Pub Date : 2023-09-30DOI: 10.1177/03611981231198845
Aidan Grenville, Willem Klumpenhouwer, Amer Shalaby
Typical performance measurements of public transit operations make use of vehicle-based data such as automated vehicle location data or passenger-based data at specific fare collection points. Ideally, the performance of a transit system from a reliability perspective and according to passenger experience should be measured through individual passenger journeys. The growing prevalence of smartphones provides one potential source for this analysis, because passive data collection methods such as obtaining Wi-Fi, cellular, and Bluetooth connection data allow us to observe devices as they move throughout the system. In this study we present a collection of methods and performance measures for using Wi-Fi connection data to measure various aspects of customer experience and reliability, including methods for detecting train arrivals at platforms, estimating wait times, measuring origin–destination travel time variation, and developing profiles of various journey types for comparison. In contrast with many other advances toward passenger-based measures, these methods do not require the combination of diverse data sets to generate useful results. These methods are applied to data from the Wi-Fi service in the subway system in Toronto, Canada.
{"title":"Using Wi-Fi Connection Data to Analyze Performance of the Subway System in Toronto, Canada","authors":"Aidan Grenville, Willem Klumpenhouwer, Amer Shalaby","doi":"10.1177/03611981231198845","DOIUrl":"https://doi.org/10.1177/03611981231198845","url":null,"abstract":"Typical performance measurements of public transit operations make use of vehicle-based data such as automated vehicle location data or passenger-based data at specific fare collection points. Ideally, the performance of a transit system from a reliability perspective and according to passenger experience should be measured through individual passenger journeys. The growing prevalence of smartphones provides one potential source for this analysis, because passive data collection methods such as obtaining Wi-Fi, cellular, and Bluetooth connection data allow us to observe devices as they move throughout the system. In this study we present a collection of methods and performance measures for using Wi-Fi connection data to measure various aspects of customer experience and reliability, including methods for detecting train arrivals at platforms, estimating wait times, measuring origin–destination travel time variation, and developing profiles of various journey types for comparison. In contrast with many other advances toward passenger-based measures, these methods do not require the combination of diverse data sets to generate useful results. These methods are applied to data from the Wi-Fi service in the subway system in Toronto, Canada.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136279832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1177/03611981231186602
Xiaoqin Liu, Gang Xiao
A scheme for conflict resolution with trajectory recovery is proposed to solve the problem of multi-aircraft flight conflict. First, the conflict resolution problem is modeled as an optimal control problem. The weighted sum of the speed change and the heading angle change is defined as the objective function. The limitations of distance, aircraft performance, and route width are taken as constraints. Second, the optimization problem is resolved by mixed integer nonlinear programming. Conflict resolution with trajectory recovery is then achieved by speed and heading angle changing three times based on the optimal solution; whether the speed and heading angle need to be changed depends on the corresponding weight coefficients in the objective function. Finally, the applicability and superiority of the designed conflict resolution scheme are verified, which is of great significance to the application of conflict resolution with trajectory recovery schemes in automated air traffic control systems.
{"title":"Flight Conflict Resolution and Trajectory Recovery Through Mixed Integer Nonlinear Programming Based on Speed and Heading Angle Change","authors":"Xiaoqin Liu, Gang Xiao","doi":"10.1177/03611981231186602","DOIUrl":"https://doi.org/10.1177/03611981231186602","url":null,"abstract":"A scheme for conflict resolution with trajectory recovery is proposed to solve the problem of multi-aircraft flight conflict. First, the conflict resolution problem is modeled as an optimal control problem. The weighted sum of the speed change and the heading angle change is defined as the objective function. The limitations of distance, aircraft performance, and route width are taken as constraints. Second, the optimization problem is resolved by mixed integer nonlinear programming. Conflict resolution with trajectory recovery is then achieved by speed and heading angle changing three times based on the optimal solution; whether the speed and heading angle need to be changed depends on the corresponding weight coefficients in the objective function. Finally, the applicability and superiority of the designed conflict resolution scheme are verified, which is of great significance to the application of conflict resolution with trajectory recovery schemes in automated air traffic control systems.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136341435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1177/03611981231203157
Jinqu Chen, Chengzhen Jiang, Xiaowei Liu, Bo Du, Qiyuan Peng, Yong Yin, Baowen Li
The resilience of an urban rail transit (URT) network when faced with disruptions is affected by the locations of stations equipped with turn-back (TB) tracks. However, limited studies have enhanced the resilience of a URT network by setting new TB tracks. The present work addresses this gap by proposing and solving a scenario model for improving the operation of a URT network under normal conditions and disruptions by considering uncertain disruptions. A solution algorithm combined with the non-dominated sorting genetic algorithm-II is proposed to solve the model. Numerical experiments conducted on the Chengdu subway system indicate that the resilience of a URT network is significantly affected by TB operations provided at stations equipped with TB tracks. Compared with a network without new TB tracks, the matching degree between passenger flow spatial distribution and TB convenience, and the network’s overall resilience metric (NORM) are improved by 12.05% and 0.58%, respectively, when five new TB tracks are installed. The solution effectiveness of the model is related to the number of new TB tracks, and the NORM decreases by an average of [Formula: see text] after adding new TB tracks to a station.
