Pub Date : 2024-07-27DOI: 10.1177/03611981241262314
Zhicheng Liu, Hong Yu
Deep reinforcement learning (DRL) is confronted with the significant problem of sparse rewards for autonomous driving in heavy traffic because of the dynamic and diverse nature of the driving environment as well as the complexity of the driving task. To mitigate the impact of sparse rewards on the convergence process of DRL, this paper proposes a novel behavioral-adaptive deep Q-network (BaDQN) for autonomous driving decisions in heavy traffic. BaDQN applies the idea of task decomposition to the DRL process. To break down the complexity of the driving task and achieve shorter exploration paths, BaDQN divides the driving task into three subtasks: Lane-Changing, Posture-Adjustment, and Wheel-Holding. BaDQN uses the finite state machine (FSM) to model the collaborative relationship between different subtasks, and abstracts each subtask separately using the Markov decision process (MDP). We used the Carla simulator to conduct experiments in a specific heavy traffic scenario. Compared with previous methods, BaDQN achieves a longer safe driving distance and a higher success rate. To discuss the adaptability of BaDQN to changes in traffic density and traffic velocity, we also conducted two extended experiments, which fully demonstrated the performance stability of BaDQN.
{"title":"Behavioral-Adaptive Deep Q-Network for Autonomous Driving Decisions in Heavy Traffic","authors":"Zhicheng Liu, Hong Yu","doi":"10.1177/03611981241262314","DOIUrl":"https://doi.org/10.1177/03611981241262314","url":null,"abstract":"Deep reinforcement learning (DRL) is confronted with the significant problem of sparse rewards for autonomous driving in heavy traffic because of the dynamic and diverse nature of the driving environment as well as the complexity of the driving task. To mitigate the impact of sparse rewards on the convergence process of DRL, this paper proposes a novel behavioral-adaptive deep Q-network (BaDQN) for autonomous driving decisions in heavy traffic. BaDQN applies the idea of task decomposition to the DRL process. To break down the complexity of the driving task and achieve shorter exploration paths, BaDQN divides the driving task into three subtasks: Lane-Changing, Posture-Adjustment, and Wheel-Holding. BaDQN uses the finite state machine (FSM) to model the collaborative relationship between different subtasks, and abstracts each subtask separately using the Markov decision process (MDP). We used the Carla simulator to conduct experiments in a specific heavy traffic scenario. Compared with previous methods, BaDQN achieves a longer safe driving distance and a higher success rate. To discuss the adaptability of BaDQN to changes in traffic density and traffic velocity, we also conducted two extended experiments, which fully demonstrated the performance stability of BaDQN.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798386","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 : 2024-07-27DOI: 10.1177/03611981241260689
Fouad Ismail Ismail, Miras Mamirov, Seunghee Kim, Jiong Hu
Recent studies have demonstrated that the carbonation treatment of recycled concrete aggregate (RCA) could enhance its properties by the conversion of adhesive paste to stronger and denser products. In addition, the use of RCA and the sequestration of CO2 during the CO2-treatment process can help to reduce the carbon footprint of concrete. This study assesses the performance of recycled aggregate concrete (RAC) developed from CO2-treated RCA. RCAs obtained from over 20 old highway and airfield pavements were treated under different pressures (5, 10, 20, 40, and 60 pounds per square inch [psi]) of CO2. The physical and mechanical properties of RCA were then examined. The complete substitution of natural coarse aggregate was carried out using both untreated and treated RCA, followed by an assessment of the resulting RAC’s fresh, mechanical, and durability properties. Furthermore, the environmental performance of concrete incorporating untreated and treated RCA was evaluated. The experimental findings revealed that the CO2 treatment pressure had a significant influence on RCA characteristics, leading to notable improvements in the mechanical and durability properties of RAC. Results demonstrated that by employing CO2 treatment at pressures of 20, 40, and 60 psi, concrete incorporating complete RCA replacement can achieve properties comparable to concrete with natural aggregate. Moreover, the RAC produced using CO2-treated RCA demonstrated a reduced CO2 equivalent when compared with concrete incorporating natural aggregate or untreated RCA. These findings underscore the potential of CO2-treated RCA as a viable and environmentally friendly alternative to natural aggregate for sustainable concrete production.
