International Journal of Transportation Science and Technology最新文献_第7页

Evaluating rail transit assignment models in the temporal dimension: The problem and its solution 从时间维度评估轨道交通分配模型：问题及其解决方案

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-06-01 DOI: 10.1016/j.ijtst.2024.05.008

Wei Zhu , Jin Wei , Changyue Xu

Passenger flow is the foundation for urban rail transit (URT) operations. However, its calculated results from assignment models may deviate from the actual situation in both spatial and temporal dimensions, which arouses more attention and needs to be evaluated in particular. On the other hand, onboard video data from URT trains provides a potential way for model evaluation. This study defines the evaluation problem, and proposes a methodological solution for evaluating rail transit assignment models in the temporal dimension, which includes qualitative validation and difference quantification. A suitable time granularity is determined for the best effectiveness, and onboard video data are used for actual passenger flow extraction. The gap between the actual and calculated data by the model is identified with nonparametric statistical techniques (NPSTs) and quantified with time series similarity measurement (TSSM) methods. A case study on the Shanghai metro demonstrates the performance of the proposed approach, and several practice implications for URT operation agencies are discussed.

客流是城市轨道交通运行的基础。然而，其分配模型的计算结果可能在空间和时间维度上偏离实际情况，这引起了更多的关注，尤其需要进行评估。另一方面，来自轨道交通列车的车载视频数据为模型评估提供了一种潜在的方法。本文对评价问题进行了界定，并提出了一种在时间维度上评价轨道交通分配模型的方法解决方案，包括定性验证和差异量化。确定合适的时间粒度以获得最佳效果，并将车载视频数据用于实际客流提取。该模型利用非参数统计技术（NPSTs）识别实际数据与计算数据之间的差距，并利用时间序列相似性度量（TSSM）方法对其进行量化。以上海地铁为例，论证了该方法的有效性，并对轨道交通运营机构的实践启示进行了讨论。

{"title":"Evaluating rail transit assignment models in the temporal dimension: The problem and its solution","authors":"Wei Zhu , Jin Wei , Changyue Xu","doi":"10.1016/j.ijtst.2024.05.008","DOIUrl":"10.1016/j.ijtst.2024.05.008","url":null,"abstract":"<div><div>Passenger flow is the foundation for urban rail transit (URT) operations. However, its calculated results from assignment models may deviate from the actual situation in both spatial and temporal dimensions, which arouses more attention and needs to be evaluated in particular. On the other hand, onboard video data from URT trains provides a potential way for model evaluation. This study defines the evaluation problem, and proposes a methodological solution for evaluating rail transit assignment models in the temporal dimension, which includes qualitative validation and difference quantification. A suitable time granularity is determined for the best effectiveness, and onboard video data are used for actual passenger flow extraction. The gap between the actual and calculated data by the model is identified with nonparametric statistical techniques (NPSTs) and quantified with time series similarity measurement (TSSM) methods. A case study on the Shanghai metro demonstrates the performance of the proposed approach, and several practice implications for URT operation agencies are discussed.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"18 ","pages":"Pages 96-114"},"PeriodicalIF":4.3,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141407584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and assessment of trajectory-based arterial through percent arrivals on red for arterial signal coordination performance evaluation 开发和评估基于轨迹的干道红灯到达百分比，用于干道信号协调性能评估

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-06-01 DOI: 10.1016/j.ijtst.2024.06.001

Jianyuan Xu , Zong Tian , Aobo Wang , Gang Xie , Luis Valenzuela

Efficient traffic signal system management plays a pivotal role in reducing traffic congestion and improving traffic mobility on urban roads. The applications of the automated traffic signal performance measures (ATSPMs) revolutionize the way of proactively managing and evaluating traffic signal systems through a suite of performance measures. The percent arrival on red (PAoR) is one of the commonly used progression performance measures in the ATSPMs to characterize vehicle arrivals at the intersection. However, the accuracy of PAoR to assess arterial signal coordination is restricted by configuration limitations of advance detectors and remains to be further explored. To address this problem, this research proposes an easy-to-use trajectory-based performance measure, i.e., arterial through percent arrival on red (ATPAoR), for arterial signal coordination performance evaluation and presents the general procedures to calculate ATPAoRs from connected vehicle data. A case study is carried out to implement the proposed ATPAoR and investigate the relationship between the ATPAoR and the PAoR. It is found that the combination of the time-space diagram (TSD) and arterial through-vehicle trajectories is effective in the actual arterial signal coordination performance visualization, ATPAoR result interpretation, and potential timing improvement recommendations. The PAoRs are found to be greater than the ATPAoRs in undersaturated conditions, and the PAoRs above 60% are recommended to identify poor arterial signal coordination design. The historical TSD can be utilized to verify the accuracy of PAoR to evaluate the actual arterial signal coordination when vehicle trajectory data are unavailable.

