Different from the traditional deterministic user equilibrium (DUE) model based on fixed travel time, the stochastic user equilibrium (SUE) model is established by assuming the perceived route travel time as a random variable. It plays an important role in traffic assignment, wherein the setting of route choice parameters decides system performance. This article studies parameter calibration of widely used SUE models including the multinomial logit (MNL), length-based C-logit (LCL), and congestion-based C-logit (CCL) models. We establish a bilevel model in which the upper level is designed to minimize the error between the real and model-based traffic flow patterns, whereas the lower level copes with the SUE traffic assignment. A series of innovative methods are built to solve this bilevel model. Considering the nonlinear calibration problem in the upper level, a Bayesian optimization method is used. For the SUE traffic assignment in the lower level, dedicated algorithms are proposed, which combine a partial linearization algorithm and a feasible direction method. Furthermore, two revised solution methods are provided: a Barzilai–Borwein (BB) step-size method and a parallel framework. Finally, the proposed model and corresponding solution approach are validated based on a case study of Yuyao, China. Solutions show that the CCL SUE model has the highest precision while requiring the longest computation time. LCL takes only 11.7% of the computation time of CCL when reaching an acceptable precision.

The reliability of urban transportation systems is crucial for ensuring smooth traffic flow and minimizing disruptions caused by external factors. This study focuses on improving the stability and efficiency of transportation systems through the calibration of a refined link performance function while building upon the U.S. Bureau of Public Roads (BPR) model. To achieve this, we propose three customized algorithms—Newton’s method, Bayesian optimization, and the differential evolutionary algorithm—to calibrate the key parameters. Additionally, we conducted a sensitivity analysis to assess the influences of the model parameters on link performance. Numerical experiments conducted in Yuyao City demonstrate the applicability and efficacy of the proposed model and solution algorithms. Our results reveal that the Newton approach is notably more efficient than the Bayesian optimization algorithm and the differential evolutionary algorithm.

As network scale and demand rise, the Uncapacitated Facility Location Problem (UFLP), a classical NP-hard problem widely studied in operations research, becomes increasingly challenging for traditional methods confined to formulation, construction, and benchmarking. This work generalizes the UFLP to network setting in light of demand intensity and network topology. A new initialization technique called Network- and Demand-Weighted Roulette Wheel Initialization (NDWRWI) has been introduced and proved to be a competitive alternative to random (RI) and greedy initializations (GI). Experiments were carried out based on the TRB dataset and compared eight state-of-the-art methods. For instance, in the ultra-large-scale Gold Coast network, the NDWRWI-based Neighborhood Search (NS) achieved a competitive optimal total cost (9,372,502), closely comparable to the best-performing baseline (RI-based: 9,189,353), while delivering superior clustering quality (Silhouette: 0.3859 vs. 0.3833 and 0.3752 for RI- and GI-based NS, respectively) and reducing computational time by nearly an order of magnitude relative to the GI-based baseline. Similarly, NDWRWI-based Variable Neighborhood Search (VNS) improved upon RI-based baseline by reducing the overall cost by approximately 3.67%, increasing clustering quality and achieving a 27% faster runtime. It is found that NDWRWI prioritizes high-demand and centrally located nodes, fostering high-quality initial solutions and robust performance across large-scale and heterogeneous networks.

As a key component of inland waterway infrastructure, the structural integrity of waterway revetments is directly related to navigation safety and aquatic ecological stability. However, in complex inland water environments, the process of damage detection and hazard prevention is confronted with numerous challenges. These include intense background interference, a high missed detection rate for small-scale damage, and insufficient real-time performance. To address the aforementioned issues, this paper proposes DH-YOLO, a lightweight architecture for damage detection. Building upon the efficient YOLOv8n backbone, the proposed model enhances feature sampling and discriminability capabilities through the task-specific integration of the Dynamic Upsampler (Dy_Sample) and the Hybrid Attention Transformer Head (HATHead) modules. This study emphasizes the detection of damage presence, rather than its classification or recognition. Evaluated on a custom-built image dataset of revetment damage, the proposed method achieves a Precision of 81.5%, Recall of 76.9%, mAP50 of 81.7%, and mAP50–95 of 48.6%, while maintaining a low computational cost of 6.9 GFLOPs. These results indicate that compared with mainstream models, the proposed algorithm achieves a favorable overall trade-off between accuracy and efficiency, and exhibits application potential for real-time damage detection and hazard prevention in complex inland waterway environments.

This paper addressed the problem of highway traffic flow multivariate time series forecasting with the challenges of variate heterogeneity. To improve forecast performance without a heavy computational burden in large-scale networks, we innovatively introduced variational mode decomposition and established a decomposition-assisted multi-tasking deep learning forecasting architecture. To improve variate-specific pattern learning and mitigate pattern mixing, we proposed a novel temporal-frequency pure convolutional neural network incorporating discrete Fourier transform, deepwise convolution, and batchwise feedforward neural network. To verify the proposed model, we conducted a case study on a regional network located in Jiangsu, China. Results demonstrate strong forecast performance and efficient computation. The proposed model offers suitability toward highway operators for large-scale engineering deployment and better facilitates their managerial actions.

Autonomous vehicle platooning improves overall energy efficiency and enhances road capacity through close-range cooperative driving. However, practical deployment under complex real-world conditions remains challenging due to sensor noise, model uncertainties, and actuator nonlinearities. This study presents a hierarchical control framework that integrates multisource sensor fusion and a controller combining longitudinal Model Predictive Control (MPC) with Lateral Feedforward-Feedback Control (LFFC) with data-driven improvement. First, a prediction-correction fusion module combines wheel odometry (ODOM), inertial measurement units (IMUs), and Global Positioning System (GPS) measurements to obtain continuous and globally consistent vehicle state estimates. Second, an MPC-LFFC-based physical controller is developed, where longitudinal MPC optimizes velocity corrections and lateral LFFC combines curvature feedforward with proportional feedback of heading and lateral errors. Third, a data-driven improvement module comprises an offline conservative Q-learning (CQL) agent that automatically calibrates controller parameters and a neural residual learning network that predicts feedforward compensation. Extensive experiments on a real-world vehicle platooning platform demonstrate that the proposed framework consistently outperforms baselines, achieving a position Root Mean Square Error (RMSE) of 0.0781 m and a 30.66% improvement in linear velocity tracking.