Journal of Advanced Transportation最新文献

{"title":"A Macroscopic Continuum Framework for Urban Traffic With Dynamic Curbside Parking Activity","authors":"Gabriel Obed Fosu,&nbsp;Fredrick Asenso Wireko,&nbsp;Richard Owusu","doi":"10.1155/atr/2124080","DOIUrl":"https://doi.org/10.1155/atr/2124080","url":null,"abstract":"<p>Urban traffic performance is strongly shaped by interactions between moving vehicles and curbside activities such as parking maneuvers, deliveries, and ride-hailing pickups. These interactions modify effective capacity and driver behavior in ways not captured by conventional macroscopic traffic models. This study introduces the macroscopic activity and roadside parking (MARP) model, a continuum framework that couples vehicle motion with parking and rejoining dynamics through mass exchange, obstruction-dependent equilibrium velocity, and nonlocal blockage effects. Linear stability analysis establishes explicit threshold conditions under which curb occupancy and temporary obstructions destabilize the flow, while weakly nonlinear analysis reduces the governing system to a Korteweg–de Vries (KdV)–Burgers equation that characterizes the evolution of stop-and-go waves near the instability boundary. Numerical simulations demonstrate that the model reproduces key qualitative features of urban traffic dynamics, including smooth capacity recovery under parking bans, congestion waves triggered by double parking, and oscillatory bottlenecks arising from spatially distributed pickup demand. The results show that curb activity acts as a dynamic source of localized and distributed perturbations, capable of reshaping traffic flow while maintaining system-level stability under certain conditions. The proposed model provides a basis for evaluating corridor-level impacts of curb management strategies within a consistent macroscopic setting.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/2124080","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386705","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":"Integrated Sliding-Mode Predictive Control With Adaptive Switching Function for Trajectory Tracking of Distributed Drive Electric Vehicles","authors":"Qianyi Tong","doi":"10.1155/atr/1712882","DOIUrl":"https://doi.org/10.1155/atr/1712882","url":null,"abstract":"<p>Distributed drive electric vehicles (DDEVs) offer significant advantages for trajectory tracking through independent wheel torque control. However, coupled longitudinal-lateral dynamics, parameter uncertainties and external disturbances pose substantial challenges for controller design. This paper proposes an integrated sliding-mode predictive control (SMPC) strategy that synergistically combines model predictive control (MPC) and sliding-mode control (SMC) for DDEV trajectory tracking. A control-oriented 3-DOF vehicle model is developed with explicit separation of controllable inputs and bounded disturbances. The lateral controller features an adaptive switching function continuously updated by the MPC’s rolling optimization, enabling robust disturbance rejection while maintaining predictive performance. An analytical MPC solution minimizes computational burden, and Lyapunov-based stability analysis guarantees convergence despite bounded uncertainties. Longitudinal velocity is regulated by a PI controller, and an optimal force distribution module based on adhesion utilization minimization translates high-level commands to individual wheel torques while respecting friction and actuator constraints. Comprehensive simulations using CarMaker under multiple scenarios, including double-lane change, sine wave trajectory with varying speed and disturbance rejection tests, demonstrate that SMPC reduces tracking errors by 28%–61% and disturbance-induced deviations by 42%–65% compared to PID, pure MPC and pure SMC benchmarks. The adaptive switching function effectively mitigates chattering while maintaining robustness, and the analytical solution ensures real-time feasibility with an average computation time of 2.3 ms. The proposed SMPC strategy provides an effective, robust and computationally practical solution for DDEV trajectory tracking, offering a compelling balance between predictive optimization and disturbance rejection for autonomous driving applications.