有效的交通信号系统管理对缓解城市道路交通拥堵、提高交通机动性起着关键作用。自动交通信号性能测量（ATSPMs）的应用通过一套性能测量，彻底改变了主动管理和评估交通信号系统的方式。红灯到达百分比（PAoR）是ATSPMs中常用的进度性能指标之一，用于表征车辆到达交叉口的情况。然而，PAoR评估动脉信号协调性的准确性受到预先检测器配置限制，仍有待进一步探索。为了解决这一问题，本研究提出了一种易于使用的基于轨迹的性能度量，即动脉通过红到达百分比（ATPAoR），用于动脉信号协调性能评估，并给出了从联网车辆数据中计算ATPAoRs的一般程序。通过一个案例研究来实现所提出的ATPAoR，并探讨了ATPAoR和PAoR之间的关系。研究发现，时空图（TSD）与动脉穿过车辆轨迹的结合在实际动脉信号协调性能可视化、ATPAoR结果解释和潜在的时间改进建议方面是有效的。在不饱和条件下，PAoRs大于ATPAoRs，建议PAoRs大于60%，以识别动脉信号协调设计不良。历史TSD可用于验证PAoR的准确性，以评估车辆轨迹数据不可用时实际动脉信号协调情况。

{"title":"Development and assessment of trajectory-based arterial through percent arrivals on red for arterial signal coordination performance evaluation","authors":"Jianyuan Xu , Zong Tian , Aobo Wang , Gang Xie , Luis Valenzuela","doi":"10.1016/j.ijtst.2024.06.001","DOIUrl":"10.1016/j.ijtst.2024.06.001","url":null,"abstract":"<div><div>Efficient traffic signal system management plays a pivotal role in reducing traffic congestion and improving traffic mobility on urban roads. The applications of the automated traffic signal performance measures (ATSPMs) revolutionize the way of proactively managing and evaluating traffic signal systems through a suite of performance measures. The percent arrival on red (PAoR) is one of the commonly used progression performance measures in the ATSPMs to characterize vehicle arrivals at the intersection. However, the accuracy of PAoR to assess arterial signal coordination is restricted by configuration limitations of advance detectors and remains to be further explored. To address this problem, this research proposes an easy-to-use trajectory-based performance measure, i.e., arterial through percent arrival on red (ATPAoR), for arterial signal coordination performance evaluation and presents the general procedures to calculate ATPAoRs from connected vehicle data. A case study is carried out to implement the proposed ATPAoR and investigate the relationship between the ATPAoR and the PAoR. It is found that the combination of the time-space diagram (TSD) and arterial through-vehicle trajectories is effective in the actual arterial signal coordination performance visualization, ATPAoR result interpretation, and potential timing improvement recommendations. The PAoRs are found to be greater than the ATPAoRs in undersaturated conditions, and the PAoRs above 60% are recommended to identify poor arterial signal coordination design. The historical TSD can be utilized to verify the accuracy of PAoR to evaluate the actual arterial signal coordination when vehicle trajectory data are unavailable.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"18 ","pages":"Pages 131-147"},"PeriodicalIF":4.3,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141413145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessment of flooding impact on thin pavement structure in Texas coastal region 得克萨斯州沿海地区洪水对薄路面结构影响的评估

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-06-01 DOI: 10.1016/j.ijtst.2024.07.001

Feng Hong , Jolanda Prozzi

Over the recent years, transportation infrastructure in the United States have experienced numerous hurricanes or tropical storms usually accompanied with heavy rainfalls. This may lead to flooding on pavements and higher groundwater levels, causing soil erosion, slope instability, reduced pavement strength, and lower pavement’s load-bearing capacity, subsequently shortening pavement service life or increasing rehabilitation and maintenance costs. This study focuses on the impact of flooding on thin pavement structure with surface-treated pavements in Texas coastal region, which contains 6 277 lane miles of roads. First, at a project level, a mechanic-empirical (M-E) pavement design tool is used to analyze the pavement performance under flooding and non-flooding/normal conditions. Pavement life is estimated for different flooding timing cases. Second, simulations are run to evaluate the impact of flooding on the pavement life at a network level. Three flooding frequencies are highlighted: low, 100-year; medium, 50-year; and high, 20-year. By a comparison with non-flooding baseline, it is found that the pavement life for the entire weak pavement network in the coastal region can be reduced at varying degrees due to the flooding impact. The quantified pavement life reduction can serve to enhance pavement design practice and system management decision made in a proactive manner.

近年来，美国的交通基础设施经历了多次飓风或热带风暴，通常伴随着强降雨。这可能导致路面水浸及地下水位上升，造成水土流失、斜坡不稳、路面强度下降及路面承载能力下降，从而缩短路面的使用寿命或增加修复及维修费用。本研究的重点是洪水对德克萨斯州沿海地区表面处理的薄路面结构的影响，该地区包含6277车道英里的道路。首先，在项目层面，使用力学-经验（M-E）路面设计工具来分析在淹水和非淹水/正常条件下的路面性能。根据不同的水浸时间估算路面寿命。其次，在网络层面上进行了模拟，以评估洪水对路面寿命的影响。突出显示了三种洪水频率：低，100年；中,50年;最高的是20年。通过与未受洪水影响的基线对比，发现沿海地区整个薄弱路面网的路面寿命受到洪水影响会有不同程度的降低。量化的路面寿命减少可以提高路面设计实践和系统管理决策的主动性。

