IET Intelligent Transport Systems最新文献

Large-volume and heavy-duty transports are essential for the successful and timely execution of large-scale industrial, socio-political and climate-related projects. As these transports grow in size and complexity, the planning process becomes increasingly challenging for all stakeholders involved. To overcome these challenges, detailed planning processes are required, especially for the trafficability of narrow passages along the transportation route. This paper introduces an advanced methodology for an enhanced 3D trafficability analysis with collision detection of large-volume and heavy-duty transports. By employing high-resolution, dense, colored 3D point clouds alongside detailed transport models, this approach offers a more accurate and comprehensive assessment of the feasibility of the transport. The methodology is further generalized to accommodate a wide variety of transport configurations and maneuvers, allowing for automated analysis across different scenarios. The primary contribution of this research lies in its ability to significantly improve collision detection accuracy and provide detailed visualizations, thereby optimizing the digital planning process of large-volume and heavy-duty transports. The findings demonstrate a distinct advantage of the 3D trafficability analysis over traditional 2D methods, especially in complex environments, leading to cost-effective and reliable transportation planning.

Negative externalities refer to costs arising from transportation activities that are not borne by service providers or consumers, often leading to their neglect in freight transportation planning. This study proposes a novel framework for optimising water-road transportation route selection by incorporating two key negative externalities: fuel consumption and traffic risk. Traffic risk is assessed using a safety performance function, while fuel consumption is estimated based on the Handbook of Emission Factors for Road Transport. The proposed framework is applied to California's road network and port system, where the optimal operation area for each major port is determined and compared across different optimisation objectives: trip distance, fuel consumption and traffic risk. Results indicate that the optimal operation area varies significantly depending on the relative weight assigned to each objective. The findings demonstrate that optimising routes beyond just minimising distance can reduce fuel consumption and traffic risk, highlighting the substantial differences in optimal operational areas under different criteria.

With the rapid development of model cities, urban rail transit (URT) systems have emerged as a crucial component in urban public transport, and passenger flow prediction serves as the cornerstone for planning the travel, avoiding the congestion, and improving the travel efficiency. In order to predict short-term passenger flow of the URT system, a hybrid convolutional neural network (CNN)-long short-term memory (LSTM)-particle swarm optimisation (PSO) model is proposed to accommodate both the spatial and temporal features of passenger flow. First, spectral clustering is employed to extract four different types of stations, in which the Calinski–Harabasz (CH) index is considered. Second, the hybrid CNN-LSTM-PSO model is constructed to predict the short-term passenger flow for different types of stations, in which CNN can extract the abstract feature with a multi-layer convolutional structure, LSTM can deal with time series data, and the PSO algorithm is employed to optimise some parameters. Third, the data from Hangzhou urban rail transit in 2019 are employed for prediction. The results show that the proposed hybrid model reveals the best performance in accuracy by comparing the equivalent CNN-LSTM, LSTM and autoregressive integrated moving average (ARIMA) models. At last, some empirical suggestions are provided to benefit both the passengers and operation and management departments of the URT system.

The optimization of spatial and temporal resources at signalized intersections is a critical aspect of intelligent transportation systems. Traditional traffic signal control methods, which usually rely on fixed signal timings and lane assignments, are suboptimal in addressing changing traffic conditions. Additionally, understanding traffic flow in a large scale is often challenging due to the lack of traffic flow monitoring infrastructure. This paper introduces Trans-Space, a novel framework that leverages transfer learning and space computing for managing spatiotemporal traffic resources at signalized intersections. Trans-Space consists of two core modules: (space computing for optimized traffic system (SCOTS) and traffic optimization with spatial–temporal control agents (TOSCA). SCOTS configures satellite constellations for high-resolution Earth observation images and utilizes space computing to extract real-time traffic flow parameters. TOSCA employs hierarchical reinforcement learning agents to optimize lane directions and signal timings based on the data provided by SCOTS. TOSCA incorporates knowledge transfer that adapts traffic management strategies from source to target intersections. Through extensive simulations, Trans-Space demonstrated superior performance over traditional and state-of-the-art models in traffic flow metrics. The paper concludes with a discussion on the prospects of space computing in traffic management and potential directions for future research.

The study investigates emergency evacuation strategies for high-capacity multi-line transfer metro stations, with a focused examination on congestion dynamics induced by interweaving passenger flows. Taking a three-line interchange station in Xi'an, China, as an example, a 3D emergency evacuation physical model was established using AnyLogic software, with pedestrian parameters and behavioural logic for security checks, level transfers, and evacuation configured through Java programming. Observations from a scenario involving 2200 passengers revealed that safety exits B, C and E, along with escalator groups 1 and 4 in high-traffic areas, were the station's evacuation bottlenecks, leading to congestion and stampede risks. Pedestrians tended to choose the nearest exits, resulting in a peak density of up to 3.79 persons/m². To address these challenges, this study proposed two optimised evacuation routes. After optimisation, evacuation time was significantly reduced by over 10%, meeting safety requirements. These findings contribute to improving emergency evacuation strategies for complex multi-line subway stations.

