Journal of Advanced Transportation最新文献

{"title":"Integrated Aircraft Routing Problem Under Stochastic Delays","authors":"Ruoyu Li,&nbsp;Yehan Dou,&nbsp;Yangyan Shi,&nbsp;F. J. Hwang,&nbsp;Junbin Wang","doi":"10.1155/atr/7019633","DOIUrl":"https://doi.org/10.1155/atr/7019633","url":null,"abstract":"<p>Within the competitive landscape of civil aviation, achieving precision in decision-making is crucial for enhancing enterprise competitiveness and revenue. This study addresses the integrated aircraft routing problem by combining flight scheduling, fleet assignment, and routing problems into an integrated framework. The stochastic attribute of flight delays poses significant challenges to decision-making, necessitating consideration within the decision process. This research proposes an integrated aircraft routing model, incorporating real-world constraints and features such as optional flights and buffer times to absorb stochastic delay impacts. A novel column generation algorithm is employed to efficiently solve the model, which includes a greedy optimal insertion algorithm for initializing decision variables and a labeling-setting algorithm for subproblem exploration. The study emphasizes the importance of accurately setting flight buffer times to mitigate stochastic delay risks. Numerical experiments on a benchmark competition dataset show that the proposed algorithm improves the initial solution by about 19% within 10.67 s and yields solutions within 10% of the MILP optimum. Sensitivity analysis further indicates that increasing the pool size of the labeling-setting algorithm from 100 to 2000 raises the objective value by about 6.1% while increasing CPU time from 2.55 to over 300 s, highlighting the trade-off between schedule quality and computational effort in practical airline applications. This research contributes to both theoretical understanding and practical optimization of aircraft routing in dynamic operational environments, holding significant implications for civil aviation management.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/7019633","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CWAP-Net: A Causal Weather-Aware Spatiotemporal Graph Framework for Short-Term Airport Stand Capacity Prediction","authors":"Pinzheng Qian,&nbsp;Jian Zhang,&nbsp;Duxin Chen,&nbsp;Haiyan Zhang,&nbsp;Xunhao Li","doi":"10.1155/atr/9019906","DOIUrl":"https://doi.org/10.1155/atr/9019906","url":null,"abstract":"<p>Accurate short-term forecasting of airport stand capacity is essential for resilient surface operations and adaptive gate coordination under rapidly evolving weather conditions. However, existing methods often degrade during adverse or transitional weather because they fail to represent how meteorological factors structurally reconfigure airport operational constraints. This study proposes CWAP-Net, a weather-aware spatiotemporal graph learning framework for short-term airport stand capacity prediction. The main innovation of CWAP-Net lies in explicitly modeling weather-induced structural reconfiguration of airport stand interactions rather than treating meteorological variables as passive exogenous inputs. Specifically, the framework integrates a stand-level spatial graph with a mechanism-consistent weather graph constructed from structured METAR and TAF bulletins to encode directional and temporal weather influences. Rather than performing causal discovery, CWAP-Net embeds domain-consistent operational mechanisms to constrain interaction patterns under nonstationary conditions. Another key innovation is the introduction of a decision-relevant learning objective that differentiates prediction errors according to their operational consequences, thereby prioritizing capacity-critical deviations that are more consequential for gate coordination and surface operation decisions. CWAP-Net is evaluated using multisource operational and meteorological data from Qingdao Jiaodong International Airport from January to March 2024. Results show that CWAP-Net outperforms representative sequence-based and graph-based baselines in RMSE, MAE, and <i>R</i>², with improved stability during rapidly changing weather. Robustness experiments covering eight-quarters from 2023 to 2024 further confirm its effectiveness across seasonal weather regimes.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/9019906","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Opening Low-Altitude Corridors Near Major Hubs: A Baseline Assessment of Civil Aviation Transportation and Safety","authors":"Yang Chao,&nbsp;Ge Xinxin","doi":"10.1155/atr/1703947","DOIUrl":"https://doi.org/10.1155/atr/1703947","url":null,"abstract":"<p>Low-altitude corridor development is accelerating across Asia, raising practical questions about how emerging unmanned and urban air mobility operations may interact with conventional hub airport performance once sustained corridor activity becomes observable. This study constructs a preintegration baseline assessment for 18 major Asian hub airports using monthly data from 2019 to 2022. Public ADS-B records from the OpenSky Network are combined with NOAA Global Summary of the Day weather aggregates and airport structural descriptors to derive three airport-month indicators: arrival-spacing dispersion, short-gap share at or below 120 s and relative runway-use intensity benchmarked to each airport’s 2019 peak arrival rate. Because sustained, credibly coded corridor activation is not observable within the study window, corridor treatment effects are not estimated. Two-way fixed-effects models show that higher