Pub Date : 2024-01-11DOI: 10.1177/03611981231220563
Yuhan Zhou, H. Mahmassani
This paper proposes an integrated framework of an activity-based behavior model and a multimodal transit assignment-simulation tool that captures road network congestion dynamics. The framework has two levels: the upper level is the demand-side activity-based model that decides individual travelers’ behavioral choices based on up-to-date information from the lower level; the lower level consists of both transit and road network estimation models on the supply side, whose inputs are trips from the upper level. The objective of this framework is to assess impacts of transit service policies, so the transit network is simulated with an agent-based multimodal hyperpath assignment model in each iteration, while the road network is mainly estimated by a macroscopic model of congestion (metamodel) instead of a simulation-based assignment model to accelerate execution time toward an equilibrated solution. Convergence under this framework is also defined from two aspects: individual choice behaviors and transit hyperpath assignment. One contribution of this paper is to incorporate the exogenous effects of road network dynamics into the integrated demand and transit assignment model, and to reduce the time to reach convergence with macroscopic modeling. This paper uses mode choice behavior as an example to demonstrate mathematical formulations and implementation procedures to reach two-level convergence. The framework is tested with the large-scale regional network of the Greater Chicago metropolitan area. The results suggest that the major advantage of the macroscopic road model is to accelerate convergence toward equilibrium when it is used to capture the traffic network congestion effects in this integrated mode choice-transit assignment framework.
{"title":"Faster Convergence of Integrated Activity-Based Models in Dynamic Multimodal Transit Assignment Using Macroscopic Road Congestion Estimation","authors":"Yuhan Zhou, H. Mahmassani","doi":"10.1177/03611981231220563","DOIUrl":"https://doi.org/10.1177/03611981231220563","url":null,"abstract":"This paper proposes an integrated framework of an activity-based behavior model and a multimodal transit assignment-simulation tool that captures road network congestion dynamics. The framework has two levels: the upper level is the demand-side activity-based model that decides individual travelers’ behavioral choices based on up-to-date information from the lower level; the lower level consists of both transit and road network estimation models on the supply side, whose inputs are trips from the upper level. The objective of this framework is to assess impacts of transit service policies, so the transit network is simulated with an agent-based multimodal hyperpath assignment model in each iteration, while the road network is mainly estimated by a macroscopic model of congestion (metamodel) instead of a simulation-based assignment model to accelerate execution time toward an equilibrated solution. Convergence under this framework is also defined from two aspects: individual choice behaviors and transit hyperpath assignment. One contribution of this paper is to incorporate the exogenous effects of road network dynamics into the integrated demand and transit assignment model, and to reduce the time to reach convergence with macroscopic modeling. This paper uses mode choice behavior as an example to demonstrate mathematical formulations and implementation procedures to reach two-level convergence. The framework is tested with the large-scale regional network of the Greater Chicago metropolitan area. The results suggest that the major advantage of the macroscopic road model is to accelerate convergence toward equilibrium when it is used to capture the traffic network congestion effects in this integrated mode choice-transit assignment framework.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139533660","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}
Pub Date : 2024-01-09DOI: 10.1177/03611981231217287
Yiying Chao, Gexin Tian, Xuefeng Wang, Yin Gu
This study investigates the economic impact of an airport economic zone (AEZ) on a city using the synthetic control method (SCM). It is an important issue for small-sized and medium-sized cities to make effective strategic plans for AEZs according to their own characteristics. Cities have begun to imitate the successful experiences of AEZs in cities with larger economies, but they often fail to replicate the same path. Moreover, the current methods are likely to reduce the reliability of the causality argument because of the lack of random sampling and random allocation of treatment. The SCM can solve this problem. In this research, the SCM was used to investigate panel data for 37 small- and medium-sized cities in China for the period 2000–2016. The results showed that the presence of an airport had a significant positive economic effect on cities with a higher economic strength and a weak positive effect on cities with a lower economic strength in our treatment group sample. In investigating the causal mechanism for this disparity, we found that the higher the match between the types of industries laid out in the AEZ and the city’s dominant industries, the better the economic development from a long-term development perspective. In addition, since AEZs are embedded in specific socio-economic contexts, it is sometimes difficult to apply successful experiences to AEZs in less developed cities. Our research utilized a new policy evaluation method and has significant implications for decision-makers.
