AI-Based Transportation Planning and Operation

• Autore: Sohn Keemin
• Pubblicazione: Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021
• Descrizione fisica: 1 electronic resource (124 p.)
• Soggetto topico: History of engineering & technology
• Soggetto non controllato: autoencoder; deep learning; traffic volume; vehicle counting; CycleGAN; bottleneck and gridlock identification; gridlock prediction; urban road network; long short-term memory; link embedding; traffic speed prediction; traffic flow centrality; reachability analysis; spatio-temporal data; artificial neural network; context-awareness; dynamic pricing; reinforcement learning; ridesharing; supply improvement; taxi; preventive automated driving system; automated vehicle; traffic accidents; deep neural networks; vehicle GPS data; driving cycle; micro-level vehicle emission estimation; link emission factors; MOVES; black ice; CNN; prevention
• Persona (resp. second.): SohnKeemin
• Sommario/riassunto: The purpose of this Special Issue is to create an an academic platform whereby high-quality research papers are published on the applications of innovative AI algorithms to transportation planning and operation. The authors present their original research articles related to the applications of AI or machine-learning techniques to transportation planning and operation. The topics of the articles encompass traffic surveillance, traffic safety, vehicle emission reduction, congestion management, traffic speed forecasting, and ride sharing strategy.
• Titolo autorizzato: AI-Based Transportation Planning and Operation
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910557486603321
• Lo trovi qui: Univ. Federico II