Knowledge Management System: Combination of Experts’ Knowledge and Automatic Improvement
This paper proposes a knowledge management system that acquires knowledge from time series data by using users background knowledge. To obtain if-then rules as knowledge, we apply decision tree learning. However usual methods of decision tree learning targets discrete value data, thus a new approach is needed for dealing with this type of data. Experts forecast future events by using their knowledge. They, in typical cases, focus on a set of useful patterns and then apply knowledge relevant to them. We apply this idea into the framework of decision tree learning. We prepare a set of patterns, which is called clues, and then express time series data in terms of the clues. Thus the clues are attributes by which features of data are described. In addition, to make a better prediction with the learning process, we develop a mechanism that improves the quality of the clues. The essential idea of the mechanism is based on a genetic algorithm. The clue is evaluated by using entropy of information theory, and is improved by GA operators. We can obtain new knowledge from improved clues and the extracted decision tree. This paper details the system and results of the experiment.
KeywordsTime Series Data Dynamic Time Warping Future Behavior Roulette Wheel Selection Knowledge Management System
Unable to display preview. Download preview PDF.
- 1.Dong, G., Pei, J.: Sequence Data Mining. Springer (2007)Google Scholar
- 2.Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Pub. (2005)Google Scholar
- 4.Kubota, K., Nakase, A., Sakai, H., Oyanagi, S.: Parallelization of decision tree algorithm and its performance evaluation. IPSJ SIG. Notes 99(66), 161–166 (1999)Google Scholar
- 5.Yamada, Y., Suzuki, E., Yokoi, H., Takabayashi, K.: Decision-tree induction from time-series data based on a standard-example split test. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML), pp. 840–847 (2003)Google Scholar
- 6.Abe, H., Hirabayashi, S., Ohsaki, M., Yamaguchi, T.: Evaluating a trading rule mining method based on temporal pattern extraction. In: The Third International Workshop on Mining Complex Data (MCD 2007) In Conjunction with ECML/PKDD 2007, pp. 49–58 (2007)Google Scholar
- 9.Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)Google Scholar
- 10.Cha, S.-H., Tappert, C.: A genetic algorithm for constructing compact binary decision trees. Journal of Pattern Recognition Research (JPRR) 4(1), 1–13 (2009)Google Scholar
- 11.Berndt, D.J., Clifford, J.: Using Dynamic Time Warping to Find Patterns in Time Series. In: Proceedings of KDD 1994: AAAI Workshop on Knowledge Discovery in Databases, Seattle, Washington, pp. 359–370 (July 1994)Google Scholar
- 12.Ross Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers (1993)Google Scholar
- 13.The University of Waikato, Machine learning project at the university of waikato in new zealand, http://www.cs.waikato.ac.nz/ml/
- 14.NESDIS-National Environmental Satellite, Data, and Information Service, Nndc climate data online, http://www.nesdis.noaa.gov/