Dissimilarity measures for symbolic objects
In this paper it is assumed that we have given a set of symbolic objects represented by the rows of a symbolic data array \(\underline{X}=(\xi_{kj})_{N\times p}\). In order to exploit the power of classical data analysis, such as multidimensional scaling, clustering, factorial or discriminant analysis, the classical dissimilarity or similarity matrix is generated from the symbolic objects. It is shown how to determine a resemblance measure between pairs of symbolic objects. The described resemblance measures are based on dissimilarity measures proposed for Boolean symbolic objects by \textit{K.C. Gowda} and \textit{E. Diday} [Pattern Recognition 24, No. 6, 567-578 (1991)], \textit{M. Ichino} and \textit{H. Yaguchi} [IEEE Trans. Syst. Man Cybern. SMC-24, No. 4, 698-708 (1994)], \textit{F.A.T. De Carvalho} [C. Hayashi et al. (eds.), Studies in Classification, Data Analysis, and Knowledge Organization, 370-378 (1998; Zbl 0894.62006)]. For the entire collection see [Zbl 1039.62501].
- Multivalued type dissimilarity measure and concept of mutual dissimilarity value for clustering symbolic patterns
- Object similarity measures and Pawlak's indiscernibility on decision tables
- Metrics in symbolic data analysis
- Discrepancy Analysis of Complex Objects Using Dissimilarities
- scientific article; zbMATH DE number 1395880 (Why is no real title available?)
- scientific article; zbMATH DE number 5057721 (Why is no real title available?)
This page was built for publication: Dissimilarity measures for symbolic objects
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2756638)
