Advertisement

A Method for Temporal Knowledge Conversion

  • Gabriela Guimarães
  • Alfred Ultsch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1642)

Abstract

In this paper we present a new method for temporal knowledge conversion, called TCon. The main aim of our approach is to perform a transition, i.e. conversion, of temporal complex patterns in multivariate time series to a linguistic, for human beings understandable description of the patterns. The main idea for the detection of those complex patterns lies in breaking down a highly structured and complex problem into several subtasks. Therefore, several abstraction levels have been introduced where at each level temporal complex patterns are detected successively using exploratory methods, namely unsupervised neural networks together with special visualization techniques. At each level, temporal grammatical rules are extracted. The method TCon was applied to a problem from medicine, sleep apnea. It is a hard problem since quite different patterns may occur, even for the same patient, as well as the duration of each pattern may differ strongly. Altogether, all patterns have been detected and a meaningful description of the patterns was generated. Even some kind of “new” knowledge was found.

Keywords

Sleep Apnea Abstraction Level Multivariate Time Series Exploratory Method Grammatical Rule 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bezdek, J. C.: Hybrid modeling in pattern recognition and control. In: Knowledge-Based Systems, Vol. 8, Number 6, Elsevier Science Publisher (1995) 359–371CrossRefMathSciNetGoogle Scholar
  2. 2.
    Bishop, C. M.: Neural Networks for Pattern Recognition. Oxford, Clarendon Press, (1995)Google Scholar
  3. 3.
    Goonatilake, S., Khebal, S. (Eds.): Intelligent Hybrid Systems, Wiley & Sons, New York (1995)Google Scholar
  4. 4.
    Guimarães, G.: Eine Methode zur Entdeckung von komplexen Mustern in Zeitreihen mit Neuronalen Netzen and deren Überführung in eine symbolische Wissenrepr äsentation. PhD Dissertation, Philipps University of Marburg, Marburg, Germany (1998)Google Scholar
  5. 5.
    Juhola, M: A syntactic Analysis Method for Sinusoidal Tracking Eye Movements. In: Computers and Biomedical Research 24 (1991) 222–233CrossRefGoogle Scholar
  6. 6.
    Kaski, S., Kohonen, T.: Exploratory Data Analysis by Self-Organizing Map: Structures of Welfare and Poverty in the World. In: Refenes, A. P. N., Abu-Mostafa, Y., Moody, J., Weigend, A.: Neural Networks in Financial Engineering. Proc. of the Intl. Conf. on Neural Networks in the Capital Markets, London, England, 11-13 October, 1995, Singapore, (1996) 498–507Google Scholar
  7. 7.
    Kohonen, T.: Self-Organizing Maps, Springer Verlag, New York (1995)Google Scholar
  8. 8.
    Kohonen, T.: Self-Organization and Associative Memory. Springer Series in Information Sciences 8, Springer Verlag, New York (1984)Google Scholar
  9. 9.
    Koski, A., Juhola, M., Meriste, M.: Syntactic recognition of ECG signals by attributed finite automata. In: Pattern Recognition, The Journal of the Pattern Recognition Society, Vol. 28, Issue 12, December (1995) 292–297Google Scholar
  10. 10.
    Palm, G., Ultsch, A., Goser, K., Rückert, U.: Knowledge Processing in Neural Architecture. In: VLSI for Neural Networks and Artificial Intelligence, New York (1994) 207–216Google Scholar
  11. 11.
    Penzel, T.: Zur Pathophysiologie der Interaktion von Schlaf, Atmung und Kreislauf-Konzepte der Kardiorespiratorischen Polysomnographie. Habilitationsschrift, Philipps Universität Marburg (1995)Google Scholar
  12. 12.
    Penzel, T., Peter, J. H.: Design of an Ambulatory Sleep Apnea Recorder. In: Nagle, H. T., Tompkins, W. J. (Eds.): Case Studies in Medical Instrument Design, IEEE, New York (1992) 171–179Google Scholar
  13. 13.
    Schweizer, M., Föhn, P., Schweizer, J., Ultsch, A.: A Hybrid Expert System for Avalanche Forecasting. In: Schertler, W., Schmid, B., Tjoa, A. M., Werther, H. Eds.) Informations and Communications Technologies in Tourism, Springer Verlag, Wien (1994) 148–153Google Scholar
  14. 14.
    Ultsch, A., Kleine, T.O, Korus, D., Farsch, S., Guimarães, G.: Pietzuch, w., Simon, J.: Evaluation of Automatic and Manual Knowledge Acquisition for Cerebrospinal Fluid (CSF). In: Keravnu, E. et al. (Eds.): Artificial Intelligence in Medicine, Lecture Notes in Artificial Intelligence 1211, Vol. 934, Springer Verlag (1997) 110–121Google Scholar
  15. 15.
    Ultsch, A., Korus, D., Wehrmann, A.: Neural Networks and their Rules Classification in Marine Geology. In: Raum und Zeit in Umweltinformationssystemen, 9th Intl Symposium on Computer Science for Environmental Protection CSEP’95, Vol. I, GI-Fachausschuff 4.6 “Informatik im Umweltschutz”, Band 7, Metropolis-Verlag, Marburg (1995) 676–693Google Scholar
  16. 16.
    Ultsch, A.: The Integration of Neural Networks with Symbolic Knowledge Processing. In: Diday et al. (Eds.): New Approaches in Classification and Data Analysis, Springer (1994) 445–454Google Scholar
  17. 17.
    Ultsch, A.: Knowledge Extraction from Self-organizing Neural Networks, in O. Opitz, B. Lausen and R. Klar, (Eds.) Information and Classification, Berlin: Springer Verlag (1993) 301–306Google Scholar
  18. 18.
    Ultsch, A.: Self-Organizing Neural Networks for Visualization and Classification. In: Proc. Conf. Soc. Information and Classification, Dortmund, April (1992)Google Scholar
  19. 19.
    Ultsch, A.: Konnektionistische Modelle und ihre Integration mit wissensbasierten Systemen. Forschungsbericht Nr. 396, Institut für Informatik, Universität Dortmund, Februar, Dortmund, Habilitationsschrift (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Gabriela Guimarães
    • 1
  • Alfred Ultsch
    • 2
  1. 1.2825-214 Caparica and Department of Mathematics, Universidade de ÉvoraCENTRIA, U. Nova de LisboaPortugal
  2. 2.Department of Mathematics and Computer SciencePhilipps University of MarburgMarburgGermany

Personalised recommendations