Stochastic Reconstruction for Inhomogeneous Point Patterns

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10434767" target="_blank" >RIV/00216208:11320/21:10434767 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=HLDg4wqyEh" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=HLDg4wqyEh</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11009-019-09738-0" target="_blank" >10.1007/s11009-019-09738-0</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Stochastic Reconstruction for Inhomogeneous Point Patterns

Popis výsledku v původním jazyce

The stochastic reconstruction approach for point processes aims at producing independent patterns with the same properties as the observed pattern, without specifying any particular model. Instead a so-called energy functional is defined, based on a set of point process summary characteristics. It measures the dissimilarity between the observed pattern (input) and another pattern. The reconstructed pattern (output) is sought iteratively by minimising the energy functional. Hence, the output has approximately the same values of the prescribed summary characteristics as the input pattern. In this paper, we focus on inhomogeneous point patterns and apply formal hypotheses tests to check the quality of reconstructions in terms of the intensity function and morphological properties of the underlying point patterns. We argue that the current version of the algorithm available in the literature for inhomogeneous point processes does not produce outputs with appropriate intensity function. We propose modifications to the algorithm which can remedy this issue.

Název v anglickém jazyce

Stochastic Reconstruction for Inhomogeneous Point Patterns

Popis výsledku anglicky

The stochastic reconstruction approach for point processes aims at producing independent patterns with the same properties as the observed pattern, without specifying any particular model. Instead a so-called energy functional is defined, based on a set of point process summary characteristics. It measures the dissimilarity between the observed pattern (input) and another pattern. The reconstructed pattern (output) is sought iteratively by minimising the energy functional. Hence, the output has approximately the same values of the prescribed summary characteristics as the input pattern. In this paper, we focus on inhomogeneous point patterns and apply formal hypotheses tests to check the quality of reconstructions in terms of the intensity function and morphological properties of the underlying point patterns. We argue that the current version of the algorithm available in the literature for inhomogeneous point processes does not produce outputs with appropriate intensity function. We propose modifications to the algorithm which can remedy this issue.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GA19-04412S" target="_blank" >GA19-04412S: Nové přístupy k modelování a statistice náhodných množin</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Methodology and Computing in Applied Probability

ISSN

1387-5841

e-ISSN

—

Svazek periodika

23

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

527-547

Kód UT WoS článku

000661508800006

EID výsledku v databázi Scopus

2-s2.0-85070986887