monthly movements are associated with lower log-transformed spacing dispersion (<i>β</i> = −2.06 × 10⁻⁴, <i>p</i> &lt; 0.001) and a higher short-gap share (<i>β</i> = 1.30 × 10⁻⁵, <i>p</i> &lt; 0.001). In the relative runway-use intensity model, more adverse weather is associated with lower runway-use intensity for the reference group, while high-density and CDM interaction terms are not statistically robust. Robustness checks using raw and winsorised variance, lower-tail spacing, pandemic-period exclusion, 2019-only estimation and removal of sparse-coverage hubs preserve the negative movement coefficient for spacing dispersion. The study contributes a reproducible measurement pipeline and strategic monitoring framework for corridor-readiness screening before sustained low-altitude corridor integration, rather than a causal evaluation of corridor effects.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/1703947","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"School Commuting in Lisbon: Exploratory Research on Active and Public Transportation Choices","authors":"Miguel San Payo,&nbsp;Gabriel Cipriano,&nbsp;Susana C. Martins,&nbsp;Antonio R. Andrade","doi":"10.1155/atr/9320090","DOIUrl":"https://doi.org/10.1155/atr/9320090","url":null,"abstract":"<p>In the past decades, there has been a significant growth in awareness related to the impacts of school commuting in metropolitan areas. The use of public transport and the promotion of active transportation choices among educational communities are key issues for the development of sustainable and efficient cities. This paper explores multiple factors, which range from the socioeconomic sphere to the built environment and safety around schools and also includes variables such as the proximity of the school to public transport stations/stops, the school grade and the school type (i.e., public or private schools). This paper aims to study how all these factors influence two different school commuting choices in Lisbon, Portugal: (1) the choice between active versus motorised travel modes and (2) the choice between public versus private transport modes. The <i>Hands Up</i> survey database, which includes 10 different modes for school commuting, was analysed to estimate binomial logistic regression models. The results suggest that school commuting independence happens at younger ages for public school students than for private school students and that a higher socioeconomic status has a negative impact regarding the use of public transport and active commuting to school. The planning of the public transport network is also pivotal since the close proximity of stations/stops of certain commuting modes discourages active commuting to school.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/9320090","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Collision Type Prediction Involving Elderly Drivers: A Machine Learning Framework With Explainability Using Kolmogorov–Arnold Networks","authors":"Philip F. Balyagati,&nbsp;Ntemi Methusela Masanja,&nbsp;Abdul S. Ngereza,&nbsp;Emmanuel Kidando,&nbsp;Angela Kitali","doi":"10.1155/atr/1828684","DOIUrl":"https://doi.org/10.1155/atr/1828684","url":null,"abstract":"<p>Elderly drivers represent a growing and vulnerable population on U.S. roadways, exhibiting distinct collision patterns and heightened risk of severe injury. Accurate prediction and interpretation of collision types involving this demographic are critical for developing targeted safety interventions. This study evaluates the performance of four machine learning models—Kolmogorov–Arnold Networks (KANs), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Traditional Neural Networks (TNNs)—in classifying the manner of collision among elderly drivers using data from the Fatality Analysis Reporting System (FARS). KANs offer a novel, interpretable neural network architecture that can capture complex nonlinear relationships with explicit feature representations, addressing the interpretability challenge common in deep learning. Model performance is assessed through accuracy, balanced accuracy, macro and weighted F1-scores, and confusion matrices, while SHapley Additive exPlanations (SHAP) provide insight into feature importance and interaction effects. Results indicate that KANs achieve competitive predictive performance comparable to RF, XGBoost, and TNNs, with the added advantage of enhanced interpretability. SHAP analysis reveals key predictors and feature interactions influencing the predicted collision type, such as the combined effect of speed limit and roadway surface condition shifting predictions toward angle and head-on configurations and the interaction of lighting and weather influencing the model’s distinction across collision types. These findings demonstrate the potential of interpretable machine learning approaches to improve understanding of crash configurations among elderly drivers, enabling more informed policy and engineering interventions.