{"title":"Assessment of flooding impact on thin pavement structure in Texas coastal region","authors":"Feng Hong , Jolanda Prozzi","doi":"10.1016/j.ijtst.2024.07.001","DOIUrl":"10.1016/j.ijtst.2024.07.001","url":null,"abstract":"<div><div>Over the recent years, transportation infrastructure in the United States have experienced numerous hurricanes or tropical storms usually accompanied with heavy rainfalls. This may lead to flooding on pavements and higher groundwater levels, causing soil erosion, slope instability, reduced pavement strength, and lower pavement’s load-bearing capacity, subsequently shortening pavement service life or increasing rehabilitation and maintenance costs. This study focuses on the impact of flooding on thin pavement structure with surface-treated pavements in Texas coastal region, which contains 6 277 lane miles of roads. First, at a project level, a mechanic-empirical (M-E) pavement design tool is used to analyze the pavement performance under flooding and non-flooding/normal conditions. Pavement life is estimated for different flooding timing cases. Second, simulations are run to evaluate the impact of flooding on the pavement life at a network level. Three flooding frequencies are highlighted: low, 100-year; medium, 50-year; and high, 20-year. By a comparison with non-flooding baseline, it is found that the pavement life for the entire weak pavement network in the coastal region can be reduced at varying degrees due to the flooding impact. The quantified pavement life reduction can serve to enhance pavement design practice and system management decision made in a proactive manner.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"18 ","pages":"Pages 261-271"},"PeriodicalIF":4.3,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141688920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A systematic literature review of defect detection in railways using machine vision-based inspection methods 使用基于机器视觉的检测方法检测铁路缺陷的系统性文献综述

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-06-01 DOI: 10.1016/j.ijtst.2024.06.006

Ankit Kumar , S.P. Harsha

Train rolling stock and track inspections are necessary for the safe operation of the train. For this reason, a regular inspection of defects is required for the train rolling stock. The conventional defect detection methods yield low efficiency, consume more time, are unreliable, and are less cost-effective. These obstacles may be mitigated by integrating a machine vision-based inspection system (MVIS). This systematic literature review explores the landscape of railway defect detection methodologies, primarily focusing on leveraging image processing techniques. This comprehensive analysis encompasses many studies examining the evolution of image processing applications in the context of railway rolling stock and rail track defect detection. From traditional methods to the latest advancements, a nuanced understanding of the challenges and innovations in this domain is required. Key themes include utilizing computer vision algorithms, machine learning models, and deep learning techniques for enhanced accuracy in identifying defects. We delve into the intricacies of image acquisition, preprocessing, and feature extraction, shedding light on the pivotal role of these processes in refining defect detection systems. Also, the current gaps and opportunities for future research, emphasizing the need for standardized datasets, benchmarking methodologies, and the integration of emerging technologies, are highlighted. This review not only consolidates the existing knowledge, but also serves as a roadmap for researchers invested in advancing the field of railway defect detection. By synthesizing insights from many studies, this review contributes to a deeper understanding of the state-of-the-art in railway defect detection using image processing, fostering dialogue and collaboration for improving railway safety and reliability.

列车车辆和轨道检查是列车安全运行的必要条件。由于这个原因，需要对火车车辆的缺陷进行定期检查。传统的缺陷检测方法效率低、耗时长、不可靠、成本效益低。这些障碍可以通过集成基于机器视觉的检测系统（MVIS）来减轻。这篇系统的文献综述探讨了铁路缺陷检测方法的前景，主要集中在利用图像处理技术。这一综合分析包含了许多研究，研究了图像处理在铁路车辆和轨道缺陷检测方面的应用的演变。从传统方法到最新进展，需要对该领域的挑战和创新有细致入微的理解。关键主题包括利用计算机视觉算法、机器学习模型和深度学习技术来提高识别缺陷的准确性。我们深入研究了图像采集、预处理和特征提取的复杂性，揭示了这些过程在改进缺陷检测系统中的关键作用。此外，还强调了当前的差距和未来研究的机会，强调了对标准化数据集、基准方法和新兴技术集成的需求。这篇综述不仅巩固了现有的知识，而且为研究人员在铁路缺陷检测领域的发展提供了一个路线图。通过综合许多研究的见解，本综述有助于更深入地了解利用图像处理技术进行铁路缺陷检测的最新技术，促进对话和合作，以提高铁路的安全性和可靠性。

{"title":"A systematic literature review of defect detection in railways using machine vision-based inspection methods","authors":"Ankit Kumar , S.P. Harsha","doi":"10.1016/j.ijtst.2024.06.006","DOIUrl":"10.1016/j.ijtst.2024.06.006","url":null,"abstract":"<div><div>Train rolling stock and track inspections are necessary for the safe operation of the train. For this reason, a regular inspection of defects is required for the train rolling stock. The conventional defect detection methods yield low efficiency, consume more time, are unreliable, and are less cost-effective. These obstacles may be mitigated by integrating a machine vision-based inspection system (MVIS). This systematic literature review explores the landscape of railway defect detection methodologies, primarily focusing on leveraging image processing techniques. This comprehensive analysis encompasses many studies examining the evolution of image processing applications in the context of railway rolling stock and rail track defect detection. From traditional methods to the latest advancements, a nuanced understanding of the challenges and innovations in this domain is required. Key themes include utilizing computer vision algorithms, machine learning models, and deep learning techniques for enhanced accuracy in identifying defects. We delve into the intricacies of image acquisition, preprocessing, and feature extraction, shedding light on the pivotal role of these processes in refining defect detection systems. Also, the current gaps and opportunities for future research, emphasizing the need for standardized datasets, benchmarking methodologies, and the integration of emerging technologies, are highlighted. This review not only consolidates the existing knowledge, but also serves as a roadmap for researchers invested in advancing the field of railway defect detection. By synthesizing insights from many studies, this review contributes to a deeper understanding of the state-of-the-art in railway defect detection using image processing, fostering dialogue and collaboration for improving railway safety and reliability.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"18 ","pages":"Pages 207-226"},"PeriodicalIF":4.3,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141709521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Strength assessment of airport pavement based on Dempster-Shafer evidence and gray relation 基于 Dempster-Shafer 证据和灰色关系的机场路面强度评估

