Abstract. The author develops and investigates the depth-based classification method based on remote concentration measure for asymmetric data processing. The motivation for the construction of the method was inefficient use of affine invariant classifiers in combination with depth functions, which vanish outside the convex hull. The idea of the proposed method is to map a remote space using a remote concentration measure, Stahel–Donoho remoteness measure, and adjusted remoteness measure.
Keywords: depth function, remote concentration measure, multi-dimensional classification.
Галкин Александр Анатольевич,
кандидат физ.-мат. наук, ассистент кафедры Киевского национального университета
имени Тараса Шевченко,
e-mail: galkin.o.a@gmail.com.