IDENTIFICATION AND PREDICTION OF MULTIPLE SHORT RECORDS BY DYNAMIC BAYESIAN MIXTURES

Pavel Ettler, Miroslav Kárný

Abstract

A short data record is not suitable for proper identification of system model which is necessary for reliable data prediction. The idea consists in utilization of multiple similar short data records for identification of a dynamic Bayesian mixture. The mixture is used for prediction according to one of three methods described. Simulated and real data examples illustrate the methods.

References

  1. AndrÉsek, J. (2004). Approximate recursive Bayesian estimation of dynamic probabilistic mixtures. In AndrÉsek, J., KárnÉ, M., and Kracík, J., editors, Multiple Participant Decision Making, pages 39-54. Advanced Knowledge International, Magill, Adelaide.
  2. Haykin, S. (1994). Neural networks: A comprehensive foundation. Macmillan College Publishing Company, New York.
  3. KárnÉ, M., B öhm, J., Guy, T., Jirsa, L., Nagy, I., Nedoma, P., and Tesar?, L. (2005). Optimized Bayesian Dynamic Advising: Theory and Algorithms. Springer, London. to appear.
  4. Nedoma, P., B öhm, J., Guy, T. V., Jirsa, L., KárnÉ, M., Nagy, I., Tesar?, L., and Andr Ések, J. (2002). Mixtools: User's Guide. Technical Report 2060, ÝTIA AV C?R, Praha.
  5. Titterington, D., Smith, A., and Makov, U. (1985). Statistical Analysis of Finite Mixtures. John Wiley & Sons, Chichester, New York, Brisbane, Toronto, Singapore. ISBN 0 471 90763 4.
Download


Paper Citation


in Harvard Style

Ettler P. and Kárný M. (2005). IDENTIFICATION AND PREDICTION OF MULTIPLE SHORT RECORDS BY DYNAMIC BAYESIAN MIXTURES . In Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 972-8865-31-7, pages 66-70. DOI: 10.5220/0001175400660070


in Bibtex Style

@conference{icinco05,
author={Pavel Ettler and Miroslav Kárný},
title={IDENTIFICATION AND PREDICTION OF MULTIPLE SHORT RECORDS BY DYNAMIC BAYESIAN MIXTURES},
booktitle={Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2005},
pages={66-70},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001175400660070},
isbn={972-8865-31-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - IDENTIFICATION AND PREDICTION OF MULTIPLE SHORT RECORDS BY DYNAMIC BAYESIAN MIXTURES
SN - 972-8865-31-7
AU - Ettler P.
AU - Kárný M.
PY - 2005
SP - 66
EP - 70
DO - 10.5220/0001175400660070