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-06-01 DOI: 10.1016/j.ijtst.2024.04.009

Chongwei Huang , Shanshan Wang , Hairui Meng , Dandan Guo , Yu Sun

The study focused on the influence of various engineering factors on the strength of rigid airport pavement. Based on different test schemes, we established indoor and outdoor tests, compared the strength test results, and quantitatively analyzed the impacts of mechanical damage, maintenance conditions, and construction technology on the splitting strength of rigid airport pavement. We further fitted the correction coefficients of the splitting strength of core samples with different height-diameter ratios. Dempster-Shafer (D-S) evidence theory and gray correlation analysis were used to analyze the correlation between the influencing factors and the pavement splitting tensile strength. The importance of the factors affecting the rigid airport pavement strength was then determined. The results showed that the loss rates of pavement splitting tensile strength caused by differences in construction technology, curing conditions, and mechanical damage were 6.90%, 4.43%, and 2.11%, respectively. The correlation between each influencing factor and pavement tensile strength was good. The degree of influence decreased in the following order: construction technology > curing conditions > mechanical damage. These findings can help the reasonable allocation of resources on construction sites.

研究了各种工程因素对机场刚性路面强度的影响。基于不同的试验方案，建立室内和室外试验，对比强度试验结果，定量分析机械损伤、养护条件、施工工艺等因素对机场刚性路面劈裂强度的影响。进一步拟合了不同高径比岩心试样劈裂强度的修正系数。采用D-S证据理论和灰色关联分析法对影响因素与路面劈裂抗拉强度的相关性进行了分析。确定了影响机场刚性路面强度因素的重要性。结果表明：施工工艺、养护条件和机械损伤差异造成的路面劈裂抗拉强度损失率分别为6.90%、4.43%和2.11%；各影响因素与路面抗拉强度的相关性较好。影响程度依次为：施工技术>；养护条件；机械损伤。这些发现有助于建筑工地资源的合理配置。

{"title":"Strength assessment of airport pavement based on Dempster-Shafer evidence and gray relation","authors":"Chongwei Huang , Shanshan Wang , Hairui Meng , Dandan Guo , Yu Sun","doi":"10.1016/j.ijtst.2024.04.009","DOIUrl":"10.1016/j.ijtst.2024.04.009","url":null,"abstract":"<div><div>The study focused on the influence of various engineering factors on the strength of rigid airport pavement. Based on different test schemes, we established indoor and outdoor tests, compared the strength test results, and quantitatively analyzed the impacts of mechanical damage, maintenance conditions, and construction technology on the splitting strength of rigid airport pavement. We further fitted the correction coefficients of the splitting strength of core samples with different height-diameter ratios. Dempster-Shafer (D-S) evidence theory and gray correlation analysis were used to analyze the correlation between the influencing factors and the pavement splitting tensile strength. The importance of the factors affecting the rigid airport pavement strength was then determined. The results showed that the loss rates of pavement splitting tensile strength caused by differences in construction technology, curing conditions, and mechanical damage were 6.90%, 4.43%, and 2.11%, respectively. The correlation between each influencing factor and pavement tensile strength was good. The degree of influence decreased in the following order: construction technology > curing conditions > mechanical damage. These findings can help the reasonable allocation of resources on construction sites.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"18 ","pages":"Pages 1-14"},"PeriodicalIF":4.3,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141029583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient implementation of a wavelet neural network model for short-term traffic flow prediction: Sensitivity analysis 小波神经网络模型在短期交通流量预测中的高效应用：敏感性分析

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-03-01 DOI: 10.1016/j.ijtst.2024.02.004

Sonia Mrad , Rafaa Mraihi , Aparna S. Murthy

The concept of a smart city is emerging to address significant challenges arising from rapid urbanization, economic growth, and climate change. Innovative technologies can be used as a means to promote sustainable and inclusive urban development. These technolgies include the deployment of the internet of things (IoT), artificial intelligence (AI), energy management, and smart transportation. In a smart city, intelligent transportation systems ITSs play a vital role in efficient traffic management. This paper explores the use of hybrid AI techniques for predicting short-term traffic flow data from M25 motorways in the UK. Since volume traffic flow data are non-stationary, wavelet transform (WT), as a powerful signal analyzer, is applied to signal decomposition for the elimination of redundant data from input matrices. The feature selection method based on the Gram-Schmidt (GS) orthogonalization process is used for the selection of more valuable features. The elimination of redundant data can speed up the learning process and improve the generalisation capability of the prediction models. After a pre-processing stage, a wavelet neural network (WNN) with a simple structure is applied as a powerful prediction tool. Two separate structures are considered for the prediction of weekday and weekend traffic volume data. The experiments explore that the debauchies-4 (db4) wavelet function with 7 decomposition levels leads to the best detection accuracy. Moreover, factors such as the range of forecasting, the type of the day, and the level of decomposition all have an impact on prediction stability. Compared with existing prediction methods, the proposed approach produces lower values of root mean square error (RMSE) and mean absolute percentage error (MAPE) for all step-horizons analyzed. These findings provide valuable implications and insights into the development of an efficient and reliable road condition monitoring system for delivering secure and sustainable transportation services.

