A scale-sensitive approach for comparing and classifying point patterns

This paper proposes a novel method for comparing and classifying point patterns. The method explicitly considers the spatial scale since the evaluation of similarity depends on the scale at which one compares point patterns. Three functions were proposed, each of which represents the similarity betw...

Full description

Saved in:
Bibliographic Details
Published in:Journal of spatial science Vol. 65; no. 2; pp. 281 - 306
Main Authors: Sadahiro, Yukio, Liu, Yan
Format: Journal Article
Language:English
Published: Taylor & Francis 03.05.2020
Subjects:
Comparison and classification
kernel smoothing
point patterns
similarity
spatial scale
ISSN:1449-8596, 1836-5655
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a novel method for comparing and classifying point patterns. The method explicitly considers the spatial scale since the evaluation of similarity depends on the scale at which one compares point patterns. Three functions were proposed, each of which represents the similarity between point patterns. A single measure was introduced to summarize the overall similarity between patterns. This single measure was used to classify point patterns into groups according to their spatial patterns. The validity of the method was tested through numerical experiments as well as the analysis of travel transaction data in Southeast Queensland, Australia.
ISSN:1449-8596
1836-5655
DOI:10.1080/14498596.2018.1492466