A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing

• Published in: Multimedia tools and applications Vol. 80; no. 20; pp. 31401 - 31433
• Main Authors: Ali, Ahmad, Zhu, Yanmin, Zakarya, Muhammad
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2021; Springer Nature B.V
• Subjects: 1194: Secured and Efficient Convergence of Artificial Intelligence and Internet of Things; Accuracy; Agglomeration; Artificial neural networks; Cloud computing; Computer Communication Networks; Computer Science; Data management; Data Structures and Information Theory; Datasets; Multimedia Information Systems; Neural networks; Predictions; Public safety; Redundancy; Safety management; Spatial dependencies; Special Purpose and Application-Based Systems; Statistical methods; Traffic flow; Traffic management; Deep learning; Data aggregation; Attention mechanism; Road safety; Crowd prediction; Neural networks

Accurate and timely predicting citywide traffic crowd flows precisely is crucial for public safety and traffic management in smart cities. Nevertheless, its crucial challenge lies in how to model multiple complicated spatial dependencies between different regions, dynamic temporal laws among differe...