智慧城市的概念正在兴起，以应对快速城市化、经济增长和气候变化带来的重大挑战。创新技术可以作为促进可持续和包容性城市发展的手段。这些技术包括物联网（IoT）、人工智能（AI）、能源管理和智能交通的部署。在智慧城市中，智能交通系统在高效的交通管理中起着至关重要的作用。本文探讨了使用混合人工智能技术预测英国M25高速公路的短期交通流量数据。由于体积交通流数据是非平稳的，将小波变换作为一种功能强大的信号分析工具，应用于信号分解中，消除输入矩阵中的冗余数据。基于Gram-Schmidt （GS）正交化过程的特征选择方法用于选择更有价值的特征。消除冗余数据可以加快学习过程，提高预测模型的泛化能力。经过预处理后，采用结构简单的小波神经网络作为预测工具。两种不同的结构被考虑用于平日和周末交通量数据的预测。实验发现，具有7个分解层次的debauchies-4 （db4）小波函数具有最佳的检测精度。此外，预测范围、天气类型、分解程度等因素都对预测稳定性有影响。与现有的预测方法相比，该方法对所分析的所有台阶层均产生较低的均方根误差（RMSE）和平均绝对百分比误差（MAPE）。这些发现为开发高效可靠的道路状况监测系统以提供安全和可持续的交通服务提供了宝贵的启示和见解。

{"title":"Efficient implementation of a wavelet neural network model for short-term traffic flow prediction: Sensitivity analysis","authors":"Sonia Mrad , Rafaa Mraihi , Aparna S. Murthy","doi":"10.1016/j.ijtst.2024.02.004","DOIUrl":"10.1016/j.ijtst.2024.02.004","url":null,"abstract":"<div><div>The concept of a smart city is emerging to address significant challenges arising from rapid urbanization, economic growth, and climate change. Innovative technologies can be used as a means to promote sustainable and inclusive urban development. These technolgies include the deployment of the internet of things (IoT), artificial intelligence (AI), energy management, and smart transportation. In a smart city, intelligent transportation systems ITSs play a vital role in efficient traffic management. This paper explores the use of hybrid AI techniques for predicting short-term traffic flow data from M25 motorways in the UK. Since volume traffic flow data are non-stationary, wavelet transform (WT), as a powerful signal analyzer, is applied to signal decomposition for the elimination of redundant data from input matrices. The feature selection method based on the Gram-Schmidt (GS) orthogonalization process is used for the selection of more valuable features. The elimination of redundant data can speed up the learning process and improve the generalisation capability of the prediction models. After a pre-processing stage, a wavelet neural network (WNN) with a simple structure is applied as a powerful prediction tool. Two separate structures are considered for the prediction of weekday and weekend traffic volume data. The experiments explore that the debauchies-4 (db4) wavelet function with 7 decomposition levels leads to the best detection accuracy. Moreover, factors such as the range of forecasting, the type of the day, and the level of decomposition all have an impact on prediction stability. Compared with existing prediction methods, the proposed approach produces lower values of root mean square error (RMSE) and mean absolute percentage error (MAPE) for all step-horizons analyzed. These findings provide valuable implications and insights into the development of an efficient and reliable road condition monitoring system for delivering secure and sustainable transportation services.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"17 ","pages":"Pages 21-38"},"PeriodicalIF":4.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139829934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Workforce forecasting for state transportation agencies: A machine learning approach 州交通机构的劳动力预测：机器学习方法

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-03-01 DOI: 10.1016/j.ijtst.2024.05.004

Adedolapo Ogungbire, Suman Kumar Mitra

A decline in the number of construction engineers and inspectors at state transportation agencies (STAs) to manage the ever-increasing lane miles has emphasized the importance of workforce planning in these agencies. Forecasting workforce requirements is crucial for effective planning in any industry or agency. This study developed machine learning (ML) models to estimate the person-hour requirements of STAs at the project level. The Arkansas Department of Transportation (ARDOT) was used as a case study, using its employee and project details data between 2012 and 2021. ML regression models ranging from linear, tree ensembles, kernel-based, and neural network-based models were developed. These models were compared based on the accuracy of their predictions, the time taken for training the models and their prediction time. Predictions were tested based on the K-fold cross validation technique. The results indicated a high performance from the random forest regression model, a tree ensemble with bagging, which recorded a mean R-squared value of 0.91. Other ML models such as an ensemble neural network model and the linear models also proved to be fit for the problem, attaining R squared value as high as 0.80 and 0.78, respectively. These findings underscore the capability of ML models to provide more accurate workforce demand forecasts for STAs and the construction industry. This enhanced accuracy in workforce planning will contribute to improved resource allocation and management.