{"title":"Enhancing Performance and Reducing Environmental Impact of Concrete with Replacement of Recycled Concrete Aggregate Treated with Various CO2 Pressures","authors":"Fouad Ismail Ismail, Miras Mamirov, Seunghee Kim, Jiong Hu","doi":"10.1177/03611981241260689","DOIUrl":"https://doi.org/10.1177/03611981241260689","url":null,"abstract":"Recent studies have demonstrated that the carbonation treatment of recycled concrete aggregate (RCA) could enhance its properties by the conversion of adhesive paste to stronger and denser products. In addition, the use of RCA and the sequestration of CO2 during the CO2-treatment process can help to reduce the carbon footprint of concrete. This study assesses the performance of recycled aggregate concrete (RAC) developed from CO2-treated RCA. RCAs obtained from over 20 old highway and airfield pavements were treated under different pressures (5, 10, 20, 40, and 60 pounds per square inch [psi]) of CO2. The physical and mechanical properties of RCA were then examined. The complete substitution of natural coarse aggregate was carried out using both untreated and treated RCA, followed by an assessment of the resulting RAC’s fresh, mechanical, and durability properties. Furthermore, the environmental performance of concrete incorporating untreated and treated RCA was evaluated. The experimental findings revealed that the CO2 treatment pressure had a significant influence on RCA characteristics, leading to notable improvements in the mechanical and durability properties of RAC. Results demonstrated that by employing CO2 treatment at pressures of 20, 40, and 60 psi, concrete incorporating complete RCA replacement can achieve properties comparable to concrete with natural aggregate. Moreover, the RAC produced using CO2-treated RCA demonstrated a reduced CO2 equivalent when compared with concrete incorporating natural aggregate or untreated RCA. These findings underscore the potential of CO2-treated RCA as a viable and environmentally friendly alternative to natural aggregate for sustainable concrete production.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797776","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 : 2024-07-27DOI: 10.1177/03611981241264272
Nachuan Li, H. Mahmassani, Yanlin Zhang, Alireza Talebpour, Samer H. Hamdar
Traffic behavior around major freeway weaving sections exhibits complex dynamics associated with multi-directional maneuvers such as lane changes (LCs) accompanied by shockwave-generating braking. Data to study both microscopic and macroscopic properties of congested weaving sections have been generally lacking, leaving an important lacuna in the underlying traffic science. The Third Generation Simulation (TGSIM) trajectory data set collected on multiple freeway locations in the USA provides a rich opportunity to examine the phenomena associated with high-density weaving operations on freeways. The focus of this paper is to examine the spatial-temporal distribution of average speed, LCs, and heavy vehicles (HVs). In addition, we examine the time-shifted association of speed with LCs and HVs. Our analysis reveals considerable variation of speed across lanes and longitudinal locations. LCs are generally associated with higher speeds of the surrounding traffic and correlate with the speed changes on the original and target lanes differently. In addition, differences of speed change have been found for vehicles that execute mandatory LCs (MLCs) and discretionary LCs (DLCs). Finally, while a lower average speed is associated with the existence of HVs, it tends to recover gradually when the HVs move downstream.
