Efficient inspection of power transmission infrastructure is essential for ensuring the reliability of modern energy systems. However, traditional inspection methods relying on manual patrols or manned helicopters suffer from low efficiency, high operational costs, and substantial carbon emissions. To address these challenges, this paper proposes a multi-UAV-vehicle cooperative inspection framework for power grid infrastructure. A mixed-integer linear programming model is developed to formulate the cooperative routing problem, which explicitly incorporates wind field effects on UAV energy consumption and employs a group-based collaborative strategy to enable scalable deployment across large-scale networks. A Terminal Pickup Mode is introduced to allow ground vehicles to retrieve UAVs at task completion points, thereby maximizing battery utilization for inspection activities rather than energy-intensive return flights. To solve large-scale problem instances efficiently, an Adaptive Large Neighborhood Search algorithm with tailored destroy and repair operators is designed. Numerical experiments demonstrate that the proposed method significantly reduces system makespan while exhibiting robust performance under adverse wind conditions compared to conventional self-return strategies. Furthermore, the analysis of vehicle-drone speed synchronization and resource allocation provides practical managerial insights for optimizing operational efficiency. The findings contribute to enabling intelligent inspection operations that support the reliable integration of sustainable energy infrastructure management.

OBJECTIVES:Urban road traffic exhibits complex and highly dynamic flow patterns, making real-time risk probability assessment challenging. Existing measures such as Time to Collision (TTC) rely on full sample vehicle trajectory data, which are difficult to obtain at large urban scales. To address this limitation, this study adopts a spatiotemporal grid representation and utilizes floating vehicle trajectory data to characterize traffic operational states and develop a real-time urban traffic risk probability assessment framework. METHODS:This study proposes an integrated spatiotemporal framework for urban traffic risk probability estimation. A Graph Attention Network Long Short Term Memory (GAT-LSTM)-based Spatiotemporal Autoencoder Neural Network (GL-SANN) is developed to extract latent risk features from vehicle operational parameters. These features are further incorporated into a Deep Clustering Spatiotemporal Network (DCSN) with K-means clustering to assess traffic risk levels. A LightGBM model is then constructed for real-time risk identification. Finally, a Spatiotemporal Graph Convolutional Risk Prediction (SGCRP) model is designed to predict future vehicle operational parameters and infer short-term risk states. RESULTS:Experiments using ride-hailing vehicle trajectory data from Xi'an demonstrate that traffic risk probability patterns can be classified into five levels, with risk probability levels increasing significantly during peak periods and decreasing during off-peak periods. Specifically, the proportion of high-risk grids reaches approximately 50%-60% during peak periods, while during off-peak periods, this proportion decreases to about 37%. Intersections and traffic-intensive grids consistently exhibit higher risk probability levels than ordinary grids. The DCSN model consistently outperforms benchmark methods. The LightGBM-based risk identification model achieves a precision of 0.984. The proposed risk prediction model improves training speed by 33.1% over the Transformer model and yields a prediction precision of 0.974. CONCLUSIONS:These findings provide a method for proactive urban traffic risk prevention and contribute to the development of intelligent transportation systems.

The operation and management of the metro system in urban areas rely on accurate predictions of future passenger flow. While using all the available information can potentially improve on the accuracy of the flow prediction, there has been little attention to the hierarchical relationship between the type of tickets collected from the passengers entering/exiting a station and its resulting passenger flow. To this end, we propose a novel Integrative Prediction Framework with the Hierarchical Message-Passing Graph Neural Network (IPF-HMGNN). The proposed framework consists of three components: initial prediction, task judgment and hierarchical coordination modules. Using the Wuxi, China metro network as an example, we study two prediction approaches (i) traditional prediction approach where the model directly predicts passenger flow at the station, and (ii) hierarchical prediction approach where the prediction of ticket type and station passenger flow are performed simultaneously considering the hierarchical constraints (i.e., the sum of predicted passenger flow per ticket type equals the predicted station aggregated passenger flow). Experimental results indicate that in the traditional prediction approach, our IPF-HMGNN can significantly reduce the mean absolute error (MAE) and root mean square error (RMSE) of the GNN prediction model by 49.56% and 53.88%, respectively. In the hierarchical prediction approach, IPF-HMGNN can achieve a maximum reduction of 35.32% in MAE and 36.18% in RMSE, while satisfying the hierarchical constraint.