管理不断增加的车道里程的州运输机构（STAs）的建筑工程师和检查员数量的下降，强调了这些机构劳动力规划的重要性。预测劳动力需求对于任何行业或机构的有效规划都是至关重要的。本研究开发了机器学习（ML）模型来估计项目级别sta的人-小时需求。阿肯色州交通部（ARDOT）被用作案例研究，使用了2012年至2021年期间的员工和项目详细信息数据。ML回归模型包括线性、树集成、基于核和基于神经网络的模型。根据预测的准确性、训练模型所需的时间和预测时间对这些模型进行比较。基于K-fold交叉验证技术对预测进行了测试。结果表明，随机森林回归模型具有较高的性能，其平均r平方值为0.91。其他ML模型，如集成神经网络模型和线性模型也被证明适合该问题，R平方值分别高达0.80和0.78。这些发现强调了机器学习模型为sta和建筑行业提供更准确的劳动力需求预测的能力。这种提高的劳动力规划准确性将有助于改进资源分配和管理。

{"title":"Workforce forecasting for state transportation agencies: A machine learning approach","authors":"Adedolapo Ogungbire, Suman Kumar Mitra","doi":"10.1016/j.ijtst.2024.05.004","DOIUrl":"10.1016/j.ijtst.2024.05.004","url":null,"abstract":"<div><div>A decline in the number of construction engineers and inspectors at state transportation agencies (STAs) to manage the ever-increasing lane miles has emphasized the importance of workforce planning in these agencies. Forecasting workforce requirements is crucial for effective planning in any industry or agency. This study developed machine learning (ML) models to estimate the person-hour requirements of STAs at the project level. The Arkansas Department of Transportation (ARDOT) was used as a case study, using its employee and project details data between 2012 and 2021. ML regression models ranging from linear, tree ensembles, kernel-based, and neural network-based models were developed. These models were compared based on the accuracy of their predictions, the time taken for training the models and their prediction time. Predictions were tested based on the <em>K</em>-fold cross validation technique. The results indicated a high performance from the random forest regression model, a tree ensemble with bagging, which recorded a mean <em>R</em>-squared value of 0.91. Other ML models such as an ensemble neural network model and the linear models also proved to be fit for the problem, attaining <em>R</em> squared value as high as 0.80 and 0.78, respectively. These findings underscore the capability of ML models to provide more accurate workforce demand forecasts for STAs and the construction industry. This enhanced accuracy in workforce planning will contribute to improved resource allocation and management.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"17 ","pages":"Pages 345-360"},"PeriodicalIF":4.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141143182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuzzy inference systems for discretionary lane changing decisions: Model improvements and research challenges 用于酌情变更车道决策的模糊推理系统：模型改进与研究挑战

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-03-01 DOI: 10.1016/j.ijtst.2024.05.001

Ehsan Yahyazadeh Rineh, Ruey Long Cheu

The lane changing decision model (LCDM) is a critical component in semi- and fully-automated driving systems. Recent research has found that the fuzzy inference system (FIS) is a promising approach to implementing LCDMs. To improve the FIS’s performance, this research reviewed the challenges in the development an FIS model to make the

(y e s, n o)

decisions in discretionary lane changes. The FIS model was revised to bring its fuzzy inference rules more consistent with the fuzzy membership functions, and its composition and defuzzification methods more in line with the classical fuzzy logic theory. An equitable test data set with approximately equal number of

(y e s, n o)

data points was assembled from the same next generation simulation (NGSIM) data used in the past research. The test results proved that: (1) an LCDM’s performance was dependent on how the

(y e s, n o)

decisions in the test data set were manually labeled; (2) separating the fuzzy inference rules into a

(y e s)

group and a

(n o)

group and compute the results separately yielded potentially better decision accuracy. Furthermore, The gene expression programming model (GEPM) performed better than the improved FIS-based model. The findings led the authors to suggest two possible research directions: (1) add the subject vehicle’s speed as an input to the LCDM and redesign the decision-making model; (2) construct models for congested and uncongested traffic separately. The authors further suggested the use of instrumented vehicles to collect a set of high-fidelity lane changing data in the naturalistic driving environment.

变道决策模型（LCDM）是半自动和全自动驾驶系统的关键组成部分。近年来的研究发现，模糊推理系统（FIS）是实现lcdm的一种很有前途的方法。为了提高FIS的性能，本研究回顾了FIS模型开发中的挑战，以做出任意变道的是或否决策。对FIS模型进行了修正，使其模糊推理规则更符合模糊隶属函数，其组成和去模糊化方法更符合经典模糊逻辑理论。从过去研究中使用的相同的下一代模拟（NGSIM）数据中组装了一个公平的测试数据集，其中包含大约相同数量的yes和no数据点。测试结果证明：(1)LCDM的性能取决于测试数据集中的是、否决策是如何手工标记的；(2)将模糊推理规则分为yes组和no组，并分别计算结果，可以获得更好的决策精度。此外，基因表达编程模型（GEPM）优于改进的基于fis的模型。研究结果表明：(1)将被试车辆车速作为LCDM的输入项，重新设计决策模型；(2)分别构建拥堵和非拥堵交通模型。作者进一步建议使用仪表车辆在自然驾驶环境中收集一组高保真的变道数据。