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/1828684","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vehicle to Two-Wheeler Accident Severity Prediction Optimization Using IGWO-Enhanced LightGBM","authors":"Xiaojian Yi,&nbsp;Lin Hu,&nbsp;Qiqi Li,&nbsp;Ruizhe Yan","doi":"10.1155/atr/7547060","DOIUrl":"https://doi.org/10.1155/atr/7547060","url":null,"abstract":"<p>The growing complexity of car to two-wheeler accident patterns underscores the urgent need for sustainable solutions in traffic safety research. Current limitations in analyzing key variables and predicting accident severity hinder the effectiveness of prevention strategies, highlighting a critical gap in achieving sustainability goals. Traditional LightGBM approaches, while valuable, require extensive hyperparameter tuning and often suffer from overfitting, compromising model accuracy and long-term sustainability. To address these challenges, this study proposes an improved gray wolf optimization (IGWO)-optimized LightGBM classification model, integrating sustainability principles to enhance accident severity prediction. The IGWO algorithm employs a dynamic weight allocation mechanism for fitness coefficients and a nonlinear step-size update strategy, significantly improving convergence precision and reducing susceptibility to local optima, key factors for sustainable model performance. Experimental results demonstrate IGWO’s superior convergence accuracy compared with baseline GWO (<i>p</i> &lt; 0.05), validating its potential for sustainable optimization. The IGWO–LightGBM model achieves balanced parameter tuning, ensuring robustness and reproducibility, cornerstones of sustainable research. Shapley Additive exPlanations (SHAP) analysis identifies the collision type as the most influential feature (SHAP value: 1.5, 42 percent higher than others), guiding targeted interventions. Environmental and spatiotemporal analyses identify critical sustainability risks; road accidents with higher severity levels occur when adhesion coefficients drop below 0.4 during winter midnight periods. These findings advocate for prioritizing high-conflict scenarios, low-adhesion road maintenance, and temporal risk management to foster sustainable traffic safety.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/7547060","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-Time Prediction of UAV Pilot Operational Errors and Adaptive Threshold Optimization Under Temporal Models","authors":"Mengmeng Duan,&nbsp;Pengfei Feng,&nbsp;Huiqing Jin,&nbsp;Shulin Zhang,&nbsp;Mingyu Lu,&nbsp;Zhenghe Hu","doi":"10.1155/atr/8464674","DOIUrl":"https://doi.org/10.1155/atr/8464674","url":null,"abstract":"<p>Operational errors by UAV pilots have become a critical bottleneck constraining the safe development of the industry. Existing prediction methods mostly adopt unified models while neglecting the impact of individual pilot capability differences on error patterns. This study proposes a real-time prediction framework for UAV pilot operational errors that integrates multidimensional adaptability features. Through a dual-channel network architecture, it separately extracts operational temporal features and pilot adaptability features, utilizes a pilot-conditional attention mechanism to inject static adaptability profiles as biases into temporal predictions, and designs an adaptive threshold optimization algorithm based on adaptability weighting to dynamically adjust warning parameters according to pilot capability levels. Based on large-scale measured data from 665 pilots, including seven adaptability indicators—finger dexterity, control function, depth perception, dynamic visual acuity, speed estimation, motion stability, and complex reaction—experimental results demonstrate that the fusion model achieves 89.7% accuracy, an AUC value of 0.928, and an average warning time of 3.2 s, significantly outperforming traditional methods. Complex reaction, control function, and motion stability contribute most to error prediction, accounting for 28.3%, 25.6%, and 19.5%, respectively. The adaptive threshold strategy reduces the false negative rate of the low-adaptability group by 50.4% and the false positive rate of the high-adaptability group by 64.6%. The model maintains stable performance across five scenarios—takeoff, cruise, hover, emergency avoidance, and landing—and maintains 84.6% accuracy under 20% data missing conditions. The research outcomes provide technical support for the transformation of UAV operational safety management from post-incident analysis to proactive prevention and from unified standards to personalized adaptation, offering important guidance for pilot selection, training, and intelligent assistance system design.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/8464674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Driving Change in Trucker Safety: A TCCM-Based Synthesis and Conceptual Framework for Understanding Truck Collision Risks","authors":"Sana Chodri,&nbsp;Aida Haghighi,&nbsp;Hossein Zolfagharinia","doi":"10.1155/atr/8047513","DOIUrl":"https://doi.org/10.1155/atr/8047513","url":null,"abstract":"<p>Truck-involved collisions represent a critical occupational hazard for commercial drivers, contributing to elevated rates of severe injuries, fatalities, and significant economic disruption across the freight industry. Despite extensive research, existing findings remain fragmented, as most studies focus on isolated risk factors rather than exploring how multiple elements might interact to influence collision outcomes for truck drivers. This systematic literature review (SLR) synthesizes findings from 98 peer-reviewed empirical studies published from 2014 to 2023, applying the theory, context, characteristics, and methodology (TCCM) framework to categorize and critically analyze key risk factors. A new conceptual framework was developed to depict two levels of empirically supported relationships: overarching factor-to-outcome effects and more granular subfactor interactions. Results revealed important interactive effects among driver behaviors (e.g., fatigue and substance use), vehicle characteristics (e.g., truck configuration and weight), environmental conditions (e.g., weather and visibility), and roadway and collision attributes (e.g., road geometry and collision type). This integrated approach clarifies fragmented evidence, identifies critical research gaps, and highlights the complex, multidimensional nature of truck collision risk. The findings also offer transportation policymakers and safety planners an evidence-based tool to prioritize high-impact risk factors, design targeted interventions, and develop predictive safety models.