Supervised Nonparametric Classification in the Context of Replicated Point Patterns

Abstract

A spatial point pattern is a collection of points in space, representing, e.g. observed locations of trees, bird nests, centers of cells in a histological sample, etc. When several independent realizations of the underlying stochastic process are observed, these realizations are referred to as replicated point patterns. The main objective of this paper is to classify a newly observed pattern into one of the existing classes using a supervised nonparametric classification method, namely the Bayes classifier in combination with the k-nearest neighbors algorithms and the kernel regression method. The dissimilarity between a pair of patterns is defined using the functional summaries extracted from the point patterns via the Cramér-von Mises or Kolmogorov-Smirnov type formula. A set of simulation experiments is presented to investigate the performance of the proposed classifier with a dissimilarity measure based on functional summaries, such as the pair correlation function. The application of such a classifier to a real point pattern dataset is also illustrated.

On using Reproducible Hilbert Spaces for the analysis of Replicated Spatial Point Processes

“…To our knowledge, the literature about supervised classification methods applied to replicated point patterns is scarce and relies mainly on dissimilaritybased methods (Mateu et al, 2015;Pawlasová and Dvořák, 2022). Similar methods have been used for supervised classification of germ-grain models in Gallego et al (2016).…”