Sudden natural disasters pose significant threats to lives, property, and infrastructure, underscoring the critical need to determine optimal locations for emergency reserve depots and plan efficient transportation routes. Therefore, this paper focuses on the location-routing optimization in emergency logistics following a disaster. In addition to the traditional considerations of rescue time and cost, we propose a novel approach that incorporates risk factors of transportation routes. The aim is to avoid secondary disasters during transport and improve rescue efficiency. Using the 2008 Wenchuan earthquake as a case, results show the hybrid machine learning CPSO-XGBoost approach employed as our road segment risk identification model achieves 0.9668 accuracy. Compared to NSGA-II, the improved ACONSGA-II algorithm shows superior optimization capability. Unlike traditional emergency location-routing models that overlook road risks, the proposed approach identifies safer location-routing solutions for material transport while maintaining rescue time and cost.

Vehicle trajectory data plays a fundamental role in intelligent traffic management system. However, missing trajectory segments due to signal interruption or insufficient sampling frequency often fail to meet the requirements of high-precision applications. This paper proposes a trajectory-conditional generative adversarial network (T-CGAN) model to address the challenge of missing trajectory imputation. Firstly, in order to reduce the generation of redundant trajectories, we construct a directed graph based on discrete spatiotemporal grids, and propose a ShapeBased Missing Trajectory Generation (SBMTG) algorithm to mine conditional information. The SBMTG algorithm reformulates the trajectory filling task as a path optimization problem on a graph with predetermined source and target points, which uses the shape based distance as the optimization objective. Then the trajectories generated by the SBMTG serve as conditional input for the adversarial neural network. Gate Recurrent Unit for Imputation is applied to the adversarial neural network component, which takes missing intervals of trajectories into account. The proposed approach is validated using a local dataset from Xi'an, China. The results consistently demonstrate the algorithm's superior accuracy in infilling missing vehicle trajectories at either single intersections or across multiple consecutive intersections.

To enhance the efficiency and sustainability of urban freight operations, China has initiated the Urban Green Freight Delivery (UGFD) project, which involves optimizing access control policies and introducing new energy vehicles. Identifying the parking trips of new energy vehicles and exploring the spatiotemporal patterns is crucial to actively promoting the optimal layout of temporary stops and the formulation of parking policies in the UGFD project. In this study, we aim to comprehend the spatiotemporal heterogeneity of parking for new energy vehicles both on roads (on-street) and within urban communities (off-street) for promoting the UGFD project. Its specific content includes: (1) proposing a method for identifying valid parking trips for the loading and unloading of goods based on trajectory data of UGFD new energy vehicles; and (2) mapping the identification results of valid parking trips onto communities and roads to analyze the spatiotemporal heterogeneity. Taking Suzhou, Jiangsu Province, China as an example, the identification results show that the established valid parking trips identification method can outperform state-of-the-art methods. The accuracy, precision, recall, and F1 value were found to be 0.957, 0.908, 0.937, and 0.922, respectively. Further examination of parking patterns indicates a bimodal temporal distribution of delivery demand, with peak activity occurring between 08:00-09:00 and between 14:00-17:00, with a higher delivery demand in the morning. Spatially, delivery demand was aggregated, while the parking time distribution of most delivery activities was normal. Additionally, the parking characteristics of communities and roads conformed to the 'Rank-size rule', suggesting that most delivery parking activities were concentrated in a few communities and roads. These findings can also be used in UGFD stop station utilization, travel time, arrival time prediction, and other related fields, all of which can further support relevant management departments in discovering abnormal delivery behaviors and reduce their negative impacts.

Turning traffic prediction at urban intersections is very important for the dynamic optimization of traffic management strategies, but accuracy is often influenced by missing data. We propose a novel approach with a Heterogeneous Two-Layer Graph Convolution (HTLGC) model to enhance prediction accuracy while addressing missing data challenges. We construct the urban road network as a heterogeneous two-layer spatial graph, with intersection nodes in the upper layer and turning nodes in the lower layer. To address the missing values, we introduce a feature propagation algorithm. The spatial module equipped with the attention mechanism is used to capture these two distinct levels of spatial information. Moreover, the temporal pattern attention module is applied to more effectively mine features over time. Experiments using license plate recognition data from Xi'an, China, demonstrate that our HTLGC model outperforms baseline algorithms under various missing data rates.

