2014 | OriginalPaper | Buchkapitel
Mining Incomplete Data with Attribute-Concept Values and “Do Not Care” Conditions
verfasst von : Patrick G. Clark, Jerzy W. Grzymala-Busse
Erschienen in: Hybrid Artificial Intelligence Systems
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this paper we present novel experimental results on comparing two interpretations of missing attribute values: attribute-concept values and “do not care” conditions. Experiments were conducted on 176 data sets, with preprocessing using three kinds of probabilistic approximations (lower, middle and upper) and the MLEM2 rule induction system. The performance was evaluated using the error rate computed by ten-fold cross validation. At 5% statistical significance level, in four cases attribute-concept values and in two cases “do not care” conditions performed better (out of 24 cases). At 10% statistical significance level, in five cases attribute-concept values and in three cases “do not care” conditions performed better. In the remaining cases the differences were not statistically significant.