{"title":"Resilience Enhancement of an Urban Rail Transit Network by Setting Turn-Back Tracks: A Scenario Model Approach","authors":"Jinqu Chen, Chengzhen Jiang, Xiaowei Liu, Bo Du, Qiyuan Peng, Yong Yin, Baowen Li","doi":"10.1177/03611981231203157","DOIUrl":"https://doi.org/10.1177/03611981231203157","url":null,"abstract":"The resilience of an urban rail transit (URT) network when faced with disruptions is affected by the locations of stations equipped with turn-back (TB) tracks. However, limited studies have enhanced the resilience of a URT network by setting new TB tracks. The present work addresses this gap by proposing and solving a scenario model for improving the operation of a URT network under normal conditions and disruptions by considering uncertain disruptions. A solution algorithm combined with the non-dominated sorting genetic algorithm-II is proposed to solve the model. Numerical experiments conducted on the Chengdu subway system indicate that the resilience of a URT network is significantly affected by TB operations provided at stations equipped with TB tracks. Compared with a network without new TB tracks, the matching degree between passenger flow spatial distribution and TB convenience, and the network’s overall resilience metric (NORM) are improved by 12.05% and 0.58%, respectively, when five new TB tracks are installed. The solution effectiveness of the model is related to the number of new TB tracks, and the NORM decreases by an average of [Formula: see text] after adding new TB tracks to a station.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136280442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1177/03611981231198851
HuanZhong Sun, XiangHong Tang, JianGuang Lu, FangJie Liu
Traffic prediction is critical to intelligent transportation and smart cities. The prediction performance of many existing traffic prediction models is limited by the fixed original graph structure and inappropriate spatio-temporal dependency extraction. For this situation, this paper proposes a spatio-temporal graph neural network based on adaptive neighborhood selection (STGNN-ANS). To obtain more flexible graph structures, STGNN-ANS designs a neighbor selection mechanism to generate a new graph structure by filtering inappropriate neighbors. To further capture the spatio-temporal dependence of traffic data, a spatio-temporal serial module of STGNN-ANS adopts the bidirectional learning manner of bidirectional long short-term memory (BiLSTM) and the graph convolution network (GCN) enhanced by self-attention mechanism to reach excellent prediction accuracy in both short-range and long-range scenarios. In this paper, a new baseline comprehensive comparison metric (BCCM) is invented to cope with the complexity in the comparative analysis of large numbers of experimental results. Many experiments have been performed on four real-world traffic datasets, and the results show that the comprehensive prediction performance of STGNN-ANS is better than previous models.
