000866394 001__ 866394
000866394 005__ 20210130003435.0
000866394 020__ $$a978-3-030-28664-4 (print)
000866394 020__ $$a978-3-030-28665-1 (electronic)
000866394 0247_ $$2doi$$a10.1007/978-3-030-28665-1_27
000866394 0247_ $$2Handle$$a2128/23606
000866394 037__ $$aFZJ-2019-05548
000866394 1001_ $$0P:(DE-HGF)0$$aTordeux, Antoine$$b0$$eCorresponding author
000866394 1112_ $$aStochastic Models, Statistics and Their Applications$$cDresden$$d2019-03-06 - 2019-03-08$$gSMSA 2019$$wGermany
000866394 245__ $$aArtificial Neural Networks Predicting Pedestrian Dynamics in Complex Buildings
000866394 260__ $$aCham$$bSpringer International Publishing$$c2019
000866394 29510 $$aSteland, Ansgar (Editor)   Chapter 27 ; ISSN: 2194-1009=2194-1017 ; ISBN: 978-3-030-28664-4=978-3-030-28665-1
000866394 300__ $$a363 - 372
000866394 3367_ $$2ORCID$$aCONFERENCE_PAPER
000866394 3367_ $$033$$2EndNote$$aConference Paper
000866394 3367_ $$2BibTeX$$aINPROCEEDINGS
000866394 3367_ $$2DRIVER$$aconferenceObject
000866394 3367_ $$2DataCite$$aOutput Types/Conference Paper
000866394 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1576510097_618
000866394 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000866394 4900_ $$aSpringer Proceedings in Mathematics & Statistics$$v294
000866394 520__ $$aThe prediction of pedestrian movements in complex buildings is a difficulttask. Recent experiments have shown that the behaviour of pedestrians tends todepend on the type of facility. For instance, flows at bottlenecks often exceed themaximal rates observed in straight corridors. This makes pedestrian behavioursgeometry-dependent. Yet the types of geometries are various, and their systematicidentification in complex buildings is not straightforward. Artificial neural networksare able to identify various types of patterns without supervision. They could be asuitable alternative for forecasts of pedestrian dynamics in complex architectures. Inthis paper, we test this assertion.We develop, train and test artificial neural networksfor the prediction of pedestrian speeds in corridor and bottleneck experiments. Theestimations are compared to those of an elementary speed-based model. The resultsshow that neural networks distinguish the flow characteristics for the two differenttypes of facilities and significantly improve the prediction of pedestrian speeds.
000866394 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0
000866394 588__ $$aDataset connected to CrossRef Book Series
000866394 7001_ $$0P:(DE-Juel1)132077$$aChraibi, Mohcine$$b1
000866394 7001_ $$0P:(DE-Juel1)132266$$aSeyfried, Armin$$b2
000866394 7001_ $$0P:(DE-HGF)0$$aSchadschneider, Andreas$$b3
000866394 773__ $$a10.1007/978-3-030-28665-1_27
000866394 8564_ $$uhttps://juser.fz-juelich.de/record/866394/files/Tordeux2019b.pdf$$yOpenAccess$$zStatID:(DE-HGF)0510
000866394 8564_ $$uhttps://juser.fz-juelich.de/record/866394/files/Tordeux2019b.pdf?subformat=pdfa$$xpdfa$$yOpenAccess$$zStatID:(DE-HGF)0510
000866394 909CO $$ooai:juser.fz-juelich.de:866394$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000866394 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132077$$aForschungszentrum Jülich$$b1$$kFZJ
000866394 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132266$$aForschungszentrum Jülich$$b2$$kFZJ
000866394 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x0
000866394 9141_ $$y2019
000866394 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000866394 9201_ $$0I:(DE-Juel1)IAS-7-20180321$$kIAS-7$$lZivile Sicherheitsforschung$$x0
000866394 980__ $$acontrib
000866394 980__ $$aVDB
000866394 980__ $$aUNRESTRICTED
000866394 980__ $$acontb
000866394 980__ $$aI:(DE-Juel1)IAS-7-20180321
000866394 9801_ $$aFullTexts