{"title":"Economic Effect and Disparity of Airport Economic Zones Utilizing the Synthetic Control Method","authors":"Yiying Chao, Gexin Tian, Xuefeng Wang, Yin Gu","doi":"10.1177/03611981231217287","DOIUrl":"https://doi.org/10.1177/03611981231217287","url":null,"abstract":"This study investigates the economic impact of an airport economic zone (AEZ) on a city using the synthetic control method (SCM). It is an important issue for small-sized and medium-sized cities to make effective strategic plans for AEZs according to their own characteristics. Cities have begun to imitate the successful experiences of AEZs in cities with larger economies, but they often fail to replicate the same path. Moreover, the current methods are likely to reduce the reliability of the causality argument because of the lack of random sampling and random allocation of treatment. The SCM can solve this problem. In this research, the SCM was used to investigate panel data for 37 small- and medium-sized cities in China for the period 2000–2016. The results showed that the presence of an airport had a significant positive economic effect on cities with a higher economic strength and a weak positive effect on cities with a lower economic strength in our treatment group sample. In investigating the causal mechanism for this disparity, we found that the higher the match between the types of industries laid out in the AEZ and the city’s dominant industries, the better the economic development from a long-term development perspective. In addition, since AEZs are embedded in specific socio-economic contexts, it is sometimes difficult to apply successful experiences to AEZs in less developed cities. Our research utilized a new policy evaluation method and has significant implications for decision-makers.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139443644","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}
Pub Date : 2024-01-09DOI: 10.1177/03611981231217271
Y. Kumbargeri, J. Planche, Jeramie J. Adams, Joseph Rovani, Michael D. Elwardany
Polymer-modified asphalts (PMAs) are known to improve the rutting, cracking, and durability of pavements, especially creating better resistance to aging susceptibility. Although the properties, benefits, and performance of PMAs overall are fairly well known and talked about in the asphalt industry, the key aspect of selecting a good base binder for effective styrene–butadiene–styrene compatibility and enhanced performance still remains largely unexplored, and is generally based on trial-and-error methodologies. The main objective of this study was to perform in-depth physical, chemical, rheological, and microstructure characterization of base (neat/unmodified) and corresponding PMA binders to understand and quantify important aspects of their composition that would contribute to developing robust and better-performing PMAs. The experimental matrix included three base asphalt binders from different sources but similar SuperpaveTM performance grades (PG) and three corresponding PMAs. A comprehensive characterization effort was carried out on these binders that included PG grading, Black Space analysis, G* master curves, determination of ΔTc, determination of saturates, aromatics, resins, and asphaltenes fractions, differential scanning calorimetry, size-exclusion chromatography, Fourier transform infrared, and microscopy. The key outcome of this study is a set of guidelines and recommendations for preferable characteristics of base binders that contribute to formulating effective PMAs and certain “dos and don’ts” with respect to the interpretation of data and/or the analysis approach. It is expected that the outcome of this study will become an important tool for formulating well-performing PMAs that will be useful to asphalt and additive suppliers as well as contractors, agencies, or both, that procure, handle, and use PMAs for pavement applications in general.