{"title":"Spatio-Temporal Graph Neural Network for Traffic Prediction Based on Adaptive Neighborhood Selection","authors":"HuanZhong Sun, XiangHong Tang, JianGuang Lu, FangJie Liu","doi":"10.1177/03611981231198851","DOIUrl":"https://doi.org/10.1177/03611981231198851","url":null,"abstract":"Traffic prediction is critical to intelligent transportation and smart cities. The prediction performance of many existing traffic prediction models is limited by the fixed original graph structure and inappropriate spatio-temporal dependency extraction. For this situation, this paper proposes a spatio-temporal graph neural network based on adaptive neighborhood selection (STGNN-ANS). To obtain more flexible graph structures, STGNN-ANS designs a neighbor selection mechanism to generate a new graph structure by filtering inappropriate neighbors. To further capture the spatio-temporal dependence of traffic data, a spatio-temporal serial module of STGNN-ANS adopts the bidirectional learning manner of bidirectional long short-term memory (BiLSTM) and the graph convolution network (GCN) enhanced by self-attention mechanism to reach excellent prediction accuracy in both short-range and long-range scenarios. In this paper, a new baseline comprehensive comparison metric (BCCM) is invented to cope with the complexity in the comparative analysis of large numbers of experimental results. Many experiments have been performed on four real-world traffic datasets, and the results show that the comprehensive prediction performance of STGNN-ANS is better than previous models.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136280587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the enrichment of smartphone uses, phone-related driving distractions have become a threat to driving safety. One way to mitigate driving distractions is to detect them and provide real-time warnings. However, most existing driving distraction recognition algorithms are pretrained models composed of structures, hyperparameters, and parameters that may not be able to account for drivers’ individual differences and, thus, might result in low model accuracy. This study proposes a domain-specific hierarchical automated machine learning (HAT-ML) model that self-learns personalized optimal models to detect driving distractions from vehicle movement data. The HAT-ML model integrates key modeling steps into auto-optimizable layers, including knowledge-based feature extraction, feature selection by recursive feature elimination, automated algorithm selection, and hyperparameter autotuning by Bayesian optimization. In our eight-degrees-of-freedom driving simulator experiment, we demonstrated the effectiveness of the proposed model using three driving distraction tasks: browsing a short message, browsing a long message, and answering a phone call. The HAT-ML model was found to be reliable and robust for predicting phone-related driving distraction, achieving satisfactory results with a predictive accuracy of 80% at the group level and 90% at the individual level. Moreover, the results revealed that each distraction and driver type required different optimized hyperparameter values, which demonstrated the value of utilizing HAT-ML to detect driving distractions. The key elements that dominated the performance of the model have several theoretical and practical implications. The proposed method not only enhanced performance, but also provided data-driven insights about model development.
{"title":"Hierarchical Automated Machine Learning Approach for Self-Optimizable Driving Distraction Recognition Based on Driver’s Lane-Keeping Performance","authors":"Chen Chai, Jiaxin Li, Md Mohaiminul Islam, Rui Feng, Miaojia Lu","doi":"10.1177/03611981231196152","DOIUrl":"https://doi.org/10.1177/03611981231196152","url":null,"abstract":"With the enrichment of smartphone uses, phone-related driving distractions have become a threat to driving safety. One way to mitigate driving distractions is to detect them and provide real-time warnings. However, most existing driving distraction recognition algorithms are pretrained models composed of structures, hyperparameters, and parameters that may not be able to account for drivers’ individual differences and, thus, might result in low model accuracy. This study proposes a domain-specific hierarchical automated machine learning (HAT-ML) model that self-learns personalized optimal models to detect driving distractions from vehicle movement data. The HAT-ML model integrates key modeling steps into auto-optimizable layers, including knowledge-based feature extraction, feature selection by recursive feature elimination, automated algorithm selection, and hyperparameter autotuning by Bayesian optimization. In our eight-degrees-of-freedom driving simulator experiment, we demonstrated the effectiveness of the proposed model using three driving distraction tasks: browsing a short message, browsing a long message, and answering a phone call. The HAT-ML model was found to be reliable and robust for predicting phone-related driving distraction, achieving satisfactory results with a predictive accuracy of 80% at the group level and 90% at the individual level. Moreover, the results revealed that each distraction and driver type required different optimized hyperparameter values, which demonstrated the value of utilizing HAT-ML to detect driving distractions. The key elements that dominated the performance of the model have several theoretical and practical implications. The proposed method not only enhanced performance, but also provided data-driven insights about model development.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136280277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1177/03611981231196148
Ronald Knezevich, Zhongyu Yang, Pingzhou (Lucas) Yu, Yi-Chang (James) Tsai
The ball bank indicator (BBI) measures the lateral forces on a vehicle. It is used to establish the advisory speed limit as outlined in the American Association of State Highway and Transportation Officials (AASHTO)’s Green Book. BBI values respond to roadway geometry and driver behavior. Currently, BBI data are available from various curves across the U.S. However, the relationship between BBI and curve lane departures is unknown. Therefore, the objective of this paper is to assess the impact of BBI as an explanatory variable for curve lane departures within a safety performance function (SPF) (i.e., a crash prediction model). To accomplish this objective, a study is conducted on rural curves in Districts 1, 2, and 6 of Georgia Department of Transportation in the U.S. BBI is integrated into a negative binomial model alongside other common explanatory variables used in the Highway Safety Manual. This SPF, with BBI incorporated, is compared with a baseline SPF without the BBI. The results show BBI is a statistically significant variable under a 99.9% threshold. Additionally, it was found that the model with BBI has 2.78% and 2.83% less mean absolute error and route mean squared error, respectively. Though the improvement in the model is minor, this finding is notable because BBI data may already be available for a transportation agency to leverage to assess risk on curves. Furthermore, this data could be even more beneficial if it were crowdsourced to gauge real-world behaviors.
