Lazy Classification Algorithms Based on Deterministic and Inhibitory Decision Rules

Part of the Studies in Computational Intelligence book series (SCI, volume 163)


In this chapter, we consider the same classification problem as in Chaps. 5 and 6: for a given decision table T and a new object v it is required to generate a value of the decision attribute on v using values of conditional attributes on v.

We compare two lazy [1] classification algorithms based on deterministic and inhibitory decision rules of the forms
$$ (a_1(x)=b_1)\wedge \ldots \wedge (a_t(x)=b_t)\rightarrow d(x)=b \; , $$
$$ (a_1(x)=b_1)\wedge \ldots \wedge (a_t(x)=b_t)\rightarrow d(x)\neq b $$
respectively, where a1,...,a t are conditional attributes, b1,...,b t are values of these attributes, d is the decision attribute and b is a value of d. By Dec(T) we denote the set of values of the decision attribute d.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  1. 1.University of RzeszowPoland
  2. 2.University of Silesia, SosnowiecPoland
  3. 3.Warsaw University, WarsawPoland

Personalised recommendations