Effective estimation and prediction of freeway congestion propagation is the basis for formulating a traffic management strategy. A new estimation and prediction model for congestion propagation based on coordinated vehicle positioning data collected from fixed detectors is proposed. A shockwave-based method is established to model the propagation trajectory of congestion in time and space using data filtered by the Savitzy-Golay. Bayesian ridge regression is applied to determine the probability range of the propagation path of the congestion. The proposed method was tested with Wi-Fi positioning data from a section of the Beijing-Kunming Freeway in China. The results of our method were compared with filed traffic conditions estimated by loop data. The results show a difference of approximately 200s between the start time of the estimated congestion and the observed time on the selected road section. The predicted congestion start time differs from the observed results by around 100s.

The operation and management of the metro system in urban areas rely on accurate predictions of future passenger flow. While using all the available information can potentially improve on the accuracy of the flow prediction, there has been little attention to the hierarchical relationship between the type of tickets collected from the passengers entering/exiting a station and its resulting passenger flow. To this end, we propose a novel Integrative Prediction Framework with the Hierarchical Message-Passing Graph Neural Network (IPF-HMGNN). The proposed framework consists of three components: initial prediction, task judgment and hierarchical coordination modules. Using the Wuxi, China metro network as an example, we study two prediction approaches (i) traditional prediction approach where the model directly predicts passenger flow at the station, and (ii) hierarchical prediction approach where the prediction of ticket type and station passenger flow are performed simultaneously considering the hierarchical constraints (i.e., the sum of predicted passenger flow per ticket type equals the predicted station aggregated passenger flow). Experimental results indicate that in the traditional prediction approach, our IPF-HMGNN can significantly reduce the mean absolute error (MAE) and root mean square error (RMSE) of the GNN prediction model by 49.56 prediction approach, IPF-HMGNN can achieve a maximum reduction of 35.32 and 36.18

Metro operation management relies on accurate predictions of passenger flow in the future. This study begins by integrating cross-city (including source and target city) knowledge and developing a short-term passenger flow prediction framework (METcross) for the metro. Firstly, we propose a basic framework for modeling cross-city metro passenger flow prediction from the perspectives of data fusion and transfer learning. Secondly, METcross framework is designed to use both static and dynamic covariates as inputs, including economy and weather, that help characterize station passenger flow features. This framework consists of two steps: pre-training on the source city and fine-tuning on the target city. During pre-training, data from the source city trains the feature extraction and passenger flow prediction models. Fine-tuning on the target city involves using the source city's trained model as the initial parameter and fusing the feature embeddings of both cities to obtain the passenger flow prediction results. Finally, we tested the basic prediction framework and METcross framework on the metro networks of Wuxi and Chongqing to experimentally analyze their efficacy. Results indicate that the METcross framework performs better than the basic framework and can reduce the Mean Absolute Error and Root Mean Squared Error by 22.35 compared to single-city prediction models.

Smart cities require advanced traffic management systems. Traffic forecasting is an essential task of the advanced transportation system. Traffic spatio-temporal data are often heterogeneous. Most existing traffic prediction models predominantly use separate components to extract the temporal and spatial features of traffic data. However, this overlooks the intrinsic connections between the spatio-temporal features of traffic data. To directly mine the spatio-temporal heterogeneity, this study constructs a global heterogeneous traffic spatio-temporal graph and proposes the Heterogeneous Traffic Spatio-Temporal Graph Convolution (HTSTGC). To reduce the complexity of the model, Simple Graph Convolution (SGC) is used to extract semi-structured meta-graph information. The receptive fields that capture temporal and spatial features can be flexibly adjusted separately through clever design, which can balance the performance and efficiency of the model. Finally, the feature fusion module applies Gated Graph Neural Network (GGNN) to fuse temporal and spatial features. The results on the PEMS datasets reveal that jointly modeling different types of relationships can improve the traffic prediction performance of the model. The proposed HTSTGC has better performance than the baseline methods in most cases. The research results can support urban traffic control, traffic pollution reduction, and sustainable urban development.

The application of UAVs in orchard management presents a substantial opportunity to enhance efficiency and promote environmentally friendly agricultural production. While individual UAVs encounter limitations, such as endurance constraints, these challenges can be mitigated through collaborative efforts involving multiple vehicles and UAVs. This study addresses the issue of multi-UAV cooperative orchard path planning with multiple vehicles by formulating a mathematical optimization model aimed at minimizing the maximum UAV operation time. In the proposed model, the vehicle solely provides batteries and supplies to the UAV. To efficiently solve this model, we propose an improved Simulated Annealing-Lin Kernighan Helsgaun (SA-LKH) algorithm. The proposed algorithm utilizes the K-means and convex hull algorithm to generate the initial solution. Subsequently, the paths of each group of UAVs and vehicles are optimized based on the LKH algorithm. Additionally, we construct a directed perturbation operator that perturbs the maximum and minimum time-consuming paths to achieve fast convergence of the algorithm. The results from four different cases demonstrate that, compared to the general variable neighborhood search algorithm, the improved Ant Colony Algorithm and Improved Genetic Algorithm, the proposed algorithm has demonstrated an average improvement in solution quality of 3.41%, 5.72% and 9.67%, respectively. The proposed method effectively enhances the solution quality, which can provide valuable insights into green cleaning management of orchards.

