Classification and Data Analysis in Vector Spaces

  • B. G. Batchelor


Here, as in Chapters 3 and 5, we shall primarily be concerned with methods for making decisions. We shall assume that the primary pattern has already been coded to yield a vector containing numeric descriptors. Such a pattern description is natural in a wide variety of applications, as the following examples show:
  1. 1.

    An autoanalyzer* may be used to define a multielement vector which describes the hormone, protein, salt, and sugar concentrations in human blood.

  2. 2.

    A time-varying signal, such as an EEG or ECG, may be applied to a set of parallel band-pass filters whose outputs are rectified and then integrated. The outputs from the integrators represent the elements of the measurement vector.

  3. 3.

    The color of vegetation, as seen from a satellite, may be used to identify certain crops. A “color” vector might contain three measurements on components from the visible spectrum, as well as ultraviolet or infrared measurements.



Vector Space Probability Density Function Measurement Vector Pattern Classification Linear Classifier 
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. Anderson, G. D., 1969, Comparison of Methods of Estimating a Probability Density Function, Ph.D Thesis, University of Washington, Seattle, Wash.Google Scholar
  2. Batchelor, B. G., 1968, Learning Machines for Pattern Recognition, Ph.D Thesis, University of Southampton, Southampton, England.Google Scholar
  3. Batchelor, B. G., 1971, Improved distance measure for pattern recognition,Electron. Lett., 7: 521.CrossRefGoogle Scholar
  4. Batchelor, B. G., 1973a, Growing and Pruning a Pattern Classifier, Inform. Sci. 6: 97.CrossRefGoogle Scholar
  5. Batchelor, B. G., 1973b, Instability of the decision surfaces of the nearest-neighbour and potential function classifiers, Inform. Sci. 5: 179.CrossRefGoogle Scholar
  6. Batchelor, B. G., 1974a, Practical Approach to Pattern Classification, Plenum Press, London and New York.Google Scholar
  7. Batchelor, B. G., 1974b, Design for a high-speed euclidean distance calculator and its use in pattern recognition, Proc. Conf. Computer Systems Technol., IEE Conf. Publ. 121: 213.Google Scholar
  8. Batchelor, B. G., and Hand, D. J., 1975, On the graphical analysis of PDF estimators for pattern recognition, Kybernetes 4: 239.CrossRefGoogle Scholar
  9. Batchelor, B. G., and Wilkins, B. R., 1968, Adaptive discriminant functions. In: Pattern Recognition, IEE Conf. Publ. 42: 168.Google Scholar
  10. Batchelor, B. G., and Wilkins, B. R., 1969, Method for location of clusters of patterns to initialise a learning machine, Electron. Lett. 5: 481.CrossRefGoogle Scholar
  11. Cover, T. M., and Hart, P. E., 1967, Nearest neighbor pattern classification, Trans. IEEE IT-13: 21.Google Scholar
  12. Everitt, B., 1974, Cluster Analysis, Heinemann, London.Google Scholar
  13. Ford, N. L., 1974, Pattern Classification and the Analysis of Training Sets, Ph.D. Thesis, University of Southampton, Southampton, England.Google Scholar
  14. Ford, N. L., Batchelor, B. G., and Wilkins, B. R., 1970, Learning scheme for the nearest neighbour classifier, Inform. Sci. 2: 139.CrossRefGoogle Scholar
  15. Fukunaga, K., 1972, An Introduction to Statistical Pattern Recognition, Academic Press, New York.Google Scholar
  16. Hand, D. J., and Batchelor, B. G., 1974, A preliminary note on pattern classification using incomplete vectors, Proc. 2nd Int. Joint Conf. Pattern Recognition, p. 15.Google Scholar
