Speed prediction in large and dynamic traffic sensor networks

Magalhães, Régis Pires; Lettich, Francesco; Macêdo, José Antônio Fernandes de; Nardini, Franco Maria; Perego, Raffaele; Renso, Chiara; Trani, Roberto

doi:10.1016/j.is.2019.101444

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Asphalt mixtures from Bogotá, Colombia, showed that reducing speed from 60 km/h to 30 km/h resulted in roughly a 15.6% decrease in asphalt mixture stiffness and a 39.5% reduction in its fatigue life. In turn, Magalhaes et al [48] delved into forecasting speeds within traffic sensor networks to enhance the decision-making capabilities of traffic management systems. Predicting speeds accurately in urban settings poses challenges due to complex traffic patterns, numerous sensors, and the dynamic nature of sensor networks.…”

Section: Connected Infrastructure and Intelligent Transportation Systemsmentioning

confidence: 99%

“…In this context, the integration of dynamic traffic management with road maintenance strategies has also been investigated [51]. Despite challenges in predicting speeds within extensive and dynamic traffic sensor networks, as explored in [48], the study referred to by [51] examined leveraging big data for informed, intelligent maintenance decisions. The approach targets the enhancement of intersections for durability and efficiency, aiding road maintainers in the initial assessment of road surface conditions.…”

Section: Dynamic Traffic Management and Adaptive Signal Controlmentioning

confidence: 99%

See 1 more Smart Citation

Blending Efficiency and Resilience in the Performance Assessment of Urban Intersections: A Novel Heuristic Informed by Literature Review

Zare,

Macioszek,

Granà

et al. 2024

Sustainability

View full text Add to dashboard Cite

Urban mobility underscores the vital importance of ensuring traffic efficiency on road segments, intersections, and transportation networks, especially in challenging circumstances. In this perspective, the essential approach to improving urban intersection efficiency should involve understanding critical factors for maintaining operational performance in the face of disruptions such as storms. This paper, inspired by a systematic literature review, presents a novel heuristic for evaluating urban intersection efficiency, with resilience as its guiding principle. The methodological path was designed to address the fundamental question: How can urban intersections be designed and managed to ensure efficiency and resilience in the face of disruptions? Drawing inspiration from the Highway Capacity Manual procedure, the methodological approach encompasses both pre-storm and post-storm scenarios, comparing delay times at roundabouts and signalized intersections before and after a storm. The results reveal significant changes in delay times for traffic signals, although the choice between roundabouts and signalized intersections should be context-specific, considering factors like traffic conditions, resilience requirements, and associated trade-offs. By shedding light on the interplay between intersection design, control strategies, and urban resilience, this research provides valuable insights into integrating resilience considerations into intersection performance assessment and management strategies. It also underscores how particular intersection designs can impact efficiency and recovery, essential considerations when assessing whether a road or intersection project is resilient.

show abstract

Section: Connected Infrastructure and Intelligent Transportation Systemsmentioning

confidence: 99%

Section: Dynamic Traffic Management and Adaptive Signal Controlmentioning

confidence: 99%

Blending Efficiency and Resilience in the Performance Assessment of Urban Intersections: A Novel Heuristic Informed by Literature Review

Zare,

Macioszek,

Granà

et al. 2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…Meanwhile, Gong et al (2020) handled the cold-start challenge for passenger flow prediction by mining supplementary information from urban statistical data to guide the learning process. Lastly, Magalhaes et al (2021) proposed the global and cluster-based approaches, where models are trained on data coming from all the sensors in the network (or groups of similar sensors, in the cluster-based case) to build resilient predictive functions. However, among these two approaches, the global-based approach naturally solves the cold start problem because it relies on a single prediction function independent of specific sensors.…”

Section: Data Cleaningmentioning

confidence: 99%