{"title":"Comprehensive Selection of Base Asphalt Binders for Effective Formulation of Polymer-Modified Asphalts","authors":"Y. Kumbargeri, J. Planche, Jeramie J. Adams, Joseph Rovani, Michael D. Elwardany","doi":"10.1177/03611981231217271","DOIUrl":"https://doi.org/10.1177/03611981231217271","url":null,"abstract":"Polymer-modified asphalts (PMAs) are known to improve the rutting, cracking, and durability of pavements, especially creating better resistance to aging susceptibility. Although the properties, benefits, and performance of PMAs overall are fairly well known and talked about in the asphalt industry, the key aspect of selecting a good base binder for effective styrene–butadiene–styrene compatibility and enhanced performance still remains largely unexplored, and is generally based on trial-and-error methodologies. The main objective of this study was to perform in-depth physical, chemical, rheological, and microstructure characterization of base (neat/unmodified) and corresponding PMA binders to understand and quantify important aspects of their composition that would contribute to developing robust and better-performing PMAs. The experimental matrix included three base asphalt binders from different sources but similar SuperpaveTM performance grades (PG) and three corresponding PMAs. A comprehensive characterization effort was carried out on these binders that included PG grading, Black Space analysis, G* master curves, determination of ΔTc, determination of saturates, aromatics, resins, and asphaltenes fractions, differential scanning calorimetry, size-exclusion chromatography, Fourier transform infrared, and microscopy. The key outcome of this study is a set of guidelines and recommendations for preferable characteristics of base binders that contribute to formulating effective PMAs and certain “dos and don’ts” with respect to the interpretation of data and/or the analysis approach. It is expected that the outcome of this study will become an important tool for formulating well-performing PMAs that will be useful to asphalt and additive suppliers as well as contractors, agencies, or both, that procure, handle, and use PMAs for pavement applications in general.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139444330","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}
Pub Date : 2024-01-08DOI: 10.1177/03611981231215335
Atif Hussain, Syed Khaja Karimullah Hussaini
With a view to reduce burden on natural resources, the use of steel slag ballast (SSB) as an alternative to the conventional granite ballast (GB) is explored in the current study. The shear behavior of GB, SSB, and slag-GB mixture with and without tire chips (TC) was evaluated under direct shear conditions. The test results indicated that SSB exhibits significantly higher friction and dilation angles ( φ and ψ) and lower particle breakage ( Bg) when compared with GB. Furthermore, it was observed that, with the addition of TC, the magnitude of φ, ψ, and Bg of both granite and steel slag samples reduced considerably. Moreover, the friction and dilation angles of slag-GB mixture were found to be directly dependent on the proportion of slag in the mixture. For instance, the values of φ, ψ, and Bg in the case of SSB20 (20% SSB and 80% GB) were 59.36°, 13.35°, and 8.26% when compared with 58.31°, 12.98°, and 8.51% in the case of GB, and 61.66°, 15.35°, and 6.81% of SSB. However, SSB80 was found to exhibit an almost similar value of φ (i.e., 61.51°) as that of SSB but with a lower value of ψ (14.89°). In this context, the optimum content of slag in the slag-GB mixture may be considered as 80%. Furthermore, the optimal range of TC to be added was determined to be 4% to 8.6% for SSB80 to attain a friction angle similar to that of GB.
{"title":"Effect of Tire Chips on the Shear Behavior of Steel Slag and Granite Ballast Mixture","authors":"Atif Hussain, Syed Khaja Karimullah Hussaini","doi":"10.1177/03611981231215335","DOIUrl":"https://doi.org/10.1177/03611981231215335","url":null,"abstract":"With a view to reduce burden on natural resources, the use of steel slag ballast (SSB) as an alternative to the conventional granite ballast (GB) is explored in the current study. The shear behavior of GB, SSB, and slag-GB mixture with and without tire chips (TC) was evaluated under direct shear conditions. The test results indicated that SSB exhibits significantly higher friction and dilation angles ( φ and ψ) and lower particle breakage ( Bg) when compared with GB. Furthermore, it was observed that, with the addition of TC, the magnitude of φ, ψ, and Bg of both granite and steel slag samples reduced considerably. Moreover, the friction and dilation angles of slag-GB mixture were found to be directly dependent on the proportion of slag in the mixture. For instance, the values of φ, ψ, and Bg in the case of SSB20 (20% SSB and 80% GB) were 59.36°, 13.35°, and 8.26% when compared with 58.31°, 12.98°, and 8.51% in the case of GB, and 61.66°, 15.35°, and 6.81% of SSB. However, SSB80 was found to exhibit an almost similar value of φ (i.e., 61.51°) as that of SSB but with a lower value of ψ (14.89°). In this context, the optimum content of slag in the slag-GB mixture may be considered as 80%. Furthermore, the optimal range of TC to be added was determined to be 4% to 8.6% for SSB80 to attain a friction angle similar to that of GB.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445981","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}
Pub Date : 2024-01-08DOI: 10.1177/03611981231220634
Xiaoqiang Hu, Yi Jiang, Shuo Li
This study proposes an innovative process of transforming a geographic information system (GIS)-based highway model into a robust building information modeling (BIM) platform using Dynamo visual programming tool. The existing GIS system used by the Indiana Department of Transportation for highway network representation has significant limitations of data storage and handling capacity, representation of complex entities, and inclusion of crucial traffic data from weigh-in-motion and automatic traffic recorder stations. The developed process involves converting poly-curves from the GIS model into model-curves compatible with BIM, classifying attributes into shape families, and integrating traffic data from traffic recorder stations. The resulting multidimensional BIM platform, extending from three to eight dimensions, encompasses essential project details and traffic data. To ensure interoperability, an Open BIM process involving the generation of an industry foundation classes (IFC) file is utilized, allowing efficient data exchange among different software platforms and stakeholders.