{"title":"Impact of Ball Bank Indicator on Predicting Rural Curve Crashes","authors":"Ronald Knezevich, Zhongyu Yang, Pingzhou (Lucas) Yu, Yi-Chang (James) Tsai","doi":"10.1177/03611981231196148","DOIUrl":"https://doi.org/10.1177/03611981231196148","url":null,"abstract":"The ball bank indicator (BBI) measures the lateral forces on a vehicle. It is used to establish the advisory speed limit as outlined in the American Association of State Highway and Transportation Officials (AASHTO)’s Green Book. BBI values respond to roadway geometry and driver behavior. Currently, BBI data are available from various curves across the U.S. However, the relationship between BBI and curve lane departures is unknown. Therefore, the objective of this paper is to assess the impact of BBI as an explanatory variable for curve lane departures within a safety performance function (SPF) (i.e., a crash prediction model). To accomplish this objective, a study is conducted on rural curves in Districts 1, 2, and 6 of Georgia Department of Transportation in the U.S. BBI is integrated into a negative binomial model alongside other common explanatory variables used in the Highway Safety Manual. This SPF, with BBI incorporated, is compared with a baseline SPF without the BBI. The results show BBI is a statistically significant variable under a 99.9% threshold. Additionally, it was found that the model with BBI has 2.78% and 2.83% less mean absolute error and route mean squared error, respectively. Though the improvement in the model is minor, this finding is notable because BBI data may already be available for a transportation agency to leverage to assess risk on curves. Furthermore, this data could be even more beneficial if it were crowdsourced to gauge real-world behaviors.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136280445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Connected and automated vehicles (CAVs) are expected to improve traffic safety effectively at signalized intersections. Considerable studies have been conducted to investigate the benefits of CAVs in improving traffic mobility and efficiency. However, in most previous research, vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication have been considered separately rather than concurrently, to study the characteristics of CAVs, resulting in the potential of CAVs not being fully exploited and inconsistency with reality. In this paper, an integrated communication system of CAVs (ICSC), which incorporates V2V and V2I communication, is proposed, to assess traffic safety at signalized intersections. In this study, the intelligent driver model (IDM) is used to approximate V2V communication between a subject CAV and preceding CAVs. A reinforcement learning algorithm is adopted to model V2I communication between a CAV and a traffic light. The traffic safety effect of ICSC, V2V-only, and V2I-only scenarios is evaluated for different market penetration rates (MPRs). The results show that the ICSC scenario significantly reduces traffic conflicts and outperforms V2V-only, V2I-only, and benchmark scenarios when the MPR is equal to or higher than 50% with different surrogate safety measures (SSMs), such as time-exposed deceleration (TED) to avoid crashing, time exposed time-to-collision (TET), and use of a spacing gap (SGAP). Moreover, the mobility effect of the ICSC scenario is studied, and appears to increase average speed and reduce delay time. Finally, the results suggest that the ICSC can improve traffic safety and mobility concurrently and exploit the potentials of CAVs at signalized intersections.