{"title":"Fuzzy inference systems for discretionary lane changing decisions: Model improvements and research challenges","authors":"Ehsan Yahyazadeh Rineh, Ruey Long Cheu","doi":"10.1016/j.ijtst.2024.05.001","DOIUrl":"10.1016/j.ijtst.2024.05.001","url":null,"abstract":"<div><div>The lane changing decision model (LCDM) is a critical component in semi- and fully-automated driving systems. Recent research has found that the fuzzy inference system (FIS) is a promising approach to implementing LCDMs. To improve the FIS’s performance, this research reviewed the challenges in the development an FIS model to make the <span><math><mrow><mfenced><mrow><mi>y</mi><mi>e</mi><mi>s</mi><mo>,</mo><mi>n</mi><mi>o</mi></mrow></mfenced></mrow></math></span> decisions in discretionary lane changes. The FIS model was revised to bring its fuzzy inference rules more consistent with the fuzzy membership functions, and its composition and defuzzification methods more in line with the classical fuzzy logic theory. An equitable test data set with approximately equal number of <span><math><mrow><mfenced><mrow><mi>y</mi><mi>e</mi><mi>s</mi><mo>,</mo><mi>n</mi><mi>o</mi></mrow></mfenced></mrow></math></span> data points was assembled from the same next generation simulation (NGSIM) data used in the past research. The test results proved that: (1) an LCDM’s performance was dependent on how the <span><math><mrow><mfenced><mrow><mi>y</mi><mi>e</mi><mi>s</mi><mo>,</mo><mi>n</mi><mi>o</mi></mrow></mfenced></mrow></math></span> decisions in the test data set were manually labeled; (2) separating the fuzzy inference rules into a <span><math><mrow><mfenced><mrow><mi>y</mi><mi>e</mi><mi>s</mi></mrow></mfenced></mrow></math></span> group and a <span><math><mrow><mfenced><mrow><mi>n</mi><mi>o</mi></mrow></mfenced></mrow></math></span> group and compute the results separately yielded potentially better decision accuracy. Furthermore, The gene expression programming model (GEPM) performed better than the improved FIS-based model. The findings led the authors to suggest two possible research directions: (1) add the subject vehicle’s speed as an input to the LCDM and redesign the decision-making model; (2) construct models for congested and uncongested traffic separately. The authors further suggested the use of instrumented vehicles to collect a set of high-fidelity lane changing data in the naturalistic driving environment.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"17 ","pages":"Pages 312-327"},"PeriodicalIF":4.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141048014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring unobserved heterogeneity in ICT usage and travel pattern changes as the pandemic subsides: A quasi-longitudinal analysis in Florida 探索信息和通信技术使用中的非观测异质性以及大流行病消退后的旅行模式变化：佛罗里达州的准纵向分析

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-03-01 DOI: 10.1016/j.ijtst.2024.04.010

Afsana Zarin Chowdhury, Ibukun Titiloye, Md Al Adib Sarker, Xia Jin

This paper presents a study that explored the behavioral heterogeneity of changes in people's information and communications technology (ICT) usage and travel patterns at the end of the pandemic. A quasi-longitudinal approach was employed to collect data from Florida residents, capturing their online durations and trip frequencies for various activities before the pandemic and at the end of 2021. Utilizing the latent class analysis (LCA) approach to identify subgroups based on the online activity durations and trip frequencies, four distinct classes were identified. A little more than one third (35%) of the respondents are resilient users who showed minimal changes in both online activity durations and trip frequencies. About 33% of respondents are trip minimizers who maintained similar online activity durations but reduced travel for non-mandatory activities. About 16% of the respondents are substitutive adapters who showed increased online activity durations combined with reduced travel for non-mandatory activities. Another 16% of the respondents are complementary users who demonstrated higher online activity durations as well as trip frequencies for non-mandatory activities. These four latent classes reflect the diverse ways in which people have adjusted their daily routines and activities. The findings offer a starting point for understanding the complexities of behavioral changes in virtual and physical mobility as we transition to the new normal.

本文提出了一项研究，探讨了大流行结束时人们信息和通信技术（ICT）使用和旅行模式变化的行为异质性。采用准纵向方法收集佛罗里达州居民的数据，捕捉他们在大流行之前和2021年底的各种活动的在线持续时间和旅行频率。利用潜在类别分析（LCA）方法根据在线活动持续时间和旅行频率确定子群体，确定了四个不同的类别。超过三分之一（35%）的受访者是弹性用户，他们在在线活动持续时间和旅行频率方面的变化很小。大约33%的受访者是旅行最小化者，他们保持类似的在线活动时间，但减少了非强制性活动的旅行。大约16%的受访者是替代适应者，他们的在线活动持续时间增加，而非强制性活动的旅行时间减少。另有16%的受访者是补充用户，他们的在线活动持续时间更长，非强制性活动的出行频率也更高。这四个潜在的类别反映了人们调整日常生活和活动的不同方式。研究结果为理解在我们向新常态过渡的过程中，虚拟和物理移动行为变化的复杂性提供了一个起点。

