Accurate and efficient forecasting of energy consumption is a crucial prerequisite for effective energy planning and policymaking. The BP neural network has been widely used in forecasting, machine learning, and various other fields due to its nonlinear fitting ability. In order to improve the prediction accuracy of the BP neural network, this paper introduces the concept of forecast lead time and establishes a mathematical model accordingly. Prior to training the neural network, the input layer data are preprocessed based on the forecast lead time model. The training and forecasting results of the BP neural network when and when not considering forecast lead time are compared and verified. The findings demonstrate that the forecast lead time model can significantly improve the prediction speed and accuracy, proving to be highly applicable for short-term energy consumption forecasting.

Sustainable highway infrastructure maintenance critically depends on precise lane line detection, yet conventional inspection approaches remain resource-depleting, carbon-intensive, and hazardous to personnel. To mitigate these constraints and address the low accuracy and high parameterization of existing models, this study utilizes unmanned aerial vehicle (UAV) imagery and proposes a UAV-based highway lane line segmentation method using an improved DeepLabV3+ model that resolves multi-scale lane line segmentation challenges in UAV imagery. MobileNetV2 is used as the backbone network to significantly reduce the number of model parameters. The Squeeze-and-Excitation (SE) attention mechanism is integrated to enhance feature extraction capabilities, particularly at lane line edges. A Feature Pyramid Network (FPN) is incorporated to improve multi-scale lane line feature extraction. We introduce a novel Waterfall Atrous Spatial Pyramid Pooling (WASPP) module, utilizing cascaded atrous convolutions with strategic dilation rate adjustments to progressively expand the receptive field and aggregate contextual information across scales. The improved model outperforms the original DeepLabV3+ by 5.04% mIoU (85.30% vs. 80.26%) and 3.35% F1-Score (91.74% vs. 88.39%) while cutting parameters by 85% (8.03 M vs. 54.8 M) and reducing training time by 2 h 50 min, thereby enhancing the model’s accuracy in lane line segmentation, reducing the number of parameters, and lowering the carbon footprint.

With the rapid expansion of highway networks, the demand for timely and reliable road information has steadily increased. However, some guide signs on newly built or extended highways in China have not been updated or adjusted in time, resulting in incomplete information and non-standard setups. These issues not only affect drivers’ navigation experience but may also negatively impact road safety and traffic efficiency. Therefore, it is crucial to establish a scientifically sound evaluation system and a comprehensive assessment model for highway guide signs. This study selected a representative highway (G2 Expressway in China) as the research subject and combined questionnaire surveys with field investigations to identify common issues such as vague information and irregular placement of guide signs. Through an in-depth analysis of travel demand, the core requirements of drivers were summarized as safety, efficiency, and comfort. Based on these insights, the study proposes four key design principles for guide signs: standardization, readability, continuity, and consistency. A set of quantifiable evaluation indicators was developed through a comprehensive analysis of key factors affecting signage performance, and factor analysis was applied to verify the independence and rationality of the indicators. On this basis, an evaluation model was constructed using the technique for order preference by similarity to ideal solution (TOPSIS) to scientifically quantify the effectiveness of guide signs. The model was applied in a field study on the Hebei section of the G2 Expressway in China (with comprehensive traffic sign coverage, high traffic volume, and more traffic sign issues), with results demonstrating the feasibility and practicality of the proposed evaluation system and model. This research offers a systematic solution to enhance the service quality of highway guide signs and provides essential references for future highway planning and management practices. It aims to comprehensively improve drivers’ travel experiences and promote the development of sustainable and intelligent transportation networks, offering valuable insights for building integrated urban systems.

