NONPARAMETRIC ALGORITHM OF AUTOMATIC CLASSIFICATION OF STATISTICAL DATA
Institute of Computational Modeling, Siberian Branch of RAS; Professor
V. A. Lapko
M. F. Reshetnev Siberian State Aerospace University, Department of Space Resources and Technologies; Professor
A. N. Khlopov
M. F. Reshetnev Siberian State Aerospace University, Department of Space Resources and Technologies; Post-Graduate Student
Abstract. A nonparametric algorithm of automatic classification of statistical data is proposed. The algorithm is based on probability density estimations of Parzen type. Application of the algorithm allows for selection of compact point sets corresponding to unimodal fragments of the probability density.
Keywords: nonparametric statistics, automatic classification, pattern recognition, probability density.