{"title":"Close Look into the Spatial-Temporal Distribution of Speed, Lane Changes, and Heavy Vehicles in a Congested Freeway Weaving Section","authors":"Nachuan Li, H. Mahmassani, Yanlin Zhang, Alireza Talebpour, Samer H. Hamdar","doi":"10.1177/03611981241264272","DOIUrl":"https://doi.org/10.1177/03611981241264272","url":null,"abstract":"Traffic behavior around major freeway weaving sections exhibits complex dynamics associated with multi-directional maneuvers such as lane changes (LCs) accompanied by shockwave-generating braking. Data to study both microscopic and macroscopic properties of congested weaving sections have been generally lacking, leaving an important lacuna in the underlying traffic science. The Third Generation Simulation (TGSIM) trajectory data set collected on multiple freeway locations in the USA provides a rich opportunity to examine the phenomena associated with high-density weaving operations on freeways. The focus of this paper is to examine the spatial-temporal distribution of average speed, LCs, and heavy vehicles (HVs). In addition, we examine the time-shifted association of speed with LCs and HVs. Our analysis reveals considerable variation of speed across lanes and longitudinal locations. LCs are generally associated with higher speeds of the surrounding traffic and correlate with the speed changes on the original and target lanes differently. In addition, differences of speed change have been found for vehicles that execute mandatory LCs (MLCs) and discretionary LCs (DLCs). Finally, while a lower average speed is associated with the existence of HVs, it tends to recover gradually when the HVs move downstream.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797666","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 : 2024-07-27DOI: 10.1177/03611981241263565
Evan P. Dicks, K. Molenaar
Risk management is a widely recognized best practice for project teams to enable successful delivery of major transportation projects. Whereas many risks are identified in workshops conducted during the design stage, other risks relevant to the project are either overlooked, missed, or underassessed, only to occur later in the project lifecycle. There is limited research examining the causes of incomplete risk identification, particularly as it relates to construction projects. Contributing factors of incomplete risk identification were examined through 12 interviews with risk management professionals based on their involvement with projects that experienced a risk that was unidentified or underassessed. The study identified 10 contributing factors through a thematic analysis of the interviews including cognitive biases, communication and alignment, facilitator expertise, imagination, experience, level of detail, management support, process standardization, stakeholder participation, and time constraints. The findings provide key insights into understanding why some but not all risks are identified, and serve as a foundation for improving the identification workshops of major transportation projects.
{"title":"Causes of Incomplete Risk Identification in Major Transportation Engineering and Construction Projects","authors":"Evan P. Dicks, K. Molenaar","doi":"10.1177/03611981241263565","DOIUrl":"https://doi.org/10.1177/03611981241263565","url":null,"abstract":"Risk management is a widely recognized best practice for project teams to enable successful delivery of major transportation projects. Whereas many risks are identified in workshops conducted during the design stage, other risks relevant to the project are either overlooked, missed, or underassessed, only to occur later in the project lifecycle. There is limited research examining the causes of incomplete risk identification, particularly as it relates to construction projects. Contributing factors of incomplete risk identification were examined through 12 interviews with risk management professionals based on their involvement with projects that experienced a risk that was unidentified or underassessed. The study identified 10 contributing factors through a thematic analysis of the interviews including cognitive biases, communication and alignment, facilitator expertise, imagination, experience, level of detail, management support, process standardization, stakeholder participation, and time constraints. The findings provide key insights into understanding why some but not all risks are identified, and serve as a foundation for improving the identification workshops of major transportation projects.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797843","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 : 2024-07-27DOI: 10.1177/03611981241258988
Tianzheng Wei, Tong Zhu, Han Bai, Liang Zhao, Xiuguang Wang
Weather visibility interference has a significant impact on driver car-following behavior. To investigate drivers’ car-following behavior and emergency avoidance behaviors under different visibility disturbances, scenarios are constructed under different foggy concentration environments based on driving simulation, and the drivers’ response behaviors are collected in the stable car-following state and emergency rear-end scenarios. Exploring the differential effects of gender and driving experience on driving behavior for fog concentrations based on multifactorial analysis of variance. A quantitative model of car-following risk is constructed based on factor analysis, and a linear mixed model is used to explore the comprehensive effects of fog concentration, speed, and the following distance at the braking time on drivers’ braking reaction time by fully considering the differences in individual behaviors. The results show that driving behavior is significantly affected by visual visibility, driver’s gender, and driving experience. With the decrease of visibility, following driving speed decreases, the following distance is shortened, the headway decreases, and the standard deviation of lane lateral offset distance increases. The rear-end collision risk of an experienced driver is higher than that of a novice driver, and the rear-end collision risk of the female is higher than that of male. The risk of collision is higher when traveling in light fog. In emergency rear-end collision scenarios, as visibility decreases, braking reaction time increases, and the risk of collision conflict increases at the moment of driver braking. The braking reaction time of the driver decreases with the increase of the speed and increases with the increase of the distance when the front vehicle is braking. The results of this study provide theoretical support and technical reference for effectively improving driving safety in a bad-visibility environment.
