Brain Electrographic State Detection Using Combined Unsupervised and Supervised Neural Networks

  • A. J. F. Coimbra
  • J. Marino-Neto
  • F. M. de Azevedo
  • C. G. Freitas
  • J. M. Barreto


This work describes the development of a new approach to NN processing of sleep-related brain electrographic signals, using two sequentially combined unsupervised (Kohonen layer, KNN) and supervised (Widrow-Hoff layer, WHNN) algorithms. Twelve parameters extracted from physiological data (EEG, EMG and EOG, obtained from unrestrained rats through several sleep-waking periods), were first processed by a KNN, that detected different signal patterns. These patterns were further examined by an EEG expert, who identified them as belonging to one of the known sleep-waking stages, or to transitional and/or unknown signal combinations. Selected outputs of the KNN, classified in this way, formed the input vectors to a WHNN, that allowed fast and reliable tracking of changes in these states (both known and newly detected) during prolonged periods of time. Such an approach can represent an important aid for simultaneous exploration, detection and also temporal following of electrographic events along the sleep-waking cycle.


Slow Wave Sleep Supervise Neural Network Kohonen Layer Kohonen Neural Network Reliable Tracking 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    I. N. Bankman, V. G. Sigillito, R. A. Wise, and P. L. Smith. Feature-based detection of the k-complex wave in the human electroencephalogram using neural networks. IEEE Transactions on Biomedical Engineering, 39 (12): 1305–1310, 1992.CrossRefGoogle Scholar
  2. [2]
    M. A. Carskadon and W. C. Dement. Normal human sleep: an overview. In M.H. Kryger, editor, Principles and Practice of Sleep Medicine, pages 3–13. Saunders, New York, 1988.Google Scholar
  3. [3]
    A. J. F. Coimbra. Análise computadorizada de sinais bioelétricos. Master’s thesis, Center of Technology, Federal University of Santa Catarina, Brazil, 1994.Google Scholar
  4. [4]
    A. J. F. Coimbra. Automatic detection of sleep-waking states using Kohonen neural networks. In 1 Congresso tìrasileiro de Redes Neurais, pages 327–331, Itajubá, Minas Gérais, Brasil, 1994.Google Scholar
  5. [5]
    A. J. F. Coimbra. Electrographic analysis of brain states using neural networks. In World Congress on Medical Physics and Biomedial Engineering, page 463, Rio de Janeiro, Brasil, 1994.Google Scholar
  6. [6]
    F. M. de Azevedo. Contribution to the study of neural networks in dynamical expert systems. PhD thesis, Institut d’ Informatique, F UN DP, Belgium, 1993.Google Scholar
  7. [7]
    R. O. Garcia. Técnicas de. inteligencia artificial aplicadas ao apoio à decisáo médica na especialidade de anestesiología. PhD thesis, Center of Technology, Federal University of Santa Catarina, Brazil, 1992.Google Scholar
  8. [8]
    B. Klöppel. Application of neural networks for eeg analysis. Neuropsychobiology, 29: 39–46, 1994.CrossRefGoogle Scholar
  9. [9]
    B. Klöppel. Classification by neural networks of evoked potentials. Neuropsychobiology, 29: 47–52, 1994.CrossRefGoogle Scholar
  10. [10]
    T. Kohonen. Seif-Organization and Associative Memory. Springer-Verlag, Berlin, 1984.Google Scholar
  11. [11]
    A. N. Mamelak, J. J. Quattrochi, and A. Hobson. Automated staging of sleep in cats using neural networks. Electroencephalography and Clinical Neurophysiology, 79: 52–61, 1991.CrossRefGoogle Scholar
  12. [12]
    R. Reimäo. Sono: Aspectos atuais. Neurològica, Psiquiatria. Atheneu, Sao Paulo, 1990.Google Scholar
  13. [13]
    S. Roberts and L. Tarassenko. New method of automated sleep quantification. Medical & Biological Engineering & Computing, 30: 509–517, 1992.CrossRefGoogle Scholar
  14. [14]
    N. Schaltenbrand, R. Lengelle, and J.-P. Macher. Neural networks model: Application to automatic analysis of human sleep. Computers and Biomedical Research, 26: 157–171, 1993.CrossRefGoogle Scholar
  15. [15]
    M. Timsit-Berthier. Approche neurophysiologique des états dépressifs. Psychologie Medicale, 22 (8): 757–763, 1990.Google Scholar
  16. [16]
    F. Y. Wu and J. D. Slater. Regional cerebral blood flow estimation by neural network-based parametric regression analysis. Int. Journal of Biomedical Computation, 33: 119–128, 1993.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • A. J. F. Coimbra
    • 1
  • J. Marino-Neto
    • 2
  • F. M. de Azevedo
    • 3
  • C. G. Freitas
    • 2
  • J. M. Barreto
    • 3
  1. 1.Lab. of NeurophysiologyUniversité Catholique de LouvainBelgium
  2. 2.Lab. de Neurofisiologia I, CFS-CCBUniversidade Federal de Santa CatarinaBrazil
  3. 3.GPEB, Dept. Electrical Eng.Universidade Federal de Santa CatarinaBrazil

Personalised recommendations