Uncertainty measures and hierarchical classification
The authors extend, and in some sense unify, two methods of hierarchical (or bottom-up) classification due to Aggarwal and to \textit{G. N. Lance} and \textit{W. T. Williams} [see Stat. Math. Digital Comput. 269--295 (1977; Zbl 0398.62050)]. The first one uses the Shannon entropy to measure how much information is lost in the aggregation procedure; the second one uses the same entropy to evaluate the similarity between two elements or between two groups of elements. For generalization, the authors use the Forte and Kampe de Feriet axiomatic theory in which a general definition of uncertainty measures is given. In this context the authors find conditions on the uncertainties which allow to construct the hierarchical classification procedure. For the entire collection see [Zbl 1051.68019].
- Fidelity Estimation for a Hierarchical Classifier
- scientific article; zbMATH DE number 4080657 (Why is no real title available?)
- scientific article; zbMATH DE number 5031271 (Why is no real title available?)
- Towards an axiomatic approach to hierarchical clustering of measures
- The uncertainty measure of hierarchical quotient space structure
This page was built for publication: Uncertainty measures and hierarchical classification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3157558)