Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which jointly learns the spatial-temporal correlation features and interdependence of multi-modality traffic data by multimodal deep learning architecture. According to the highly nonlinear charac...

Timely traffic prediction is important in advanced traffic management systems. Observing traffic flow, we find repetitive or regular behavior over time. By taking advantage of tools in frequency domain analysis, this paper proposes a new criterion function that can detect the onset of congestion. It is found that the changing rate of the cross-correlation between density dynamics and flow rate ...

Dynamic arrest is a general phenomenon across a wide range of dynamic systems including glasses, traffic flow, and dynamics in cells, but the universality of dynamic arrest phenomena remains unclear. We connect the emergence of traffic jams in a simple traffic flow model directly to the dynamic slowing down in kinetically constrained models for glasses. In kinetically constrained models, the fo...

A macroscopic traffic flow model describes the evolution of aggregated traffic characteristics over time and space, which is a basic and critical component for various modern intelligent transportation systems, e.g., a real-time freeway control system. Traditional macroscopic traffic flow models are built in the Eulerian coordinates using Eulerian traffic characteristics, such as density, speed...

Accident risk has been applied extensively in transportation safety analysis. Risk is often used to describe the level of safety in transportation systems by incorporating a measure of exposure, such as traffic flow or kilometers driven. The most commonly applied definition of accident risk states that risk is a linear function of accidents and traffic flow. This definition, however, creates pr...

As an important component of intelligent transportation-management systems, accurate traffic-parameter prediction can help traffic-management departments to conduct effective traffic management. Due the nonlinearity, complexity, and dynamism highway-traffic data, traffic-flow is still a challenging issue. Currently, most spatial–temporal traffic-flow-prediction models adopt fixed-structure time...

Safety of vessel transit in congested sea areas such as busy ports and coastal waters is a key issue for navigation officers and traffic operators. With performance improvement of observation devices and introduction of new information systems, vessel traffic service is expected to play a larger role in supporting the officers onboard. Increase in amount of available information demands higher ...

The collective movement of animal groups often occurs in confined spaces. As animal groups are challenged to move at high density, their mobility dynamics may resemble the flow of densely packed non-living soft materials such as colloids, grains, or polymers. However, unlike inert soft-materials, self-propelled collective living systems often display social interactions whose influence on colle...