Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System is of great significance for urban planning, management, control. However, has always been considered open scientific issue, owing to constraints road network topological structure law dynamic change with time, namely, spatial dependence temporal dependence. To capture simultaneously, we propose a novel neural network-based method, graph convolutional (T-GCN) model, which combination (GCN)...

We modeled the mobility of mobile phone users in order to study fundamental spreading patterns that characterize a virus outbreak. find although Bluetooth viruses can reach all susceptible handsets with time, they spread slowly because human mobility, offering ample opportunities deploy antiviral software. In contrast, using multimedia messaging services could infect hours, but currently phase transition on underlying call graph limits them only small fraction users. These results explain...

In this paper, we combine the most complete record of daily mobility, based on large-scale mobile phone data, with detailed Geographic Information System (GIS) uncovering previously hidden patterns in urban road usage. We find that major usage each segment can be traced to its own - surprisingly few driver sources. Based finding propose a network by defining bipartite framework, demonstrating contrast traditional approaches, which define importance solely topological measures, role depends...

Big data for social transportation brings us unprecedented opportunities resolving problems which traditional approaches are not competent and building the next-generation intelligent systems. Although have been applied analysis, there still many challenges. First, evolve with time contain abundant information, posing a crucial need collection cleaning. Meanwhile, each type of has specific advantages limitations transportation, one alone is capable describing overall state system. Systematic...

While considering the spatial and temporal features of traffic, capturing impacts various external factors on travel is an essential step towards achieving accurate traffic forecasting. However, existing studies seldom consider or neglect effect complex correlations among traffic. Intuitively, knowledge graphs can naturally describe these correlations. Since networks are essentially heterogeneous networks, it challenging to integrate information in both networks. On this background, study...

Abstract Despite the fact that punctuality is an advantage of rail travel compared with other long-distance transport, train delays often occur. For this study, a three-month dataset weather, delay and schedule records was collected analysed in order to understand patterns predict time. We found severe weather are determined mainly by type bad while ordinary historical time frequency trains. Identifying factors closely correlated delays, we developed machine-learning model each at station....

Traffic flow data collected by traffic sensing devices is crucially important for transportation planning and management. However, are typically distributed sparsely in road networks owing to their high installation maintenance costs. The present study combines license plate recognition (LPR) with taxi GPS trajectory develop a data-driven approach estimating large networks. applied estimate an actual network comprising 5,495 segments using the records of only 68 (1.2% total). Five-fold cross...

Using road GIS (geographical information systems) data and travel demand for two U.S. urban areas, the dynamical driver sources of each segment were located. A method to target clusters closely related traffic congestion was then developed improve network efficiency. The targeted show different spatial distributions at times a day, indicating that our can encapsulate into networks. As proof concept, when we lowered speed limit or increased capacity segments in clusters, found both number...

Predicting the distributions of path flow between origin-destination (OD) pairs in an urban road network is crucial for developing efficient traffic control and management strategies. Here, we use large-scale taxi GPS trajectory data San Francisco Shenzhen to study predictability distribution networks. We develop approach project time-varying into a high-dimensional space. In space, information entropy used measure distribution. find that OD are general characterized with high...

Mode split is an important step in the estimation of travel demand. Beside traditional costly surveys, many mode methods, which employ new emerging large-scale social signal data, are recently proposed. In this paper, we develop a model based on widely available mobile phone data and transportation networks' geographical data. The shares three modes (car, public transportation, walking) each census tract estimated for Boston central suburb area. Finally, proposed validated with real share...

Based on large-scale human mobility data collected in San Francisco and Boston, the morning peak urban rail transit (URT) ODs (origin-destination matrix) were estimated most vulnerable URT segments, those capable of causing largest service interruptions, identified. In both networks, a few highly segments observed. For this small group vital impact failure must be carefully evaluated. A bipartite usage network was developed used to determine inherent connections between transits their...

Identifying and predicting the travel hotspots in urban areas can provide crucial support for building intelligent transportation systems. In this study, we propose to use potentials of mobility field identify develop a K-shape clustering transformer-decoder (KSC-TD) model predict multi-step potentials. KSC-TD model, method is used cluster grids with similar potential time series, whereas trained each by integrating multi-head masked attention mechanism scheduled sampling strategy. The...

The emergence of large-scale social signal data has provided unprecedented opportunities to develop techniques for improving transportation systems. In this paper, we use two types data, namely, mobile phone and subway card investigate congestion avoidance routing methodologies in the Beijing San Francisco road networks. were used estimate detailed travel demand information target sources congestion, order intelligent models. We study fundamental scenarios, shortest path (SP) scenario...

Tremendous volumes of messages on social media platforms provide supplementary traffic information and encapsulate crowd wisdom for solving transportation problems. However, manifested in human languages are usually characterized with redundant, fuzzy subjective features. Here, we develop a data fusion framework to identify reporting non-recurring events by connecting the states inferred from taxi global positioning system (GPS) data. Temporal-spatial anomalies caused then retrieved...