DISCOVERING N-ARY TIMED RELATIONS FROM SEQUENCES

Nabil Benayadi, Marc Le Goc

Abstract

The goal of this position paper is to show the problems with most used timed data mining techniques for discovering temporal knowledge from a set of timed messages sequences. We will present from a simple example that Apriori-like algorithms for mining sequences as Minepi and Winepi fail for mining a simple sequence generated by a very simple process. Consequently, they cannot be applied to mine sequences generated by complexes process as blast furnace process. We will show also that another technique called TOM4L(Timed Observations Mining for Learning) can be used for mining such sequences and generate significantly better results than produced by Apriori-like techniques. The results obtained with an application on very complex real world system is presented to show the operational character of the TOM4L.

References

  1. Benayadi, N. and Goc, M. L. (2008). Discovering temporal knowledge from a crisscross of timed observations. In The proceedings of the 18th European Conference on Artificial Intelligence (ECAI'08), University of Patras, Patras, Greece.
  2. Benayadi, N. and Le Goc, M. (2008). Using a measure of the crisscross of series of timed observations to discover timed knowledge. Proceedings of the 19th International Workshop on Principles of Diagnosis (DX'08).
  3. Bouché, P. (2005). Une approche stochastique de modélisation de séquences d'événements discrets pour le diagnostic des systèmes dynamiques. These, Faculté des Sciences et Techniques de Saint Jéroˆme.
  4. Le Goc, M. (2006). Notion d'observation pour le diagnostic des processus dynamiques: Application à Sachem et à la découverte de connaissances temporelles. Hdr, Faculté des Sciences et Techniques de Saint Jéroˆme.
  5. Mannila, H. (2002). Local and global methods in data mining: Basic techniques and open problems. 29th International Colloquium on Automata, Languages and Programming.
  6. Mannila, H., Toivonen, H., and Verkamo, A. I. (1997). Discovery of frequent episodes in event sequences. Data Mining and Knowledge Discovery, 1(3):259-289.
  7. Roddick, F. J. and Spiliopoulou, M. (2002). A survey of temporal knowledge discovery paradigms and methods. IEEE Transactions on Knowledge and Data Engineering, (14):750-767.
Download


Paper Citation


in Harvard Style

Benayadi N. and Le Goc M. (2010). DISCOVERING N-ARY TIMED RELATIONS FROM SEQUENCES . In Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-674-021-4, pages 428-433. DOI: 10.5220/0002762304280433


in Bibtex Style

@conference{icaart10,
author={Nabil Benayadi and Marc Le Goc},
title={DISCOVERING N-ARY TIMED RELATIONS FROM SEQUENCES},
booktitle={Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2010},
pages={428-433},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002762304280433},
isbn={978-989-674-021-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - DISCOVERING N-ARY TIMED RELATIONS FROM SEQUENCES
SN - 978-989-674-021-4
AU - Benayadi N.
AU - Le Goc M.
PY - 2010
SP - 428
EP - 433
DO - 10.5220/0002762304280433