OBJECTIVE:Vehicle automation technologies have the potential to address the mobility needs of older adults. However, age-related cognitive declines may pose new challenges for older drivers when they are required to take back or "takeover" control of their automated vehicle. This study aims to explore the impact of age on takeover performance under partially automated driving conditions and the interaction effect between age and voluntary non-driving-related tasks (NDRTs) on takeover performance. METHOD:A total of 42 older drivers (M = 65.5 years, SD = 4.4) and 40 younger drivers (M = 37.2 years, SD = 4.5) participated in this mixed-design driving simulation experiment (between subjects: age [older drivers vs. younger drivers] and NDRT engagement [road monitoring vs. voluntary NDRTs]; within subjects: hazardous event occurrence time [7.5th min vs. 38.5th min]). RESULTS:Older drivers exhibited poorer visual exploration performance (i.e., longer fixation point duration and smaller saccade amplitude), lower use of advanced driving assistance systems (ADAS; e.g., lower percentage of time adaptive cruise control activated [ACCA]) and poorer takeover performance (e.g., longer takeover time, larger maximum resulting acceleration, and larger standard deviation of lane position) compared to younger drivers. Furthermore, older drivers were less likely to experience driving drowsiness (e.g., lower percentage of time the eyes are fully closed and Karolinska Sleepiness Scale levels); however, this advantage did not compensate for the differences in takeover performance with younger drivers. Older drivers had lower NDRT engagement (i.e., lower percentage of fixation time on NDRTs), and NDRTs did not significantly affect their drowsiness but impaired takeover performance (e.g., higher collision rate, longer takeover time, and larger maximum resulting acceleration). CONCLUSIONS:These findings indicate the necessity of addressing the impaired takeover performance due to cognitive decline in older drivers and discourage them from engaging in inappropriate NDRTs, thereby reducing their crash risk during automated driving.

Accurate and reliable short-term forecasting of passenger flows can ensure the operation of urban rail trans-port.Considering the differences in the timing characteristics of passenger flows at different stations,a deep learning method for predicting passenger flows at urban stations is developed based on station classification.Firstly,stations are classified by dynamic time warping and the K-means algorithm,and the timing characteristics of the passenger flow of various stations are analyzed.Secondly,the complete ensemble empirical mode decomposition with adaptive noise is used to decompose passenger flow data of various stations to reduce the effects of data noise.Finally,a deep learning pre-diction method integrating long short-term memory and Transformer model is proposed to predict the passenger flow of different types of stations.The method is verified by using the passenger flow data of Xi'an Metro.The results show that the stations can be classified into four types according to the timing characteristics of passenger flow data on working days and non-working days:occupation-residential balance type,business office type,leisure and entertainment type,and dense residential type.Compared with the other three single models and three combined models,mean absolute error of passenger flow prediction results of the proposed method in different types of stations is reduced by 16.36%～51.02%,root mean square error is reduced by 10.35%～50.76%,and mean absolute percentage error is reduced by 14.71%～48.62%.Compared with the other six models,the prediction results of the station passenger flow data based on the statis-tics of different time intervals of 15 min,30 min,45 min and 60 min,the three indicators are respectively reduced by 12.63%～51.02%,8.08%～49.12%and 6.83%～47.26%.

Accurately assessing the resilience of the road network is crucial for responding to emergencies and enhancing public safety. Signal control plays a significant role in managing traffic flow. However, its impact is often overlooked in resilience assessments, where traffic flow and signal control are usually considered separately. A Movement-Specific Resilience (MSR) assessment model is proposed to integrate signal timing into resilience analysis. To accurately represent traffic flow paths under phase control, a dual graph is used to depict the topological network, allowing the assessment of relationships among all movements at an intersection. Based on this, a cascading failure model is developed to analyze the impact of signal control on traffic flow reassignment, reflecting how signal timing influences traffic flow propagation after failures. The method is validated using data collected from a sub-road network in Xi'an city. Results reveal the cumulative resilience of single lanes is not equivalent to the resilience of road segments. The MSR is higher when the network's failure degree is low and decreases as the failure level increases. Furthermore, road saturation is inversely related to MSR, while MSR is proportional to capacity. MSR remains unaffected by failures and oversaturation when capacity exceeds a certain threshold. These insights could be a theoretical foundation for bolstering resilience via signal control adjustments.