{"title":"Effects of Driver Gender, Driving Experience, and Visibility on Car-Following Behavior","authors":"Tianzheng Wei, Tong Zhu, Han Bai, Liang Zhao, Xiuguang Wang","doi":"10.1177/03611981241258988","DOIUrl":"https://doi.org/10.1177/03611981241258988","url":null,"abstract":"Weather visibility interference has a significant impact on driver car-following behavior. To investigate drivers’ car-following behavior and emergency avoidance behaviors under different visibility disturbances, scenarios are constructed under different foggy concentration environments based on driving simulation, and the drivers’ response behaviors are collected in the stable car-following state and emergency rear-end scenarios. Exploring the differential effects of gender and driving experience on driving behavior for fog concentrations based on multifactorial analysis of variance. A quantitative model of car-following risk is constructed based on factor analysis, and a linear mixed model is used to explore the comprehensive effects of fog concentration, speed, and the following distance at the braking time on drivers’ braking reaction time by fully considering the differences in individual behaviors. The results show that driving behavior is significantly affected by visual visibility, driver’s gender, and driving experience. With the decrease of visibility, following driving speed decreases, the following distance is shortened, the headway decreases, and the standard deviation of lane lateral offset distance increases. The rear-end collision risk of an experienced driver is higher than that of a novice driver, and the rear-end collision risk of the female is higher than that of male. The risk of collision is higher when traveling in light fog. In emergency rear-end collision scenarios, as visibility decreases, braking reaction time increases, and the risk of collision conflict increases at the moment of driver braking. The braking reaction time of the driver decreases with the increase of the speed and increases with the increase of the distance when the front vehicle is braking. The results of this study provide theoretical support and technical reference for effectively improving driving safety in a bad-visibility environment.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798092","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 : 2024-07-26DOI: 10.1177/03611981241258987
Slavica Gavric, Ismet Göksad Erdagi, Daniel Rodriguez, Aleksandar Stevanovic
Numerous studies have assessed video detection systems, but automated pedestrian video detection systems (APVDS) have not received as much attention. Although some researchers have evaluated the accuracy of APVDS, none quantified the consequential effects that false or missed pedestrian calls have on critical vehicular and pedestrian performance metrics. To address this gap, this study introduces a microsimulation-based approach to analyze the impact of missed and false pedestrian calls on signalized intersection operation. This method employs simulation inputs that mimic various detection scenarios from the field, allowing for greater flexibility in analysis. Additionally, the study compares the impacts of incorrect calls under different operational strategies, including APVDS with and without the pedestrian recycle feature of the controller, pedestrian recall operations, and common push-button operations with or without pedestrian recycle. Results show that the proposed microsimulation approach is a valuable tool for future studies, especially considering the idiosyncratic nature of specific sites where the percentage of false and missed calls depends on local conditions. The study reveals that neither of the two analyzed APVDS systems is mature enough to work as a standalone option. Microsimulation results show that even though the single-camera video detection system (VDS) appears to be a safer option than the double-camera VDS, it fails to provide any benefits in pedestrian and vehicular delay over the pedestrian recall operations. This research may be of practical significance as transportation agencies could utilize the proposed microsimulation approach to evaluate APVDSs effectively. Knowing the strengths and limits of APVDS can help agencies make informed implementations.
