Abstract
ARC II is a learning system that allows to discover relationships from symbolic data. The learning strategy is based on probabilistic induction and produces dependence relationships between a fact and a set of facts. The system also takes into account dated facts or events in order to produce causal relationships between an event (effect), and a set of facts (cause) including at least one event. Relationships are represented under the form of uncertain production rules. The algorithm ensures that (1) the rules are complete, i.e. that the premises include all known relevant facts and (2) the rules are elementary, i.e. no irrelevant fact belongs to the premises. ARC II has been applied to the analysis of medical data.
Keywords
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
D.I. Abrams, Acquired Immunodeficiency Syndrome and Related Malignancies: a Topical Overview, Seminar in Oncology, Vol 18, n∘ 5, pp 41–45, 1991
P. Clark, T. Niblett, The CN2 Induction Algorithm. Machine Learning 3: 261–283, 1989
J.S. Dover, Cutaneous Manifestations of Human Immunodeficiency Virus Infection. Part I, Archives of Dermatology, Vol 127, pp 1383–1391, 1991
R. S. Michalski, Y. Kodratoff, Research in Machine Learning: Recent Progress, Classification of Methods and Future Directions. Machine Learning: an Artificial Intelligence Approach, Vol III, pp 3–30, 1990
G. Pavillon, ARC II: Un Algorithme d'Apprentissage par Induction Probabiliste, Thèse de Doctorat, Paris VI, 1995
G. Piatestky-Shapiro, Discovery, Analysis, and Presentation of Strong Rules. Knowledge Discovery in Databases, AAAI Press/The MIT Press, 229–248, 1991
J.R. Quinlan, Induction of Decision Trees. Machine Learning 1, pp 81–106, 1986
P. Smyth, R.M. Goodman, Rule Induction Using Information Theory. Knowledge Discovery in Databases, AAAI Press/The MIT Press, 159–176, 1991
P. Suppes, “A Probabilistic Theory of Causality”, Acta Philosophica Fennica, Fasc XXIV, 1970
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pavillon, G. (1996). Knowledge discovery from epidemiological databases. In: Apers, P., Bouzeghoub, M., Gardarin, G. (eds) Advances in Database Technology — EDBT '96. EDBT 1996. Lecture Notes in Computer Science, vol 1057. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014153
Download citation
DOI: https://doi.org/10.1007/BFb0014153
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61057-1
Online ISBN: 978-3-540-49943-5
eBook Packages: Springer Book Archive