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/1712882","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386598","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":"Presenting Spatial Data Mining Based on a Stage-Interpretable Multilayer Deep Learning Approach to Analyze the Factors Affecting the Crash Frequency of Light Vehicles in Rural Freeways","authors":"Amirmohammad Ramezanpoor,&nbsp;Meysam Effati","doi":"10.1155/atr/3783288","DOIUrl":"https://doi.org/10.1155/atr/3783288","url":null,"abstract":"<p>Some studies show that most light vehicle crashes occur on rural freeways. Crash frequency analysis presents significant challenges due to the complexity of large-scale datasets, hidden intervariable relationships, limited interpretability, and the influence of segmentation methods used. The present study aims to provide an innovative stage-interpretable multilayer perceptron (SI-MLP) method based on deep learning for quantitative and spatial analysis of the effect of geometric factors, weather conditions, and traffic parameters on the crash frequency by presenting a combined dynamic–static segmentation approach in rural freeways. The stage-interpretable method makes the interpretability of deep learning algorithm results possible by stepwise feature omission and assessing its impact on model accuracy. To this aim, significant variables were selected using a decision tree algorithm in conjunction with the Pearson correlation test. The Poisson regression model was utilized to compare the results with those of the proposed SI-MLP method due to the discrete nature of the data and the ability of such an algorithm to model the crash frequency. TabNet was also considered as a benchmark to assess the proposed SI-MLP, since it supports both crash frequency classification (enabling direct accuracy comparison with the MLP-based formulation) and regression-based crash frequency estimation as a numerical outcome. The results revealed that the proposed SI-MLP outperforms the Poisson regression model and the TabNet benchmark in identifying influential crash factors, owing to its ability to capture complex patterns and relationships and to extract high-level features from crash data enriched with geometric and weather information. In the three-class setting (low, medium, and high crash frequency levels), the SI-MLP achieved an overall accuracy of 0.81 and a Macro-F1 of 0.81. Based on the results, the vehicle type and color, license type, temperature, driver’s age, lighting conditions, and front collision with a fixed object were identified as variables affecting the crash frequency. In the next step, the effective variables identified by the proposed method were analyzed using thematic kernel density maps to model the clustering patterns and spatial autocorrelation of the crash frequency, with an emphasis on the most effective factors. Identifying key contributing factors within high-crash segments using the proposed approach allows for the formulation of targeted safety priorities and supports the deployment of proactive countermeasures in segments with the highest risk.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/3783288","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386830","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":"Bibliometric Analysis of Transport Infrastructure Hypernetwork: Review and Prospects","authors":"Zhiguo Shao,&nbsp;Fei Wang,&nbsp;Mengdi Li,&nbsp;Cui Li","doi":"10.1155/atr/1332400","DOIUrl":"https://doi.org/10.1155/atr/1332400","url":null,"abstract":"<p>The transport infrastructure is transitioning into a multilayer, multifunctional hypernetwork form, posing challenges to traditional single-mode planning methods in analyzing cross-system risk transmission mechanisms and achieving spatiotemporal resource optimization. This leads to suboptimal system synergy and resilience. By examining articles on TIH research from 2002 to 2025 in the Web of Science core database, this study utilizes VOSviewer and CiteSpace bibliometric analysis software to visualize annual publication volumes, countries, journals, authors, institutions, keywords, and cocitations. It identifies hotspots and trends in TIH research across time and space dimensions. While research on the TIH commenced early, significant growth occurred only in the past 5 years. Current research predominantly focuses on multiagent trajectory prediction, cross-modal fusion, and resilient multilayer networks. The knowledge structure analysis presented in this study elucidates the evolution of knowledge and frontier breakthroughs in TIH research, offering insights to scholars in the field. This empirical evidence supports multimode collaborative modeling, intelligent resilience technology development, and policy formulation to enhance the operational efficiency and disaster response capabilities of hypernetwork systems. This study advocates for theoretical innovation to support the sustainable development of infrastructure in alignment with carbon-neutral goals.