MULTIDIMENSIONAL DATA PROJECTION ALGORITHMS SAVING CALCULATIONS OF DISTANCES

Abstract

In this paper, the triangulation method, the classic algorithm for Sammon’s projection and the combi-nation of Sammon’s algorithm with the triangulation method are examined for mapping new points in detail. A new realization of the combination of Sammon’s algorithm and the triangulation method is proposed. These algorithms are analyzed and compared in the following respects: visual evaluation of data projection, evaluation of data mapping time and evaluation of projection error.