The guide signs at expressway play an important role in conveying road information to drivers. To study the reasonable setting of guide signs at expressway with consecutive dense exits, firstly, a bidirectional eight-lane expressway segment model were constructed with three exit ramp scenarios: “single exit”, “consecutive double exits”, and “consecutive triple exits”. Two groups of schemes (standard group and optimized group) for guide signs were set, resulting in 10 different experimental comparison schemes. Secondly, thirty-two licensed drivers were recruited to conduct experimental tests using a driving simulation platform. Then four types of experimental data related to driving operations are collected: participants’ subjective perception, vehicle operation safety, driving maneuvers smoothness, and cumulative eye movement comfort. These data were used to compare and analyze the 10 different design schemes of guide signs, determining the optimal design alternatives for expressway segment with three exit ramp scenarios. The comparative analysis of the experimental data across the three exit ramp scenarios revealed that factors such as ramp spacing, guide signs content, and placement distance of guide signs significantly impact vehicle safety and comfort. There is an inverse relationship between ramp spacing and both vehicle safety and driving comfort. The participants’ visual recognition efficiency is enhanced by optimizing the content and placement distance of the guide sign effectively, further ensuring the safe and smooth operation of vehicles. This study can effectively reduce traffic conflicts at expressway exit ramps and decrease the incidence of traffic accidents. Additionally, it provides solid theoretical support for the design and sustainable development of expressway traffic facilities.

Given the severe global traffic safety challenges—including threats to human lives and socioeconomic impacts—this study analyzes visual behavior to promote sustainable transportation, improve road safety, and reduce resource waste and pollution caused by accidents. Four typical road sections, namely, turning, straight ahead, uphill, and downhill, were selected, and the eye movement data of 23 drivers in different driving stages were collected by aSee Glasses eye-tracking device to analyze the visual gaze characteristics of the drivers and their transfer patterns in each road section. Using Markov chain theory, the probability of staying at each gaze point and the transfer probability distribution between gaze points were investigated. The results of the study showed that drivers’ visual behaviors in different road sections showed significant differences: drivers in the turning section had the largest percentage of fixation on the near front, with a fixation duration and frequency of 29.99% and 28.80%, respectively; the straight ahead section, on the other hand, mainly focused on the right side of the road, with 31.57% of fixation duration and 19.45% of frequency of fixation; on the uphill section, drivers’ fixation duration on the left and right roads was more balanced, with 24.36% of fixation duration on the left side of the road and 25.51% on the right side of the road; drivers on the downhill section looked more frequently at the distance ahead, with a total fixation frequency of 23.20%, while paying higher attention to the right side of the road environment, with a fixation duration of 27.09%. In terms of visual fixation, the fixation shift in the turning road section was mainly concentrated between the near and distant parts of the road ahead and frequently turned to the left and right sides; the straight road section mainly showed a shift between the distant parts of the road ahead and the dashboard; the uphill road section was concentrated on the shift between the near parts of the road ahead and the two sides of the road, while the downhill road section mainly occurred between the distant parts of the road ahead and the rearview mirror. Although drivers’ fixations on the front of the road were most concentrated under the four road sections, with an overall fixation stability probability exceeding 67%, there were significant differences in fixation smoothness between different road sections. Through this study, this paper not only reveals the laws of drivers’ visual behavior under different driving environments but also provides theoretical support for behavior-based traffic safety improvement strategies.

Filling-type large-size cement-stabilized macadam (F-LSBC) is a promising base material for mitigating reflection cracking in semi-rigid pavements. However, its engineering application is hindered by the challenge of balancing strength, crack resistance, and construction adaptability. More fundamentally, the relationship between micromechanical features—especially the interfacial transition zone (ITZ)—and the macroscopic behavior of filling-type cement-stabilized composites remains insufficiently understood. This study used conventional cement-stabilized macadam (CSM) as a reference and combined nanoindentation with macro-scale mechanical, fatigue, and drying shrinkage tests to clarify the micro–macro mechanisms of F-LSBC. Results show that the ITZ in F-LSBC exhibits substantially lower elastic modulus (reduced by 60–75%) and hardness (reduced by 55%), along with greater porosity and phase volume fraction than CSM. Cluster analysis revealed a thicker ITZ (55–90 μm vs. 40 μm), indicating notable interfacial weakening. These microstructural features lead to reduced strength and fatigue life. Nevertheless, due to its high coarse aggregate content and weak-interface-induced “crack-without-displacement” mechanism, F-LSBC demonstrates enhanced shrinkage resistance, with drying shrinkage reduced to 81.36% of that of CSM at 180 days. The findings emphasize the key role of ITZ characteristics in determining performance and suggest that improved interface engineering could enhance durability and shrinkage control in pavement bases.