{"title":"Microsimulation Approach to Investigate the Impact of Incorrect Automated Pedestrian Detection on the Operation of Signalized Intersections","authors":"Slavica Gavric, Ismet Göksad Erdagi, Daniel Rodriguez, Aleksandar Stevanovic","doi":"10.1177/03611981241258987","DOIUrl":"https://doi.org/10.1177/03611981241258987","url":null,"abstract":"Numerous studies have assessed video detection systems, but automated pedestrian video detection systems (APVDS) have not received as much attention. Although some researchers have evaluated the accuracy of APVDS, none quantified the consequential effects that false or missed pedestrian calls have on critical vehicular and pedestrian performance metrics. To address this gap, this study introduces a microsimulation-based approach to analyze the impact of missed and false pedestrian calls on signalized intersection operation. This method employs simulation inputs that mimic various detection scenarios from the field, allowing for greater flexibility in analysis. Additionally, the study compares the impacts of incorrect calls under different operational strategies, including APVDS with and without the pedestrian recycle feature of the controller, pedestrian recall operations, and common push-button operations with or without pedestrian recycle. Results show that the proposed microsimulation approach is a valuable tool for future studies, especially considering the idiosyncratic nature of specific sites where the percentage of false and missed calls depends on local conditions. The study reveals that neither of the two analyzed APVDS systems is mature enough to work as a standalone option. Microsimulation results show that even though the single-camera video detection system (VDS) appears to be a safer option than the double-camera VDS, it fails to provide any benefits in pedestrian and vehicular delay over the pedestrian recall operations. This research may be of practical significance as transportation agencies could utilize the proposed microsimulation approach to evaluate APVDSs effectively. Knowing the strengths and limits of APVDS can help agencies make informed implementations.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799916","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 : 2024-07-26DOI: 10.1177/03611981241258986
Junfan Zhuo, Feng Zhu
In traffic flow stability analysis, extensive research has been conducted on stability criteria, offering binary classifications of stability, that is, defining flow as stable or unstable. Despite being informative, this classification falls short of providing detailed characteristics of stability, such as the time required for a vehicle to regain equilibrium subject to a disturbance from a preceding vehicle. To address this problem, in this study, a quantitative metric, the time to equilibrium (TTE), is introduced under the condition of local stability. In a car-following scenario of two vehicles, considering that the preceding vehicle undergoes a short-term deceleration–acceleration change, an analytical formulation of the TTE is derived by employing linear stability analysis with the disturbance approximated using the Dirac delta function. The bisection method is then applied to approximate analytical solutions. Subsequent simulation experiments, utilizing various car-following parameters and disturbance settings, demonstrate the general validity of the proposed analytical TTE, barring some large errors in extreme scenarios (unlikely in real-world driving) and the intrinsic features of the Dirac delta function. We then provide applicable ranges for car-following parameters with different selection criteria. Lastly, by using real-world vehicle trajectory data, the proposed TTE is further validated.
{"title":"Time to Equilibrium in a Car-Following Scenario under Local Stable Conditions","authors":"Junfan Zhuo, Feng Zhu","doi":"10.1177/03611981241258986","DOIUrl":"https://doi.org/10.1177/03611981241258986","url":null,"abstract":"In traffic flow stability analysis, extensive research has been conducted on stability criteria, offering binary classifications of stability, that is, defining flow as stable or unstable. Despite being informative, this classification falls short of providing detailed characteristics of stability, such as the time required for a vehicle to regain equilibrium subject to a disturbance from a preceding vehicle. To address this problem, in this study, a quantitative metric, the time to equilibrium (TTE), is introduced under the condition of local stability. In a car-following scenario of two vehicles, considering that the preceding vehicle undergoes a short-term deceleration–acceleration change, an analytical formulation of the TTE is derived by employing linear stability analysis with the disturbance approximated using the Dirac delta function. The bisection method is then applied to approximate analytical solutions. Subsequent simulation experiments, utilizing various car-following parameters and disturbance settings, demonstrate the general validity of the proposed analytical TTE, barring some large errors in extreme scenarios (unlikely in real-world driving) and the intrinsic features of the Dirac delta function. We then provide applicable ranges for car-following parameters with different selection criteria. Lastly, by using real-world vehicle trajectory data, the proposed TTE is further validated.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141799946","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}
Automated methods have been widely used by highway agencies to collect pavement condition data. However, there are still accuracy and precision issues associated with the reliability of the existing automated data collection methods. Therefore, this research aims to develop data quality check procedures to improve the reliability of automated pavement condition data for highway agencies. The study comprises three main components: identification of data quality check indexes; establishment of data quality thresholds; and implementation of data quality check procedures. Annual pavement rating data collected by a vendor using automated technologies and manual audit data from an independent third party were utilized to develop thresholds and test the procedures. Three districts, including two urban and one rural districts in Texas, were selected for the data quality check implementation. The results indicate that the proposed procedures, along with defined indexes and thresholds, efficiently identify pavements with data quality issues at both the section level and the county level. By pinpointing problematic areas, highway agencies can allocate resources for quick quality checks, enhancing the accuracy and precision of automated pavement condition data. The study can help highway agencies enhance the accuracy and precision of automated pavement condition data, ultimately leading to improvements in their pavement conditions.