  17. Hand, D. J., and Batchelor, B. G., 1975, Classification of incomplete pattern vectors using orthogonal function methods, Proc. 3rd Int. Conf. on Cybernetics and Systems, Bucharest, Rumania.Google Scholar
  18. Hart, P. E., 1968, Condensed nearest neighbour rule, Trans. IEEE IT-14: 515.Google Scholar
  19. Hellerman, H., 1967, Digital Computer System Principles, McGraw-Hill, New York.Google Scholar
  20. Iverson, K., 1962, A Programming Language, Wiley, New York.Google Scholar
  21. Jardine, N., and Sibson, R., 1971, Mathematical Taxonomy, Wiley, New York.Google Scholar
  22. Katzan, H., 1970, APL Programming and Computer Techniques, Van Nostrand-Reinhold, New York.Google Scholar
  23. Lewin, D. W., 1972, Theory and Design of Digital Computers, Nelson, London.Google Scholar
  24. Lill, B., and Redstone, L., 1968, A study of learning and recognition algorithms, IEE Conf. Publ. 42.Google Scholar
  25. Martin, J., 1973, Design of Man-Computer Dialogues, Prentice-Hall, Englewood-Cliffs, N.J.Google Scholar
  26. Mattson, A. L., and Damman, J. E., 1965, A technique for determining and coding subclasses in pattern recognition problems, IBM J. 9: 4.CrossRefGoogle Scholar
  27. Miller, G. A., 1967, Psychology of Communication, Penguin, Harmondsworth, U.K.Google Scholar
  28. Mucciardi, A. N., and Gose, E. E., 1971, Comparison of seven techniques for choosing subsets of pattern recognition properties, Trans. IEEE C-20: 1023.Google Scholar
  29. Mucciardi, A. N., and Gose, E. E., 1972, An automatic clustering algorithm and its properties in high dimensional spaces, Trans. IEEE SMC-2: 247.Google Scholar
  30. Nilsson, N. J., 1965, Learning Machines, McGraw-Hill, New York.Google Scholar
  31. Patrick, E. A., 1972, Fundamentals of Pattern Recognition, Prentice-Hall, Englewood-Cliffs, N.J.Google Scholar
  32. Rosenfeld, A., and Pfaltz, J. L., 1968, Distance functions on digital pictures, Pattern Recognition 1: 33.CrossRefGoogle Scholar
  33. Sammon, J. W., 1969, Non-linear mapping for data structure analysis, Trans. IEEE C-18: 401.Google Scholar
  34. Sebestyen, G. S., 1962, Decision-Making Processes in Pattern Recognition, Macmillan, New York.Google Scholar
  35. Sebestyen, G. S., and Edie, J., 1966, An algorithm for non-parametric pattern recognition, Trans. IEEE EC-15: 908.Google Scholar
  36. Sokal, R. R., and Sneath, P. H. A., 1963, Principles of Numerical Taxonomy, Freeman, San Francisco.Google Scholar
  37. Wilkins, B. R., and Batchelor, B. G., 1970, Evolution of a descriptor set for pattern recognition, Proc. Conf. Technical Biol. Probl. Control, Instrument Society of America, p. 794.Google Scholar
  38. Wilkins, B. R., and Ford, N. L., 1972, Analysis of training sets for adaptive pattern recognition. In Machine Perception of Patterns and Pictures, Inst. Physics, Conf. Ser. 13: 267.Google Scholar
  39. Wolfe, J. H., 1967, Normix: Computational Methods for Estimating the Parameters of a Multivariate Normal Mixture of Distributions. (Research Memo SRM 68-2), U.S. Naval Personnel Research Activity, San Diego, Calif. (Defense Documentation Center Ad 656 588).Google Scholar
  40. Wolfe, J. H., 1970, Pattern clustering by multivariate mixture analysis, Multivariate Behav. Res., 5: 329.CrossRefGoogle Scholar

Copyright information

© Plenum Press, New York 1978

Authors and Affiliations

  • B. G. Batchelor
    • 1
  1. 1.Department of ElectronicsUniversity of SouthamptonSouthamptonEngland

Personalised recommendations