{"title":"Innovative Approach to Convert Geographic Information System-Based Highway Models into Multidimensional Building Information Modeling Platforms Using Dynamo","authors":"Xiaoqiang Hu, Yi Jiang, Shuo Li","doi":"10.1177/03611981231220634","DOIUrl":"https://doi.org/10.1177/03611981231220634","url":null,"abstract":"This study proposes an innovative process of transforming a geographic information system (GIS)-based highway model into a robust building information modeling (BIM) platform using Dynamo visual programming tool. The existing GIS system used by the Indiana Department of Transportation for highway network representation has significant limitations of data storage and handling capacity, representation of complex entities, and inclusion of crucial traffic data from weigh-in-motion and automatic traffic recorder stations. The developed process involves converting poly-curves from the GIS model into model-curves compatible with BIM, classifying attributes into shape families, and integrating traffic data from traffic recorder stations. The resulting multidimensional BIM platform, extending from three to eight dimensions, encompasses essential project details and traffic data. To ensure interoperability, an Open BIM process involving the generation of an industry foundation classes (IFC) file is utilized, allowing efficient data exchange among different software platforms and stakeholders.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445325","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}
With the development of the urban rail transit network (URTN), the network structure and performance have changed, and the node importance has also been redistributed. However, little research has been done on how hub nodes change as the network develops over a lengthy period. Moreover, most hub node identification methods only focus on the analysis of topological networks or single-dimension measurements, resulting in inaccurate identification results. To overcome the above limitations, a novel method of hub node identification is proposed. Based on the ridership-weighted network model, the node centrality and reliability are aggregated to quantify the weighted comprehensive importance of the nodes. Furthermore, network invulnerability measurement is used to demonstrate the effectiveness of the proposed method. This method is applied to the Xi’an Urban Rail Transit Network (XURTN) from 2011 to 2021. With the XURTN’s development, its connectivity, balance, and fault tolerance have improved. After the basic network skeleton was formed, the number and proportion of hub nodes increased steadily. By comparing the spatial characteristics of the identified hub nodes over two successive periods, it can be found that the evolution direction of the hub nodes is correlated with the type of new lines and coincides also with the development direction of the urban area. In addition, the node orders of the proposed method have a greater impact on the network vulnerability, in which the network-weighted efficiency [Formula: see text] decreases faster and more dramatically, that is, 1.17%–45.75% more than that of other methods. Overall, this study provides a basis for the URTN and station planning and management.
