An Artificial Neural Network Framework for Pedestrian Walking Behavior Modeling and Simulation
Collective Dynamics · 2020-03-27 · 5
DOI: 10.17815/cd.2020.62 ↗At a glance
Journal article in Collective Dynamics, published online on 2020-03-27. Written by Peter Kielar and 1 co-authors. Cited 5 times so far (Crossref). The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Movement behavior models of pedestrian agents form the basis of computational crowd simulations. In contemporary research, a large number of models exist. However, there is still no walking behavior model that can address the various influence factors of movement behavior holistically. Thus, we endorse the use of artificial neural networks to develop walking behavior models because machine learning methods can integrate behavioral factors efficiently, automatically, and data-driven. In this paper, we support this approach by providing a framework that describes how to include artificial neural networks into a pedestrian research context. The framework comprises 5 phases: data, replay, training, simulation, and validation. Furthermore, we describe and discuss a prototype of the framework.
Cite
APA
Kielar, P., & Borrmann, A. (2020). An Artificial Neural Network Framework for Pedestrian Walking Behavior Modeling and Simulation. Collective Dynamics, 5. https://doi.org/10.17815/cd.2020.62
Vancouver
Kielar P, Borrmann A. An Artificial Neural Network Framework for Pedestrian Walking Behavior Modeling and Simulation. Collective Dynamics. 2020;5. doi:10.17815/cd.2020.62
BibTeX
@article{Kielar2020,
author = {Kielar, Peter and Borrmann, André},
title = {An Artificial Neural Network Framework for Pedestrian Walking Behavior Modeling and Simulation},
journal = {Collective Dynamics},
year = {2020},
volume = {5},
doi = {10.17815/cd.2020.62}
}
EUVIMED