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/1332400","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148387005","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":"Impact of Level 3 Automated Driving Technology on Road Work Zone Safety","authors":"Zhepu Xu,&nbsp;Ziyi Song,&nbsp;Shiyu Zhang,&nbsp;Jiatong Song,&nbsp;Yupu Dong,&nbsp;Peiyan Chen","doi":"10.1155/atr/6396683","DOIUrl":"https://doi.org/10.1155/atr/6396683","url":null,"abstract":"<p>As China’s road infrastructure transitions into a maintenance-focused era, work zones are becoming increasingly prevalent. Concurrently, Level 3 (L3) automated vehicles are poised to become a regular feature on roadways. However, the interaction between these vehicles and work zones presents a unique safety challenge: L3 automation may disengage under specific work zone conditions, potentially impacting traffic safety in complex and unpredictable ways. This paper investigates the implications of L3 automated driving technology (ADT) on expressway work zone safety and its ramifications for traffic management. Employing microscopic traffic simulation and all-type traffic conflict analysis, we examine the influence of market penetration rate (MPR), traffic volume, disengagement threshold, and driver takeover behavior. Safety performance is evaluated using three complementary indicators, namely, disengagement events, minimum risk maneuver (MRM) events, and traffic conflicts. Our findings reveal a nuanced impact, often contrary to expectations. The results show that ADT does not uniformly improve work zone safety; rather, its effects vary across safety indicators and traffic conditions. L3 disengagement from automated mode can lead to new traffic conflicts if driver takeover is inadequate or delayed. In general, higher MPR tends to reduce conflict occurrence, although its safety benefits are not uniform across all indicators and scenarios. Therefore, future research and development should prioritize optimizing disengagement detection systems and enhancing driver takeover mechanisms to improve safety and ensure smoother traffic flow within work zones. The findings also suggest that traffic management strategies in work zones should be adapted to mixed-traffic environments involving both automated and human-driven vehicles.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/6396683","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148325049","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":"A Study of Vehicle Control Under Mixed Traffic Flows: A Three-Layer Control Framework With Real-Time Signal-Trajectory Coordination at Isolated Intersections","authors":"Junman Dong,&nbsp;Xianglong Sun,&nbsp;Ningning Wang","doi":"10.1155/atr/8980121","DOIUrl":"https://doi.org/10.1155/atr/8980121","url":null,"abstract":"<p>Traditional signal control methods are difficult to adapt to the dynamic demands of mixed traffic flows from connected and automated vehicles (CAVs) and connected vehicles (CVs), leading to mismatches in spatial and temporal resources, conflicting control objectives, and uncontrolled cascade effects. Therefore, we propose a single-intersection signal-trajectory cooperative control framework with “hierarchical interaction-dynamic coupling.” Vehicle level: construct an improved intelligent driver model (IDM) to portray CV-induced response behavior, and design an adaptive cruise control (ACC)/cooperative adaptive cruise control (CACC) dual-mode switching mechanism to realize CAV’s adaptive safety following of the front vehicle type. Intersection level: establish a mixed-integer linear programming (MILP) dynamic signal timing model, couple NEMA dual-ring phase structure with vehicle arrival time window constraints, and propose a dynamic platoon splitting strategy. Trajectory level: CAV eco-driving trajectories are generated using piecewise trigonometric velocity profiles to optimize signal timing and vehicle trajectories jointly. SUMO simulations demonstrate that the proposed framework reduces average delay by 50% and fuel consumption by 37% under 60% CAV penetration, improves traffic throughput, and provides an effective solution for mixed traffic scenarios.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/8980121","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324939","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":"VR Simulator–Based Study to Explore Pedestrian–Vehicle Collisions at Unsignalized Intersections","authors":"Bo Wang,&nbsp;Jian Zhang,&nbsp;Yu Qian,&nbsp;Xiaomeng Shi,&nbsp;Mao Ye","doi":"10.1155/atr/3841145","DOIUrl":"https://doi.org/10.1155/atr/3841145","url":null,"abstract":"<p>The unsignalized intersections are areas where right-of-way rules are complex, and pedestrians face an increased risk of injury. Despite extensive research on pedestrian behaviors at intersections, there is a need for comprehensive studies that systematically identify the factors influencing