{"title":"Hub Node Identification in Urban Rail Transit Network Evolution Using a Ridership-Weighted Network","authors":"Tian Tian, Yanqiu Cheng, Yichen Liang, Chen Ma, Kuanmin Chen, Xianbiao Hu","doi":"10.1177/03611981231217500","DOIUrl":"https://doi.org/10.1177/03611981231217500","url":null,"abstract":"With the development of the urban rail transit network (URTN), the network structure and performance have changed, and the node importance has also been redistributed. However, little research has been done on how hub nodes change as the network develops over a lengthy period. Moreover, most hub node identification methods only focus on the analysis of topological networks or single-dimension measurements, resulting in inaccurate identification results. To overcome the above limitations, a novel method of hub node identification is proposed. Based on the ridership-weighted network model, the node centrality and reliability are aggregated to quantify the weighted comprehensive importance of the nodes. Furthermore, network invulnerability measurement is used to demonstrate the effectiveness of the proposed method. This method is applied to the Xi’an Urban Rail Transit Network (XURTN) from 2011 to 2021. With the XURTN’s development, its connectivity, balance, and fault tolerance have improved. After the basic network skeleton was formed, the number and proportion of hub nodes increased steadily. By comparing the spatial characteristics of the identified hub nodes over two successive periods, it can be found that the evolution direction of the hub nodes is correlated with the type of new lines and coincides also with the development direction of the urban area. In addition, the node orders of the proposed method have a greater impact on the network vulnerability, in which the network-weighted efficiency [Formula: see text] decreases faster and more dramatically, that is, 1.17%–45.75% more than that of other methods. Overall, this study provides a basis for the URTN and station planning and management.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139446317","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}
To ensure the safe and punctual transportation of freight trains, it is crucial for the train to travel at the targeted speed on the track. This paper proposes a scheme for speed tracking and anti-slip control for freight trains. The speed tracking is implemented through predictive auto disturbance rejection control (PADRC), which includes a flexible Smith estimation module capable of accurately predicting the output of large time delay systems, such as freight trains. The key to anti-slip control relies on the precise observation of the radial velocity and slip rate. Therefore, an unscented Kalman filter observer is designed in this article, incorporating an adaptive parameter adjustment mechanism to enhance observation accuracy. The anti-slip parameters obtained from this observer can then be used to determine the anti-slip control scheme. The effectiveness of this scheme is demonstrated through simulations of the HXD1 electric traction locomotive’s driving process, using line data from the Geku line section in China. Compared to conventional active disturbance rejection control, PADRC reduces speed fluctuation by 55%, and freight trains under anti-slip control decrease the slip speed by 90%.
{"title":"Speed Tracking and Anti-Slip Control for Heavy Freight Trains Considering the Conicity of the Wheel","authors":"Lingzhi Yi, Yu Yi, JianLin Li, Cheng Xie, DaKe Zhang, Wenbo Jiang","doi":"10.1177/03611981231217281","DOIUrl":"https://doi.org/10.1177/03611981231217281","url":null,"abstract":"To ensure the safe and punctual transportation of freight trains, it is crucial for the train to travel at the targeted speed on the track. This paper proposes a scheme for speed tracking and anti-slip control for freight trains. The speed tracking is implemented through predictive auto disturbance rejection control (PADRC), which includes a flexible Smith estimation module capable of accurately predicting the output of large time delay systems, such as freight trains. The key to anti-slip control relies on the precise observation of the radial velocity and slip rate. Therefore, an unscented Kalman filter observer is designed in this article, incorporating an adaptive parameter adjustment mechanism to enhance observation accuracy. The anti-slip parameters obtained from this observer can then be used to determine the anti-slip control scheme. The effectiveness of this scheme is demonstrated through simulations of the HXD1 electric traction locomotive’s driving process, using line data from the Geku line section in China. Compared to conventional active disturbance rejection control, PADRC reduces speed fluctuation by 55%, and freight trains under anti-slip control decrease the slip speed by 90%.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447848","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}
Pub Date : 2024-01-07DOI: 10.1177/03611981231217497
Dimitrios Sarigiannis, Maria Atzemi, Jimi B. Oke, Eleni Christofa, S. Gerasimidis
Road crashes are a prevalent public health issue across the globe. The objective of this research was to develop a methodology for accurately classifying high-risk crash locations. The hypothesis of this study was that readily obtained roadway indicators can be used along with machine learning techniques to categorize locations as high crash-risk. A database containing 5,383 locations was created during 2012 to 2015 as part of the Hellenic National Road Safety Project and used to develop three binary machine learning models to classify high crash-risk locations based on roadway indicators. The three models were random forest, gradient boosting, and extra trees. This research used features engineering to reduce the number of indicators in the model, and the synthetic minority oversampling technique to address imbalances in the dataset between the minority (high crash-risk locations identified using crash reports) and majority classes (medium to low crash-risk locations identified based on local police testimonies, site inspections, and geometry analysis). Although all three models performed similarly, the extra trees model outperformed the other two on a range of performance metrics, including the area under the precision–recall curve and the F1-score. The findings revealed that design speeds, pavement markings, signage presence, and pavement condition were the most influential factors affecting roadway safety. The contribution of this research is in the development of a transferable methodology for classifying high crash-risk locations in addition to revealing key indicators for crash-risk potential, which in turn can inform cost-effective data collection and maintenance activities.
