Calibration of the Pedestrian Ingress Model in the Vaccination Center
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26110%2F22%3APU145769" target="_blank" >RIV/00216305:26110/22:PU145769 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.femtc.com/events/2022/d2-04-uhlik/" target="_blank" >https://www.femtc.com/events/2022/d2-04-uhlik/</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Calibration of the Pedestrian Ingress Model in the Vaccination Center
Popis výsledku v původním jazyce
In recent years, there has been a need to optimize the operation of high-capacity facilities. The covid- 19 pandemic has increased this need even more. The presented paper proposes new procedures for the calibration of agent-based pedestrian models based on video analysis, which have the potential to respond to these needs. In paper is demonstrated the calibration process based on machine learning methods. A model of a vaccination centre waiting room was designed in two settings - basic, which does not include waiting points analysis and advanced, which includes waiting point analysis. Three validation tests were performed and shown, that the proposed calibration approach increases the accuracy of the waiting room model.
Název v anglickém jazyce
Calibration of the Pedestrian Ingress Model in the Vaccination Center
Popis výsledku anglicky
In recent years, there has been a need to optimize the operation of high-capacity facilities. The covid- 19 pandemic has increased this need even more. The presented paper proposes new procedures for the calibration of agent-based pedestrian models based on video analysis, which have the potential to respond to these needs. In paper is demonstrated the calibration process based on machine learning methods. A model of a vaccination centre waiting room was designed in two settings - basic, which does not include waiting points analysis and advanced, which includes waiting point analysis. Three validation tests were performed and shown, that the proposed calibration approach increases the accuracy of the waiting room model.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
20104 - Transport engineering
Návaznosti výsledku
Projekt
<a href="/cs/project/TJ04000232" target="_blank" >TJ04000232: Efektivní časoprostorové predikce s využitím metod strojového učení</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů