Enhancing crowd management through behaviourally informed synthetic datasets and predictive deep learning models

Collecting and annotating real-world crowd data hinders effective analysis of overcrowding. The limited availability of detailed and diverse crowd datasets affects the reliability of predictive models. Existing crowd management approaches tend to prioritise anomaly detection over prediction, and mos...

Descripció completa

Dades bibliogràfiques

Autors principals:	S Vijaya Lakshmi Gayathri, Talapaneni Harshitha, Harikrishnan Kriyasri, Ananthakrishnan Balasundaram
Format:	Artigo
Idioma:	Inglês
Publicat:	Elsevier 2025-12-01
Col·lecció:	Results in Engineering
Matèries:	Anomaly prediction Crowd simulation Crowd behaviour Overcrowding Group movement Synthetic dataset
Accés en línia:	http://www.sciencedirect.com/science/article/pii/S2590123025042562
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!