overload injuries of thoracolumbular vertebrae in persons exposed to heavy physical exertions or vibrations in the workplace. European Coal and Steel Community, Fifth Medical Programme, 1993.Google Scholar
  2. [2]
    Burton, K., Tillotson, M., Biggermann, M., Brinckmann, P., and Frobin F. Quantification of overload injuries of thoracolumbular vertebrae in persons exposed to heavy physical exertions or vibrations in the workplace Part II: Occurrence and magnitude of overload injury in exposed cohorts. Clinical Biomechanics 13, 1998.Google Scholar
  3. [3]
    Spinal Research Unit, University of Huddersfield, Cross Church Street, Huddersfield, England.Google Scholar
  4. [4]
    Franke, R. Scattered data interpolation: Tests of some methods. Math. Comp., 38:181–200, 1982.MathSciNetMATHGoogle Scholar
  5. [5]
    Powell, M. J. D. Radial basis functions in 1990. Advances in Numerical Analysis Volume II, Cox. and Mason (Eds.), Oxford University Press. 105–210, 1991.Google Scholar
  6. [6]
    Dyn, N. Interpolation of scattered data by radial functions. Topics in Multivariate Approximation, Schumaker, Chui and Utreras (Eds.), Academic Press, New York, 1997, pp. 47–61.Google Scholar
  7. [7]
    Light, W. Some aspects of radial basis function approximation. NATO ISI Series, 256:163–190, 1992.MathSciNetGoogle Scholar
  8. [8]
    Kohonen, T. Self Organisation and Associative Memory, 3 Edition Springer-Verlag, 1989.CrossRefGoogle Scholar
  9. [9]
    Hinton, G. E. Learning translation invariant recognition in massively parallel networks. Proceedings of PARLE conference on Parallel Architectures and Languages in Europe (1987), Springer-Verlag, pp. 1–13.CrossRefGoogle Scholar
  10. [10]
    Golub, G., and Kahan, W. Calculating the singular values and pseudo inverse of a matrix. SIAM Numerical Analysis B2. 2:202–204, 1965.MathSciNetGoogle Scholar
  11. [11]
    Mackay, D. J. C. A practical Bayesian framework for backpropagation networks. Neural Computation 4, 3:448–472, 1992.CrossRefGoogle Scholar
  12. [12]
    Langdell, S. J. Radial basis function networks for modelling real world data. Ph.D. thesis, University of Huddersfield, 1998.Google Scholar
  13. [13]
    Bishop, C. M. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1996.MATHGoogle Scholar
  14. [14]
    Orr, M. J. L. Regularisation in the selection of radial basis function centres. Neural Computation 7. 3:606–623, 1995.CrossRefGoogle Scholar
  15. [15]
    Friedman, J. H. Flexible metric nearest neighbour classification. Technical Report, Stanford University, 1994.Google Scholar
  16. [16]
    White H. Learning in neural networks: A statistical perspective. Neural Computation 1. 4:425–464, 1989.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • S. J. Langdell
    • 1
  • J. C. Mason
    • 1
  1. 1.Department of Mathematics and StatisticsUniversity of HuddersfieldQueensgateUK

Personalised recommendations