道路交通事故是全球普遍存在的公共健康问题。本研究的目的是开发一种方法，用于准确划分车祸高风险地点。本研究的假设是，可以将容易获得的道路指标与机器学习技术结合使用，将地点归类为碰撞事故高风险地点。作为希腊国家道路安全项目的一部分，该项目在 2012 年至 2015 年期间创建了一个包含 5383 个地点的数据库，并利用该数据库开发了三种二元机器学习模型，以根据道路指标对高碰撞风险地点进行分类。这三种模型分别是随机森林、梯度提升和额外树。这项研究使用了特征工程来减少模型中的指标数量，并使用合成少数群体超采样技术来解决数据集中少数群体（根据碰撞报告确定的高碰撞风险地点）和多数群体（根据当地警方证词、现场检查和几何分析确定的中低碰撞风险地点）之间的不平衡问题。虽然这三种模型的性能相似，但额外树模型在一系列性能指标上都优于其他两种模型，包括精确度-召回曲线下的面积和 F1 分数。研究结果表明，设计速度、路面标线、标志牌的存在以及路面状况是影响道路安全的最大因素。这项研究的贡献在于，除了揭示了潜在碰撞风险的关键指标外，还开发了一种可移植的方法，用于对高碰撞风险地点进行分类，从而为具有成本效益的数据收集和维护活动提供依据。
{"title":"Feature Engineering and Decision Trees for Predicting High Crash-Risk Locations Using Roadway Indicators","authors":"Dimitrios Sarigiannis, Maria Atzemi, Jimi B. Oke, Eleni Christofa, S. Gerasimidis","doi":"10.1177/03611981231217497","DOIUrl":"https://doi.org/10.1177/03611981231217497","url":null,"abstract":"Road crashes are a prevalent public health issue across the globe. The objective of this research was to develop a methodology for accurately classifying high-risk crash locations. The hypothesis of this study was that readily obtained roadway indicators can be used along with machine learning techniques to categorize locations as high crash-risk. A database containing 5,383 locations was created during 2012 to 2015 as part of the Hellenic National Road Safety Project and used to develop three binary machine learning models to classify high crash-risk locations based on roadway indicators. The three models were random forest, gradient boosting, and extra trees. This research used features engineering to reduce the number of indicators in the model, and the synthetic minority oversampling technique to address imbalances in the dataset between the minority (high crash-risk locations identified using crash reports) and majority classes (medium to low crash-risk locations identified based on local police testimonies, site inspections, and geometry analysis). Although all three models performed similarly, the extra trees model outperformed the other two on a range of performance metrics, including the area under the precision–recall curve and the F1-score. The findings revealed that design speeds, pavement markings, signage presence, and pavement condition were the most influential factors affecting roadway safety. The contribution of this research is in the development of a transferable methodology for classifying high crash-risk locations in addition to revealing key indicators for crash-risk potential, which in turn can inform cost-effective data collection and maintenance activities.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139448763","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}
Pub Date : 2024-01-03DOI: 10.1177/03611981231215672
Rob Jones, Moritz Köllner, K. Moreno-Sader, Dávid Kovács, Thaddaeus Delebinski, Reza Rezaei, William H. Green
Although heavy-duty trucks constitute the backbone of freight transportation in the United States, they also contribute significantly to greenhouse gas emissions. Various alternative powertrains to reduce emissions have been assessed, but few specific to U.S. long-haul applications with a consistent basis of assumptions. To enable a more accurate assessment for all stakeholders, a representative drive cycle for long-haul truck operations in the United States is introduced (USLHC8) for modeling and simulation purposes. This was generated from 58,000 mi of real driving data through a unique random microtrip selection algorithm. USLHC8 covers a total driving time of 10 h 47 min, an average vehicle speed of 55.58 mph, and road grade ranging from −6% to +6%. To establish a benchmark for further powertrain comparisons, a vehicle-level simulation of a conventional diesel powertrain was paired with USLHC8. Benchmarks are presented for fuel consumption, well-to-wheel emissions, and total cost to society under different scenarios (present-day, mid-term, and long-term).
