Citation:
Abstract:
We present our experience in visualization multivariate data when the data vectors have class assignment. The goal is then to visualize the data in such a way that data vectors belonging to different classes (subgroups) appear differentiated as much as possible. We consider for this purpose the traditional CDA (Canonical Discriminant Functions), the GDA (Generalized Discriminant Analysis, Baudat and Anouar, 2000) and the Supervised SOM (Kohonen, Makivasara, Saramaki 1984). The methods are applied to a set of 3-dimensional erosion data containing N=3420 data vectors subdivided into 5 classes of erosion risk. By performing the mapping of these data to a plane, we hope to gain some experience how the mentioned methods work in practice and what kind of visualization is obtained. The final conclusion is that the traditional CDA is the best both in speed (time) of the calculations and in the ability of generalization.