pedestrian–vehicle collisions at unsignalized intersections to enhance pedestrian safety in a targeted manner. This research, therefore, investigated the pedestrian crossing behavior in a simulator-based virtual reality environment, with a total of twenty-seven variables (e.g., gender, age, area of residence, and history of jaywalking) and 784 samples. Then, a binary logistic regression model was employed to examine the specific impacts of these factors on pedestrian–vehicle collisions from the perspective of pedestrian behaviors, individual characteristics, and external environments. Results showed that males and younger individuals are more likely to have a higher risk of pedestrian–vehicle collisions than females and middle-aged individuals; those who have a history of jaywalking were more likely to have a higher risk of pedestrian–vehicle collisions; the Myers–Briggs Type Indicator (MBTI) of ENFP, ENTP, INFP, ESFP, and INTP significantly increase the risk of pedestrian–vehicle collisions; and the presence of oversize vehicles in critical areas and implementation interventions reduce the risk of pedestrian–vehicle collisions. Conversely, factors such as alcohol consumption, carrying luggage, and using mobile phones all contribute to an increased risk of pedestrian–vehicle collisions; more observations before crossing intersections and a greater number of pedestrians waiting in the same direction can both reduce the risk of pedestrian–vehicle collisions. The findings not only provide a theoretical basis for predicting pedestrian–vehicle collisions and enhancing active prevention strategies for pedestrian safety but also contribute to creating a safer driving environment for autonomous vehicles in real-world settings within the context of China.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/3841145","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324821","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":"Appraising Machine Learning Algorithms for Modeling of Road Accident Counts by Severity in Nigeria","authors":"Solomon O. Giwa,&nbsp;Raymond T. Taziwa,&nbsp;Oguntola J. Alamu,&nbsp;Mohsen Sharifpur","doi":"10.1155/atr/4334754","DOIUrl":"https://doi.org/10.1155/atr/4334754","url":null,"abstract":"<p>Road accidents are caused by several causative factors leading to various degrees of injury and death. This paper explored the capability of diverse machine learning algorithms in predicting the counts of road accident severity in Nigeria. Road accident data (number of accidents, causative factors, and degrees of casualty) used in this study were sourced from the National Bureau of Statistics. The correlation coefficient and analysis of variance were performed on the data. The input parameters, which were the number of accidents resulting from 18 accident causative factors, were used to predict the output parameters (minor, fatal, and serious) using different machine learning algorithms (simple linear and linear regression, random tree, support vector machine, and artificial neural network [ANN]). These algorithms were used to develop models to predict the counts by the severity (minor, fatal, and serious) of road accidents. The correlation coefficient and analysis of variance revealed that brake failure (as a mechanical factor) had the highest correlation coefficients (0.9765—fatal, 0.9842—serious, and 0.8375—minor) for the accident severity with significantly identical datasets (<i>p</i> value &lt; 0.05). The models developed using the ANN algorithm had the highest <i>R</i>² (92.6% for fatal, 98.7% for serious, and 89.9% for minor) for predicting the counts of accident severity, and these were associated with the lowest error values for the studied error metrics. These results showed the predictive power of the ANN algorithm to forecast the underlying nonlinear and intricate patterns inherent in the data used in this work. However, other developed machine learning models performed moderately well in predicting all the accident severities. The work demonstrated the prediction capability of the ANN algorithm in modeling accident severities and the possibility of utilizing machine learning algorithms to predict the counts of road accident severity in Nigeria.