{"title":"Exploring unobserved heterogeneity in ICT usage and travel pattern changes as the pandemic subsides: A quasi-longitudinal analysis in Florida","authors":"Afsana Zarin Chowdhury, Ibukun Titiloye, Md Al Adib Sarker, Xia Jin","doi":"10.1016/j.ijtst.2024.04.010","DOIUrl":"10.1016/j.ijtst.2024.04.010","url":null,"abstract":"<div><div>This paper presents a study that explored the behavioral heterogeneity of changes in people's information and communications technology (ICT) usage and travel patterns at the end of the pandemic. A quasi-longitudinal approach was employed to collect data from Florida residents, capturing their online durations and trip frequencies for various activities before the pandemic and at the end of 2021. Utilizing the latent class analysis (LCA) approach to identify subgroups based on the online activity durations and trip frequencies, four distinct classes were identified. A little more than one third (35%) of the respondents are resilient users who showed minimal changes in both online activity durations and trip frequencies. About 33% of respondents are trip minimizers who maintained similar online activity durations but reduced travel for non-mandatory activities. About 16% of the respondents are substitutive adapters who showed increased online activity durations combined with reduced travel for non-mandatory activities. Another 16% of the respondents are complementary users who demonstrated higher online activity durations as well as trip frequencies for non-mandatory activities. These four latent classes reflect the diverse ways in which people have adjusted their daily routines and activities. The findings offer a starting point for understanding the complexities of behavioral changes in virtual and physical mobility as we transition to the new normal.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"17 ","pages":"Pages 276-292"},"PeriodicalIF":4.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141046920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigation of factors affecting crash severity of rear-end crashes with high collision speeds in work zones: A South Carolina case study 调查影响工作区高碰撞速度追尾碰撞严重程度的因素：南卡罗来纳州案例研究

IF 4.3 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-03-01 DOI: 10.1016/j.ijtst.2024.07.003

Mahyar Madarshahian , Jason Hawkins , Nathan Huynh , Chowdhury K.A. Siddiqui

The aim of this study is to identify factors that affect injury severity levels of work zone rear-end crashes with high collision speeds (

⩾

35 miles per hour (mph, 1 mph equals about 1.609 344 km/h)). Using statewide crash data provided by the South Carolina Department of Transportation from 2014 to 2020, a mixed binary logit model with heterogeneity in mean and variance is estimated. The model’s outcome variable is injury or non-injury (i.e., property damage only), and the explanatory variables include information related to vehicle, collision, time, occupant, roadway, and environmental characteristics. The estimation results show that the interstate variable is best modeled as a random parameter at a 90% confidence level. Late-night and dawn/dusk conditions influence the mean effect, while driving under the influence affects the variance of the random parameter. Factors positively influencing injury severity include multi-vehicle involvement, airbag deployment, dark conditions, and truck-involved crashes. Conversely, advanced warning area, activity area, lane shift/crossover, young and middle-aged drivers, and dawn/dusk conditions have negative effects on injury severity.

这项研究的目的是确定影响高碰撞速度(小于或等于35英里/小时（mph， 1英里/小时等于约1.609 344公里/小时）的工作区追尾碰撞伤害严重程度的因素。利用2014年至2020年南卡罗来纳州交通部提供的全州碰撞数据，估计了均值和方差异质性的混合二元logit模型。模型的结果变量是伤害或非伤害（即仅财产损失），解释变量包括与车辆、碰撞、时间、乘员、道路和环境特征相关的信息。估计结果表明，在90%的置信水平下，州际变量最适合作为随机参数建模。深夜和黎明/黄昏条件影响均值效应，而在此影响下驾驶影响随机参数方差。影响伤害严重程度的积极因素包括多车卷入、安全气囊展开、黑暗条件和卡车卷入的碰撞。相反，预警区、活动区、车道换挡/交叉、中青年驾驶员和黎明/黄昏条件对伤害严重程度有负面影响。

{"title":"Investigation of factors affecting crash severity of rear-end crashes with high collision speeds in work zones: A South Carolina case study","authors":"Mahyar Madarshahian , Jason Hawkins , Nathan Huynh , Chowdhury K.A. Siddiqui","doi":"10.1016/j.ijtst.2024.07.003","DOIUrl":"10.1016/j.ijtst.2024.07.003","url":null,"abstract":"<div><div>The aim of this study is to identify factors that affect injury severity levels of work zone rear-end crashes with high collision speeds (<span><math><mrow><mo>⩾</mo></mrow></math></span>35 miles per hour (mph, 1 mph equals about 1.609 344 km/h)). Using statewide crash data provided by the South Carolina Department of Transportation from 2014 to 2020, a mixed binary logit model with heterogeneity in mean and variance is estimated. The model’s outcome variable is injury or non-injury (i.e., property damage only), and the explanatory variables include information related to vehicle, collision, time, occupant, roadway, and environmental characteristics. The estimation results show that the interstate variable is best modeled as a random parameter at a 90% confidence level. Late-night and dawn/dusk conditions influence the mean effect, while driving under the influence affects the variance of the random parameter. Factors positively influencing injury severity include multi-vehicle involvement, airbag deployment, dark conditions, and truck-involved crashes. Conversely, advanced warning area, activity area, lane shift/crossover, young and middle-aged drivers, and dawn/dusk conditions have negative effects on injury severity.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"17 ","pages":"Pages 361-374"},"PeriodicalIF":4.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141712942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0