Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Handling the description noise using an attribute value ontology

Treść / Zawartość
Warianty tytułu
Języki publikacji
The quality of any classifier depends on a number of factors, including the quality of training data. In real-world scenarios, data are often noisy. One reason for noisy data (erroneous values) is in the representation language, insufficient to model different levels of knowledge granularity. In this paper, to address the problem of such description noise, we propose a novel extension of the na've Bayesian classifier by an attribute value ontology (AVO). In the proposed approach, every attribute is a hierarchy of concepts from the domain knowledge base. In this way an example is described either very precisely (using a concept from the low-level of the hierarchy) or, when it is not possible, in a more general way (using a concept from higher levels of the hierarchy). Our general strategy is to classify a new example using training examples described in the same way or more precisely at lower levels of knowledge granularity. Hence, the hierarchy introduces a bias which in effect can contribute to improvement of a classification.
Opis fizyczny
Bibliogr. 17 poz., il.
  • Institute of Computing Science, Poznan University of Technology ul. Piotrowo 2, 60-965 Poznan, Poland
  • Almuallim H., Akiba, Y. and Kaneda, S. (1996) An Efficient Algorithm for Finding Optimal Gain-Ratio Multiple-Split Tests on Hierarchical Attributes in Decision Tree Learning. In: AAAI/IAAI, Vol. 1. AAAI press, 703-708.
  • Breiman, L., Friedman, J.H., Olshen,R.A. and Stone, C.J. (1984) Classification and Regression Trees. Wadsworth, Belmont, California.
  • Clark,P. and Niblett,T. (1987) Induction in Noisy Domains. In: Progress in Machine Learning (Proceedings of the 2nd European Working Session on Learning), Sigma Press, Bled, Yugoslavia, 11-30.
  • Han, J., Cai, Y. and Cercone, N. (1992) Knowledge Discovery in Databases: An Attribute-Oriented Approach. In: L.Y. Yuan, ed., VLDB, Morgan Kaufmann, 547-559.
  • Han, J. and Kamber, M. (2006) Data Mining: Concepts and Techniques, 2nd ed. Morgan Kaufmann.
  • Haussler, D. (1988) Quantifying Inductive Bias: AI Learning Algorithms and Valiant’s Learning Framework. Artif. Intell., 36(2), 177-221.
  • Hickey, R.J. (1996) Noise Modelling and Evaluating Learning from Examples. Artif. Intell., 82 (1-2), 157-179.
  • Kudoh, Y., Haraguchi, M. and Okubo, Y. (2003) Data abstractions for decision tree induction. Theor. Comput. Sci., 292(2), 387-416.
  • Núñez. M. (1991) The Use of Background Knowledge in Decision Tree Induction. Machine Learning, 6(3), 231-250.
  • Quinlan, J.R. (1986) Induction of Decision Trees. Machine Learning, 1(1), 81-106.
  • Tanaka, H. (1996) Decision Tree Learning Algorithm with Structured Attributes: Application to Verbal Case Frame Acquisition. In: COLING. Center for Sprogteknologi, Copenhagen, 943-948.
  • Taylor, M.G., Stoffel, K. and Hendler, J.A. (1997) Ontology-based Induction of High Level Classification Rules. In: Proceedings of the SIGMOD Dataming and Knowledge Discovery Workshop. ACM Press.
  • Walker, A. (1980) On Retrieval from a Small Version of a Large Data Base. In: VLDB, IEEE Computer Society, 47-54.
  • Wu, X. (1995) Knowledge Acquisition from Databases. Ablex Publishing Corp., Norwood.
  • Zhang, J., Kang, D., Silvescu, A. and Honavar, V. (2006) Learning accurate and concise naïve Bayes classifiers from attribute value taxonomies and data. Knowl. Inf. Syst., 9(2):157-179.
  • Zhang, J., Silvescu, A. and Honavar, V. (2002) Ontology-Driven Induction of Decision Trees at Multiple Levels of Abstraction. In: S. Koenig and R.C. Holte, eds., SARA, LNCS 2371, Springer, 316-323.
  • Zhu, X. and Wu, X. (2004) Class Noise vs. Attribute Noise: A Quantitative Study. Artif. Intell. Rev., 22(3), 177-210.
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.