Universität zu Köln

Tordeux, Antoine, Chraibi, Mohcine, Seyfried, Armin ORCID: 0000-0001-8888-0978 and Schadschneider, Andreas ORCID: 0000-0002-2054-7973 (2020). Prediction of pedestrian dynamics in complex architectures with artificial neural networks. J. Intell. Transport. Syst., 24 (6). S. 556 - 569. PHILADELPHIA: TAYLOR & FRANCIS INC. ISSN 1547-2442

Full text not available from this repository.

Abstract

Pedestrian behavior tends to depend on the type of facility. The flow at bottlenecks, for instance, can exceed the maximal rates observed in straight corridors. Consequently, accurate predictions of pedestrians movements in complex buildings including corridors, corners, bottlenecks, or intersections are difficult tasks for minimal models with a single setting of the parameters. Artificial neural networks are robust algorithms able to identify various types of patterns. In this paper, we will investigate their suitability for forecasting of pedestrian dynamics in complex architectures. Therefore, we develop, train, and test several artificial neural networks for predictions of pedestrian speeds in corridor and bottleneck experiments. The estimations are compared with those of a classical speed-based model. The results show that the neural networks can distinguish the two facilities and significantly improve the prediction of pedestrian speeds.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Tordeux, Antoine UNSPECIFIED UNSPECIFIED UNSPECIFIED Chraibi, Mohcine UNSPECIFIED UNSPECIFIED UNSPECIFIED Seyfried, Armin UNSPECIFIED orcid.org/0000-0001-8888-0978 UNSPECIFIED Schadschneider, Andreas UNSPECIFIED orcid.org/0000-0002-2054-7973 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-330667
DOI:	10.1080/15472450.2019.1621756
Journal or Publication Title:	J. Intell. Transport. Syst.
Volume:	24
Number:	6
Page Range:	S. 556 - 569
Date:	2020
Publisher:	TAYLOR & FRANCIS INC
Place of Publication:	PHILADELPHIA
ISSN:	1547-2442
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language MODEL Multiple languages Transportation; Transportation Science & Technology Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/33066