001044146 001__ 1044146
001044146 005__ 20250729202320.0
001044146 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-03048
001044146 037__ $$aFZJ-2025-03048
001044146 041__ $$aEnglish
001044146 1001_ $$0P:(DE-Juel1)185971$$aAlia, Ahmed$$b0$$eCorresponding author$$ufzj
001044146 1112_ $$aModelling, Data Analytics and AI in Engineering$$cPorto$$d2025-07-07 - 2025-07-11$$gMadeAI 2025$$wPortugal
001044146 245__ $$aA Dynamic Distance Social LSTM for Predicting Pedestrian Trajectories in Crowded Environments
001044146 260__ $$c2025
001044146 3367_ $$033$$2EndNote$$aConference Paper
001044146 3367_ $$2DataCite$$aOther
001044146 3367_ $$2BibTeX$$aINPROCEEDINGS
001044146 3367_ $$2DRIVER$$aconferenceObject
001044146 3367_ $$2ORCID$$aLECTURE_SPEECH
001044146 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1753769244_5604$$xAfter Call
001044146 520__ $$aThis work introduces dynamic distance Social Long Short-Term Memory, a deep learning approach for pedestrian trajectory prediction in crowded environments. The approach integrates a new dynamic distance-based loss function into Social Long Short-Term Memory, enhancing collision avoidance without compromising displacement accuracy. The method is trained and evaluated on a heterogeneous density dataset and four homogeneous density datasets, covering various crowd-density levels. Experimental results show that the proposed approach outperforms baseline methods in reducing collision rates without decreasing displacement accuracy and, in most cases, even improving it.
001044146 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001044146 7001_ $$0P:(DE-Juel1)132077$$aChraibi, Mohcine$$b1$$ufzj
001044146 7001_ $$0P:(DE-Juel1)132266$$aSeyfried, Armin$$b2$$ufzj
001044146 8564_ $$uhttps://juser.fz-juelich.de/record/1044146/files/Abstract.pdf$$yOpenAccess
001044146 8564_ $$uhttps://juser.fz-juelich.de/record/1044146/files/MADEAI25-Final.pptx$$yRestricted
001044146 909CO $$ooai:juser.fz-juelich.de:1044146$$popenaire$$popen_access$$pVDB$$pdriver
001044146 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185971$$aForschungszentrum Jülich$$b0$$kFZJ
001044146 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132077$$aForschungszentrum Jülich$$b1$$kFZJ
001044146 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132266$$aForschungszentrum Jülich$$b2$$kFZJ
001044146 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001044146 9141_ $$y2025
001044146 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001044146 920__ $$lyes
001044146 9201_ $$0I:(DE-Juel1)IAS-7-20180321$$kIAS-7$$lZivile Sicherheitsforschung$$x0
001044146 980__ $$aconf
001044146 980__ $$aVDB
001044146 980__ $$aUNRESTRICTED
001044146 980__ $$aI:(DE-Juel1)IAS-7-20180321
001044146 9801_ $$aFullTexts