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/4334754","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324822","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":"Research on Collision Risk Warning Methods for Vulnerable Road Users at Unsignalized Intersections","authors":"Rui Cheng,&nbsp;Xu Gao,&nbsp;Yunjian Bi,&nbsp;Junji Dai,&nbsp;Tao Wang,&nbsp;Bingheng Yang,&nbsp;Enchu Li","doi":"10.1155/atr/7113421","DOIUrl":"https://doi.org/10.1155/atr/7113421","url":null,"abstract":"<p>Unsignalized intersections pose high collision risks between motor vehicles and vulnerable road users (VRUs). To enhance safety, this study proposes a collision warning method integrating trajectory prediction and dynamic risk assessment. UAV aerial footage was processed using YOLOv7-DeepSort for multiobject detection and tracking, constructing a high-precision trajectory dataset capturing VRU–vehicle interactions. A trajectory prediction model based on bidirectional extended long short-term memory (Bi-xLSTM) was designed, combining bidirectional LSTM’s sequential modeling with xLSTM’s enhanced memory to accurately capture VRU behavior and environmental interactions. Experiments show pedestrian and nonmotorized vehicle trajectory prediction achieved average displacement errors (ADEs) of 0.55 and 0.30 m and final displacement errors (FDEs) of 0.87 and 0.45 m, respectively, significantly outperforming traditional models. Building on this, an elliptical dynamic risk field–based warning model was proposed. It dynamically assesses potential collision risks by fusing Bi-xLSTM predictions with real-time vehicle states. Incorporating dynamic features like vehicle shape, speed sensitivity, and direction dependence and optimizing the risk field algorithm and warning thresholds via a two-level warning mechanism based on braking analysis, the model significantly improves warning timeliness and accuracy. Simulations demonstrated F1 scores of 96.26% (pedestrian) and 96.88% (nonmotorized vehicle), surpassing TTC and DTC algorithms, validating their robustness and practicality. This research provides theoretical and technical support for safety interventions at unsignalized intersections.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/7113421","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324823","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":"Dynamic Traffic Demand Forecasting Based on Microzone: A Spatial Analysis of Smart Card Data Using Machine Learning Methodologies","authors":"Kyoungtae Kim,&nbsp;Inmook Lee,&nbsp;Solsaem Choi,&nbsp;Ki-Han Song","doi":"10.1155/atr/5849967","DOIUrl":"https://doi.org/10.1155/atr/5849967","url":null,"abstract":"<p>This study seeks to develop an innovative dynamic model for predicting public transportation traffic volume. Current static traffic demand forecasting models suffer from significant drawbacks, as they struggle to adapt to real-time changes due to their rigid reliance on fixed time intervals and limited datasets. To overcome these constraints, the research strategically divides regions into microzones and constructs a flexible forecasting model by examining traffic volume variations across microzones and trip contexts, leveraging smart card data and comprehensive socioeconomic indicators. To improve the precision of forecasting, a SHapley Additive ExPlanations (SHAP) analysis was performed to pinpoint the most significant variables. These key variables were subsequently re-extracted from the original dataset and utilized as input parameters for the model. The primary independent variables encompassed traffic-related factors, including transfer frequency, direct distance between the origin and destination points, and integrated stop IDs for both the starting and ending locations. Furthermore, the analysis incorporated socioeconomic indicators such as population size, household count, workforce numbers, sales area, associative area, and the number of hospitals at both the origin and destination points. To uncover the spatial dynamics of traffic volume, a random forest model was utilized to evaluate the significance of critical variables and predict traffic flow patterns. Additionally, Bayesian linear regression and ordinary least squares (OLS) analyses were implemented to examine explanatory relationships and explore the nuanced characteristics of direct demand models. The predictive capabilities of each forecasting approach were subsequently compared and assessed. In this study, dynamic refers to an operationally updatable microzone forecasting framework rather than an explicit time-step time-series model. This research aims to address urban mobility challenges by developing a sophisticated approach to predict traffic volumes. By conducting detailed spatial analysis, identifying critical influencing factors, and creating precise forecasting models at the microzone level, the study seeks to help reduce traffic congestion and optimize public transportation system performance in real time.</p>","PeriodicalId":50259,"journal":{"name":"Journal of Advanced Transportation","volume":"2026 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/atr/5849967","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324502","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}