Big data analytics has been rapidly integrated into Intelligent Transportation System (ITS), empowering diverse applications such as real-time traffic prediction and management. However, incomplete traffic time-series data during the data analysis are nearly inevitable due to the constraints of data collection or packet loss in the communication process. Existing tensor-based completion methods fail to perform well in consecutively missing (CM) cases where a sub-series of the traffic time series is completely missing. Moreover, their high computational complexity prevents the road network-level implementation. Therefore, to tackle these problems, a batch-oriented traffic data completion method for large-scale road networks is proposed in this paper. In order to preserve multi-way natures of traffic data, we first model the traffic data by tensors so that traffic data completion becomes a tensor completion problem. Several types of tensor structures are adopted in order to analyze their impacts on traffic data completion. Thereafter, a Content-Aware traffic data completion method is further developed based on the Generative Adversarial Net (CA-GAN). More specifically, the formulated traffic tensors are interpreted as samples from a high-dimensional traffic distribution and a GAN is then proposed to learn this distribution. By considering effects of traffic data from different days and links, a weighted loss function is employed to search for the raw traffic tensor in the obtained traffic distribution. Afterwards, the estimated raw traffic tensor is used to complete the missing data. Visualization results demonstrate that our GANs can produce verisimilar traffic patterns with different time spans. Finally, our experiments on real traffic datasets show that the proposed CA-GAN method can effectively batch incomplete traffic tensors in CM cases with fast recovery process.

Dynamic path generation in complex transportation networks is essential for intelligent transportation systems. Traditional methods, such as shortest path algorithms or heuristic-based models, often fail to capture real-world travel behaviors due to their reliance on simplified assumptions and limited ability to handle long-range dependencies or non-linear patterns. To address these limitations, we propose PathGen-LLM, a large language model (LLM) designed to learn spatial–temporal patterns from historical paths without requiring handcrafted features or graph-specific architectures. Exploiting the structural similarity between path sequences and natural language, PathGen-LLM converts spatiotemporal trajectories into text-formatted token sequences by encoding node IDs and timestamps. This enables the model to learn global dependencies and semantic relationships through self-supervised pretraining. The model integrates a hierarchical Transformer architecture with dynamic constraint decoding, which synchronizes spatial node transitions with temporal timestamps to ensure physically valid paths in large-scale road networks. Experimental results on real-world urban datasets demonstrate that PathGen-LLM outperforms baseline methods, particularly in long-distance path generation. By bridging sequence modeling and complex network analysis, PathGen-LLM offers a novel framework for intelligent transportation systems, highlighting the potential of LLMs to address challenges in large-scale, real-time network tasks.

As a new dynamic real-time traffic information collecting technique, floating car system is being paid more and more attention in the area of transportation. Based on the actual data condition of Beijing, this paper puts forward a processing flow method for real-time floating car system applied to modern metropolises with complex urban road network. And a series of experiments are reported to validate the feasibility and operational efficiency of the method from the aspects of map-matching efficiency, road network coverage and result reliability.

Car travel characteristics is one of the important factors affecting of the urban road network operation. To provide support for traffic refinement management and policy making, collecting car travel data and having in depth analysis of its travel behavior characteristics, is the key aspect in encouraging car travel behavior change and reducing the vehicle use intensity. Based on the travel data and track data collecting by the vehicle OBD data, car travel characteristics analysis method is put forward, and the quantitative indicators such as trip rate, travel frequency, travel distance can be get, and the travel index variation characteristics were analyzed under the different stages, different regions and different policy. Studying the travel rule by using the big data analysis method, on a deep level, traffic characteristics of user portrait, road network non-linear coefficient can be further obtained. The analysis results show that the intelligent driving data can better reflect the characteristics of the car travel behavior, and make quantitative evaluation of the implementation of the transport demand management policies.

The objective of this paper is to develop a road network reliability evaluation framework for large-scale events by using the dynamic traffic simulation model INTEGRATION and statistics models. A real vocal concert in Beijing Capital Gym is selected as the case study. The temporal distribution characteristics of the network reliability are analyzed under the selected large-scale event. The results indicate that the travel time reliability decreases visibly around one hour before the curtain time and reaches its minimum near half an hour before the curtain time of the concert. Further, the effect of the selected event on the network reliability is analyzed by comparing two scenarios in terms of whether there is a large-scale event. The critical links significantly affected by the large-scale event are identified, based on the difference of travel time reliabilities between these two scenarios. It is demonstrated that the impact of large-scale events on the network reliability is not dispersed in the radial direction, but rather scattered. Finally, the paper evaluates the impact of installing Variable Message Signs (VMS) on these critical links during the period of large-scale events on reliability.