The Time Space Diagram (TSD) can abstractly represent multiple data sources and the macroscopic state of road traffic. However, the TSDs may be incomplete due to missing data, which seriously affects traffic management. Therefore, this paper proposed a Multi-Directional Recurrent Graph Convolutional Network (MDRGCN) for reconstructing TSDs and estimating missing traffic speeds given sparse data. We designed multi-directional RNN layers for scanning the TSDs from horizontal and vertical directions, which can fully exploit the contextual dependencies of the traffic information. In addition, our model includes graph convolution layers for mining potential spatial correlations in the TSDs. The performance of the model reconstructed from TSDs is validated on the NGSIM dataset. We also provided a comparison with other advanced methods, and the experimental results show that our method can perform well at both low and high missing rates, significantly outperforming the baseline methods.

For sophisticated management, advertisement placement, and epidemic prevention control of urban rail transit (URT), accurate and real-time predictions of passenger flows at different levels are of great importance. Unlike traditional prediction tasks, hierarchical prediction (HP) requires that the hierarchical constraints be satisfied as much as possible (the sum of the predicted passenger flow of child nodes should nearly equal the parent node) to achieve realistic predictions. This article proposes a multiobjective HP (MOHP) framework with an error compensation (EC) mechanism for predicting URT passenger flow with a hierarchical structure. Three components are included: the initial prediction module, the EC module, and the hierarchical coordination module. In the initial prediction module, the initial passenger flow prediction of each layer is carried out. The EC model is developed based on proportional-integral-derivative control to compensate for the initial predicted value of every layer. As a final step, a trainable HP model is constructed based on deep learning to coordinate the prediction values of each layer. As examples, we construct three scenarios of passenger flow hierarchy based on the URT system in Wuxi, China. The constructed prediction framework is used to conduct experimental analyses. As a result, the MOHP-EC prediction framework could satisfy the hierarchical constraints and use the passenger flow hierarchical information to reduce prediction errors. The mean absolute error was reduced by 35%, and the root-mean-square error was reduced by 39%.

针对新建公共自行车站点无法根据历史数据对未来使用需求进行预测的问题,提出了一种修正的地理加权回归模型探索单位时间节点需求生成与可达性间的关系.改进的模型以路网距离作为限制条件,获取基于泰森多边形的站点吸引重叠区域.同时,为减小用地区位导致的预测误差,改进的模型增添用地混合度和建筑强度作为解释变量.利用所提出的模型对西安市公共自行车系统运营数据分析的结果表明,各类用地最大需求生成率集中在早晚高峰时段,并在以天为周期的循环中具有各异的变化规律.公共自行车系统的需求生成率随着起点/终点与目标停靠站点之间距离增大而逐渐减小,表现为早高峰时期的线性衰减,晚高峰时期的指数衰减以及非高峰时期的立方衰减.研究成果可用于确定西安市新建公共自行车站点位置和规模,并预测其相应的使用需求率.

为探究平面交叉口不同严重程度交通事故影响因素的关联特性,从驾驶人、环境、道路、车辆4个维度出发,建立了带约束的二进制粒子群-蚁群算法以挖掘交叉口事故严重程度的关联规则.首先通过二进制粒子群算法确定最优提升度和支持度阈值,再利用蚁群算法挖掘最大频繁项集,并增加规则前项与后项的约束,以提高关联规则挖掘效率.对2 022条平面交叉口事故数据的分析结果表明,提出的BPSO-ACA算法可在精准识别潜在因素与事故等级关联结果的基础上减少冗余无效关联规则,并将规则挖掘效率提升17％-29％.驾驶人年龄、分心状态、交叉口形态、交叉口车道数和天气均与交叉口事故严重程度有强关联性;车道数少是导致轻微事故升级为一般事故的重要因素;路面湿滑是导致交叉口事故升级为重大事故的关键因素,尤其在雨雪雾等不良天气条件下,机非事故为重大等级的可能性最高.研究成果可为交通管理部门的主动防控措施提供理论指导,减少交叉口事故数量及降低事故严重程度.