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/8047513","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy-Saving Optimization of Urban Rail Transit Operation Considering Onboard Energy Storage Devices","authors":"Lianbo Deng,&nbsp;Huaru Liu,&nbsp;Zijian Guo,&nbsp;Yangting Qu","doi":"10.1155/atr/6359116","DOIUrl":"https://doi.org/10.1155/atr/6359116","url":null,"abstract":"<p>To address the energy-saving optimization problem of urban rail transit train operation, this paper proposes a collaborative optimization method for onboard energy storage device (OBESD) capacity configuration and train interstation operation strategies. Based on a train multi-interval operation model and a train energy flow model, a collaborative optimization framework is established with the objective of minimizing the total life-cycle cost, comprehensively considering both OBESD investment costs and train operational energy consumption costs. Constraints including multi-interval train operation, fixed interstation running times, OBESD charging/discharging power and capacity, and passenger riding comfort are incorporated into the model. With the number of OBESD modules and train speed profiles as decision variables, an energy-saving optimization model considering multi-interval train dynamics and time-varying energy flow is developed. To solve the model, a dual-layer optimization algorithm is proposed. The outer layer determines the optimal number of OBESD modules using a fixed-step search strategy, while the inner layer optimizes train operation strategies under a given storage configuration using a simulated annealing algorithm based on multiparameter speed combinations. This approach enables collaborative optimization between train operation strategies and onboard energy storage capacity. The proposed method is validated using real-world operational data from Guangzhou Metro Line 1. The results show that the proposed model can effectively reduce train net energy consumption while strictly satisfying interstation running time constraints, achieving an energy-saving rate of 13.90% for full-line operation. In addition, sensitivity analysis results indicate that the optimal OBESD configuration is significantly influenced by economic parameters such as electricity price, storage investment cost, and life-cycle years, highlighting the important role of economic conditions in practical engineering applications. The findings provide practical decision support for urban rail transit operators in configuring onboard energy storage systems to achieve cost-effective energy savings.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/6359116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Truck Driver’s Psychological State on Long Downhill Sections Based on LSTM Neural Network","authors":"Yan Zhang,&nbsp;Xia Luo,&nbsp;Zhongze Tang,&nbsp;Yunyong He,&nbsp;Enhuai He,&nbsp;Jianping Gao","doi":"10.1155/atr/9358484","DOIUrl":"https://doi.org/10.1155/atr/9358484","url":null,"abstract":"<p>Long downhill sections on mountainous expressways pose elevated safety risks for heavy trucks, yet most existing studies emphasize vehicle performance rather than driver psychological state. This study uses the average percentage change in pupil size (APCPS) as a pupillometry-based proxy of truck drivers’ psychological fluctuations and proposes a unit-based, time-series prediction framework. Four real-world trips were conducted on a 48-km long downhill section of the G50 Expressway (China) using a Smart Eye eye-tracking system. Guided by driver behavioral adaptation theory, the section was divided into a driving-in unit, an adaptation unit, and a driving-out unit, and the associations between APCPS and key alignment variables (horizontal curve radius, CCR, average longitudinal grade, and continuous downgrade length) were quantified for each unit (e.g., driving-in: curvature change rate <i>r</i> = 0.726, <i>p</i> = 0.043; slope <i>r</i> = −0.668, <i>p</i> = 0.016). Previous research has used LSTM to analyze driver states, but most of these studies have focused on either simpler terrain or broader driver data without considering the specific dynamics of complex terrains like long downhill sections. This study’s novelty lies in the unit-based analysis, where each segment of the downhill section is treated as a distinct unit influenced by different alignment features. An LSTM-based model with unit-specific inputs was then trained and evaluated using a hold-out split (80% training and 20% independent test) to predict APCPS. The model achieved low prediction errors, with MAPE of 3.85%, 3.97%, and 3.26% (MAE: 0.02, 0.01, and 0.01) in the driving-in, adaptation, and driving-out units, respectively. The proposed framework can support real-time in-vehicle warnings and vehicle–infrastructure communication for long downhill sections, and it provides quantitative evidence for alignment design control and safety facility placement.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/9358484","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}