THE ULTRAMETRIC PROPERTIES OF BINARY DATASETS
Journal Title: Silesian Journal of Pure and Applied Mathematics - Year 2016, Vol 6, Issue 1
Abstract
Many multivariate algorithms commonly applied for binary datasets depend on a proper metric (i.e., dissimilarity function) imposed on binary vectors. In the following work the relationships between different metrics defined on the randomly generated binary datasets and the cophenetic correlation coefficient (CCC) will be presented.
Authors and Affiliations
Piotr Wilczek
CHARACTERISTICS AND DECOMPOSITION OF EXPRESSIONS IN THE PF-NOTATION
The paper presents a selected aspects of classical parenthesis-free notation. With the introduction of the concepts of the pattern of expression and the characteristics were obtained convenient tools for classification a...
THE MODES OF A MIXTURE OF TWO NORMAL DISTRIBUTIONS
Mixture distributions arise naturally where a statistical population contains two or more subpopulations. Finite mixture distributions refer to composite distributions constructed by mixing a number K of component distri...
BASIC SUMS AS PARAMETERS CHARACTERIZING
We discuss the method of distributions’ characterization of geometric objects on the plane. The method is based on the basic sums. These basic sums perform the same role in description of image as the n-point correlation...
THE METHOD OF FINDING POINTS OF INTERSECTION OF TWO CUBIC BEZIER CURVES USING THE SYLVESTER MATRIX
Sylvester matrix is used to create a 9th degree polynomial from coefficients of two cubic Bezier curves. The real roots of this polynomial allow to compute points of intersection of aforementioned curves. An additional c...
IMPLICIT FINITE DIFFERENCE METHOD FOR THE SPACE FRACTIONAL HEAT CONDUCTION EQUATION WITH THE MIXED BOUNDARY CONDITION
This paper presents the numerical solution of the space fractional heat conduction equation with Neumann and Robin boundary conditions. In described equation the Riemann-Liouville fractional derivative is used. Considere...