{"title":"Enhancing Reliability in Automated Pavement Condition Data with a Data Quality Check Approach for Highway Agencies","authors":"Xiaohua Luo, Jueqiang Tao, Feng Wang, Ajmain Faieq, Haitao Gong, Feng Hong","doi":"10.1177/03611981241246247","DOIUrl":"https://doi.org/10.1177/03611981241246247","url":null,"abstract":"Automated methods have been widely used by highway agencies to collect pavement condition data. However, there are still accuracy and precision issues associated with the reliability of the existing automated data collection methods. Therefore, this research aims to develop data quality check procedures to improve the reliability of automated pavement condition data for highway agencies. The study comprises three main components: identification of data quality check indexes; establishment of data quality thresholds; and implementation of data quality check procedures. Annual pavement rating data collected by a vendor using automated technologies and manual audit data from an independent third party were utilized to develop thresholds and test the procedures. Three districts, including two urban and one rural districts in Texas, were selected for the data quality check implementation. The results indicate that the proposed procedures, along with defined indexes and thresholds, efficiently identify pavements with data quality issues at both the section level and the county level. By pinpointing problematic areas, highway agencies can allocate resources for quick quality checks, enhancing the accuracy and precision of automated pavement condition data. The study can help highway agencies enhance the accuracy and precision of automated pavement condition data, ultimately leading to improvements in their pavement conditions.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141268469","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}
Freight transportation plays a crucial role in sustaining the Canadian economy. However, heavy truck transportation also puts enormous pressure on roadway networks. Spring Load Restrictions (SLR) are implemented to minimize road damage caused by heavy traffic during the thaw-weakening season, and Winter Weight Premium (WWP) is used to reduce the impact of SLR on trucking operations by allowing higher axle loads in winter. However, existing policies apply fixed dates each year for these restrictions, regardless of the actual structural capacity of the pavement. Different methods have been proposed to improve the application of SLR and WWP; however, they rely mainly on indirect indices, such as the cumulative thawing index and cumulative freezing index, which pose challenges in their calculation. This study explores the practical implementation of machine learning models for accurately determining the start and end dates of SLR and WWP. In a novel approach, machine learning models directly derive the start and end dates of SLR and WWP from frost and thaw depths in the pavement structure which are determined by pavement temperature and moisture content. In contrast to previous studies that neglected the influence of soil moisture content on determining the start and end dates of SLR and WWP, this study examines the variation in soil moisture content to evaluate the validity of existing theories. The findings reveal a high level of agreement between the machine learning model’s estimations of frost and thaw depths and the measured values, with R2 values exceeding 0.91.