{"title":"Realistic U.S. Long-Haul Drive Cycle for Vehicle Simulations, Costing, and Emissions Analysis","authors":"Rob Jones, Moritz Köllner, K. Moreno-Sader, Dávid Kovács, Thaddaeus Delebinski, Reza Rezaei, William H. Green","doi":"10.1177/03611981231215672","DOIUrl":"https://doi.org/10.1177/03611981231215672","url":null,"abstract":"Although heavy-duty trucks constitute the backbone of freight transportation in the United States, they also contribute significantly to greenhouse gas emissions. Various alternative powertrains to reduce emissions have been assessed, but few specific to U.S. long-haul applications with a consistent basis of assumptions. To enable a more accurate assessment for all stakeholders, a representative drive cycle for long-haul truck operations in the United States is introduced (USLHC8) for modeling and simulation purposes. This was generated from 58,000 mi of real driving data through a unique random microtrip selection algorithm. USLHC8 covers a total driving time of 10 h 47 min, an average vehicle speed of 55.58 mph, and road grade ranging from −6% to +6%. To establish a benchmark for further powertrain comparisons, a vehicle-level simulation of a conventional diesel powertrain was paired with USLHC8. Benchmarks are presented for fuel consumption, well-to-wheel emissions, and total cost to society under different scenarios (present-day, mid-term, and long-term).","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139451127","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}
Pub Date : 2024-01-03DOI: 10.1177/03611981231216975
Xingjing Xu, Ilir Bejleri, Karla Rodrigues Silva, Sivaramakrishnan Srinivasan
Both horizontal curves and intersections are generally considered high-risk locations in roadway safety. Although extensive research has been conducted separately on the safety of curves and intersections, the safety performance of curves as affected by their spatial relationship with intersections has not been fully understood. Previous research has not examined this relationship because of the use of limited or pre-existing datasets that did not include intersection data in the analysis. This study addresses these gaps by analyzing the spatial relationship between curves and intersections, utilizing a large dataset of over 8,000 rural curves in Florida. The study performs a systemic analysis using this dataset and six years of statewide crash data of all injury severity levels and develops customized curve Safety Performance Functions based on various spatial relationships between curves and intersections. This study confirms that the previously identified risk factors such as traffic volume, curve radius and length, roadway speed limit, and functional classification have significant impacts on curve safety. More importantly, the study quantifies, for the first time in the literature, the influence of intersections on curves or close to curves on safety, demonstrating that curves with one or more intersections present a higher risk than curves with no intersections. The findings show that the presence of nearby intersections can increase the crash risk for curves with no intersections but can lead to a decrease in crashes for curves with one or multiple intersections. These findings can be utilized to determine high-risk curve locations for systemic safety analysis studies.
{"title":"Effects of Intersections on the Safety of Horizontal Curves","authors":"Xingjing Xu, Ilir Bejleri, Karla Rodrigues Silva, Sivaramakrishnan Srinivasan","doi":"10.1177/03611981231216975","DOIUrl":"https://doi.org/10.1177/03611981231216975","url":null,"abstract":"Both horizontal curves and intersections are generally considered high-risk locations in roadway safety. Although extensive research has been conducted separately on the safety of curves and intersections, the safety performance of curves as affected by their spatial relationship with intersections has not been fully understood. Previous research has not examined this relationship because of the use of limited or pre-existing datasets that did not include intersection data in the analysis. This study addresses these gaps by analyzing the spatial relationship between curves and intersections, utilizing a large dataset of over 8,000 rural curves in Florida. The study performs a systemic analysis using this dataset and six years of statewide crash data of all injury severity levels and develops customized curve Safety Performance Functions based on various spatial relationships between curves and intersections. This study confirms that the previously identified risk factors such as traffic volume, curve radius and length, roadway speed limit, and functional classification have significant impacts on curve safety. More importantly, the study quantifies, for the first time in the literature, the influence of intersections on curves or close to curves on safety, demonstrating that curves with one or more intersections present a higher risk than curves with no intersections. The findings show that the presence of nearby intersections can increase the crash risk for curves with no intersections but can lead to a decrease in crashes for curves with one or multiple intersections. These findings can be utilized to determine high-risk curve locations for systemic safety analysis studies.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139536548","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：