On the basis of a generative adversarial network (GAN) and a convolutional neural network (CNN), this work proposes an ER-GAN-CNN to forecast the traffic flow in the presence of missing data by improving GAN. Due to the occurrence of emergencies and the fault of the relevant equipment, the equipment for passenger flow detection may lose some data, which would have negative impacts on passenger flow prediction. In order to cope with such situations, GAN is introduced to make up for the missing data in this paper. On the basis of complete data and CNN, inception blocks are built thereafter to further predict the passenger flow/traffic flow. The accuracy of the prediction of passenger flow is significantly improved with the help of the ER-GAN-CNN, which is able to provide more accurate and rapid traffic guidance for the drivers.

The current moving block systems still depend on wayside interlocking systems and zone controllers, resulting in complex control flow and limited control efficiency. While recent train-centric solutions have simplified the system and enhanced line capacity, they still require explicit resource requests from the wayside infrastructure controller and necessitate storing all routes in onboard equipment. These limitations constrain system performance and maintainability. This study introduces an autonomous train control principle for fully train-centric route generation and track resource management, eliminating reliance on wayside controllers. The proposed system models track layouts as directed graphs and generates routes through route factorisation and composition, ensuring compliance with railway safety and operational requirements. By utilising train-to-train coordinate transformations, ATCS enables direct management of track resources between trains without intermediaries, significantly improving the system's performance. Furthermore, a novel braking model is introduced, optimising headway distances and improving track utilisation. The proposed principle is evaluated on an actual railway track layout in Korea, and the results demonstrate its feasibility, achieving shorter headways, improved track capacity, and enhanced system maintainability and flexibility when compared to conventional CBTC and train-centric CBTC systems.

Traffic forecasting plays a pivotal role in the advancement of intelligent transportation systems, with significant implications for congestion alleviation and optimal route planning. Existing approaches typically focus on capturing the temporal dynamics of traffic states and the spatial dependencies across road networks to improve prediction accuracy. Nevertheless, two noteworthy limitations persist in these approaches: (1) A lack of consideration for the interaction between spatiotemporal features over varying time scales, which impedes the effective utilization of traffic state information for forecasting future conditions. (2) The inherent stochasticity and distributional imbalances in traffic flow, which introduce uncertainty and contribute to overfitting issues in deep learning models. To address these challenges, we propose a novel method, the heterogeneous-scale multi-graph convolution networks based on kernel density estimation (KDE-HSMGCN). This method integrates two core components: the frequency feature layer and the heterogeneous-scale spatiotemporal layers. The frequency feature layer employs a mapping network to learn and equalize traffic flow distributions, mitigating the effects of distribution imbalance and overfitting during model training. The heterogeneous-scale spatiotemporal layers utilize stacked spatiotemporal layers to capture traffic state information across varying time scales. Experimental evaluations on two diverse traffic datasets demonstrate the superior performance of KDE-HSMGCN in medium and long-term forecasting scenarios.

Urban traffic speed prediction with high precision is the unremitting pursuit of intelligent transportation systems. The fundamental challenges of traffic speed prediction lie in the accurate modelling of the complex temporal and spatial correlations of transportation systems. Among all the methods, the hybrid “GNN + RNN” models have achieved state-of-the-art results. However, these methods still cannot address the following two challenges. First, in addition to the topology of road networks, the traffic speed could be affected by a variety of other factors, such as road functionality and weather. Second, in addition to predicting traffic speed, it is necessary to diagnose the causes of the prediction results. In this paper, we propose a multi-graph attentive network (MGAN), to predict and diagnose urban traffic speed. We create GNN model by using multiple graphs to encode the factors affecting them from various aspects. And we design a hierarchical attention mechanism to organize and pinpoint the fine-grained effects of different affecting factors for diagnosing the prediction results. The experimental results demonstrate that MGAN achieves state-of-the-art prediction performance on two real-world datasets, outperforming the strongest baseline by at least $��5.94�\%�$ across three prediction horizons, and is able to intuitively diagnose the prediction results.

Accurate platform-based passenger flow prediction based on deep learning technology becomes crucial for efficient operation and management; in particular, the prediction integrating external weather factors, temporal dependencies and spatial features is desired but has not been addressed. This paper is different from the previous station-based passenger flow prediction, but reconstructs data recorded by the Automatic Fare Collection System (AFCS) for platform-based prediction. Existing deep learning techniques often struggle with issues such as high computational cost in traffic flow prediction. To address these issues, a novel passenger flow prediction model is proposed that integrates convolutional neural networks (CNN) with bi-directional long short-term memory networks (BILSTM) and an attention mechanism (CNN-BILSTM-Attention). The proposed model takes preprocessed numerical weather features, temporal and spatial features as input. The CNN extracts spatial patterns from passenger flow data, the BILSTM captures temporal dependencies and the attention mechanism dynamically adjusts the importance weights of features at different time slots. By integrating these components, the model effectively captures spatiotemporal patterns while accounting for weather impacts. Experimental results demonstrate that the proposed approach outputs an efficient and accurate prediction.