{"title":"Application of the Machine Learning Method to Determine Spring Load Limits and Winter Weight Premium","authors":"Yunyan Huang, Taher Baghaee Moghaddam, Leila Hashemian, Alireza Bayat","doi":"10.1177/03611981241246780","DOIUrl":"https://doi.org/10.1177/03611981241246780","url":null,"abstract":"Freight transportation plays a crucial role in sustaining the Canadian economy. However, heavy truck transportation also puts enormous pressure on roadway networks. Spring Load Restrictions (SLR) are implemented to minimize road damage caused by heavy traffic during the thaw-weakening season, and Winter Weight Premium (WWP) is used to reduce the impact of SLR on trucking operations by allowing higher axle loads in winter. However, existing policies apply fixed dates each year for these restrictions, regardless of the actual structural capacity of the pavement. Different methods have been proposed to improve the application of SLR and WWP; however, they rely mainly on indirect indices, such as the cumulative thawing index and cumulative freezing index, which pose challenges in their calculation. This study explores the practical implementation of machine learning models for accurately determining the start and end dates of SLR and WWP. In a novel approach, machine learning models directly derive the start and end dates of SLR and WWP from frost and thaw depths in the pavement structure which are determined by pavement temperature and moisture content. In contrast to previous studies that neglected the influence of soil moisture content on determining the start and end dates of SLR and WWP, this study examines the variation in soil moisture content to evaluate the validity of existing theories. The findings reveal a high level of agreement between the machine learning model’s estimations of frost and thaw depths and the measured values, with R2 values exceeding 0.91.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141265856","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 : 2024-06-04DOI: 10.1177/03611981241250339
Jaswant Singh, Hemant Gehlot
Natural disasters can lead to substantial disruptions in road networks, making many critical links unusable. It is important to timely repair the damaged links as they allow transportation of emergency services, relief materials, and so forth, after disasters. Many existing studies that focus on optimal recovery of damaged links after disasters assume that only a single agency is available for repair. Moreover, most of the existing studies do not consider travel time on links to be a function of traffic flow passing through the links and assume that the traffic flow gets distributed based on user equilibrium each time a link is repaired. However, such a traffic distribution is unrealistic as it assumes that the traffic flow remains the same across all the days for which a link is repaired and the traffic distribution gets suddenly modified whenever a link is fully repaired. The goal of this paper is to address these gaps in the literature of disaster recovery. We study the problem of determining the optimal repair scheduling of damaged links to minimize the sum of the total system travel time over the repair duration given that multiple repair agencies are available for recovery. Also, we consider a day-to-day traffic flow evolution where the route choices of travelers depend on the travel conditions of the previous day. We formulate this problem as a mixed-integer non-linear program. We proposed two solution methodologies to solve the problem: a genetic algorithm and a greedy algorithm. We tested these methodologies under different settings.
{"title":"Recovery Scheduling of Road Networks Considering Day-to-Day Flow Evolution","authors":"Jaswant Singh, Hemant Gehlot","doi":"10.1177/03611981241250339","DOIUrl":"https://doi.org/10.1177/03611981241250339","url":null,"abstract":"Natural disasters can lead to substantial disruptions in road networks, making many critical links unusable. It is important to timely repair the damaged links as they allow transportation of emergency services, relief materials, and so forth, after disasters. Many existing studies that focus on optimal recovery of damaged links after disasters assume that only a single agency is available for repair. Moreover, most of the existing studies do not consider travel time on links to be a function of traffic flow passing through the links and assume that the traffic flow gets distributed based on user equilibrium each time a link is repaired. However, such a traffic distribution is unrealistic as it assumes that the traffic flow remains the same across all the days for which a link is repaired and the traffic distribution gets suddenly modified whenever a link is fully repaired. The goal of this paper is to address these gaps in the literature of disaster recovery. We study the problem of determining the optimal repair scheduling of damaged links to minimize the sum of the total system travel time over the repair duration given that multiple repair agencies are available for recovery. Also, we consider a day-to-day traffic flow evolution where the route choices of travelers depend on the travel conditions of the previous day. We formulate this problem as a mixed-integer non-linear program. We proposed two solution methodologies to solve the problem: a genetic algorithm and a greedy algorithm. We tested these methodologies under different settings.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141266300","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：