This title appears in the Scientific Report :
2020
Please use the identifier:
http://hdl.handle.net/2128/26024 in citations.
Please use the identifier: http://dx.doi.org/10.1080/15472450.2019.1621756 in citations.
Prediction of pedestrian dynamics in complex architectures with artificial neural networks
Prediction of pedestrian dynamics in complex architectures with artificial neural networks
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 intersection...
Saved in:
Personal Name(s): | Tordeux, Antoine |
---|---|
Chraibi, Mohcine (Corresponding author) / Seyfried, Armin / Schadschneider, Andreas | |
Contributing Institute: |
Zivile Sicherheitsforschung; IAS-7 |
Published in: | Journal of intelligent transportation systems, 24 (2020) 6, S. 556-568 |
Imprint: |
Philadelphia, Pa.
Taylor and Francis, Inc.
2020
|
DOI: |
10.1080/15472450.2019.1621756 |
Document Type: |
Journal Article |
Research Program: |
Computational Science and Mathematical Methods |
Link: |
Published on 2019-06-04. Available in OpenAccess from 2020-06-04. Published on 2019-06-04. Available in OpenAccess from 2020-06-04. |
Publikationsportal JuSER |
Please use the identifier: http://dx.doi.org/10.1080/15472450.2019.1621756 in citations.
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. |