A set theoretic view of the ISA hierarchy

Abstract

The ISA (is-a) hierarchies are widely used in the classification and the representation of related objects. In terms of assessing similarity between two nodes, current distance approaches suffer from its nature that only parent-child relationships among nodes are captured in the hierarchy. This paper presents an idea of treating a hierarchy as a set rather than as a tree in the traditional view. The established set theory is applied to provide the foundation where the relations between nodes can be mathematically specified and results in a more powerful and logical assessment of similarity between nodes. © Springer-Verlag Berlin Heidelberg 2008.