{"title":"Traffic Safety Assessment with Integrated Communication System of Connected and Automated Vehicles at Signalized Intersections","authors":"Xu Wang, Xinguo Jiang, Haibo Li, Xinyu Zhao, Zuoan Hu, Chuan Xu","doi":"10.1177/03611981231201107","DOIUrl":"https://doi.org/10.1177/03611981231201107","url":null,"abstract":"Connected and automated vehicles (CAVs) are expected to improve traffic safety effectively at signalized intersections. Considerable studies have been conducted to investigate the benefits of CAVs in improving traffic mobility and efficiency. However, in most previous research, vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication have been considered separately rather than concurrently, to study the characteristics of CAVs, resulting in the potential of CAVs not being fully exploited and inconsistency with reality. In this paper, an integrated communication system of CAVs (ICSC), which incorporates V2V and V2I communication, is proposed, to assess traffic safety at signalized intersections. In this study, the intelligent driver model (IDM) is used to approximate V2V communication between a subject CAV and preceding CAVs. A reinforcement learning algorithm is adopted to model V2I communication between a CAV and a traffic light. The traffic safety effect of ICSC, V2V-only, and V2I-only scenarios is evaluated for different market penetration rates (MPRs). The results show that the ICSC scenario significantly reduces traffic conflicts and outperforms V2V-only, V2I-only, and benchmark scenarios when the MPR is equal to or higher than 50% with different surrogate safety measures (SSMs), such as time-exposed deceleration (TED) to avoid crashing, time exposed time-to-collision (TET), and use of a spacing gap (SGAP). Moreover, the mobility effect of the ICSC scenario is studied, and appears to increase average speed and reduce delay time. Finally, the results suggest that the ICSC can improve traffic safety and mobility concurrently and exploit the potentials of CAVs at signalized intersections.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136341749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-29DOI: 10.1177/03611981231198478
Hongtao Dang, Jennifer Shane
The Disadvantaged Business Enterprise program, established by the United States Department of Transportation, aims to remove barriers to participation of Disadvantaged Business Enterprises (DBEs) in highway projects, to promote the use of DBEs in federally assisted contracts, and to assist the development of DBEs. A DBE is a small, for-profit business owned by socially and economically disadvantaged individuals such as women or minorities. DBEs need various supportive services, depending on many factors, such as business area, size, and strategy. State Departments of Transportation often provide or hire third parties to provide supportive services to DBEs that are relatively expensive and inefficient. These services may also support only some and unintentionally exclude other DBEs. Under many challenges, one ultimate goal is to find a framework that covers all valuable DBE supportive services. This study proposes, tests, and validates a framework for providing effective and comprehensive DBE supportive services in the transportation sector. Based on discussions with DBE liaison officers and service providers, we propose the business, engineering, construction, and other (BECO) framework to provide DBE supportive services. We then use a sequential explanatory design in mixed methods, collecting quantitative and qualitative data to evaluate and validate the BECO framework. We analyze quantitative data using confirmatory factor analysis and qualitative data using pattern coding techniques. The results provide insights and reveal useful DBE supportive services using the BECO framework. The framework is useful for assessing DBE needs, informing DBE liaison officers and service providers, and offering the most useful supportive services to DBEs.
{"title":"BECO (Business, Engineering, Construction, and Other) Framework for Providing Effective and Comprehensive Supportive Services to Disadvantaged Business Enterprises in the United States","authors":"Hongtao Dang, Jennifer Shane","doi":"10.1177/03611981231198478","DOIUrl":"https://doi.org/10.1177/03611981231198478","url":null,"abstract":"The Disadvantaged Business Enterprise program, established by the United States Department of Transportation, aims to remove barriers to participation of Disadvantaged Business Enterprises (DBEs) in highway projects, to promote the use of DBEs in federally assisted contracts, and to assist the development of DBEs. A DBE is a small, for-profit business owned by socially and economically disadvantaged individuals such as women or minorities. DBEs need various supportive services, depending on many factors, such as business area, size, and strategy. State Departments of Transportation often provide or hire third parties to provide supportive services to DBEs that are relatively expensive and inefficient. These services may also support only some and unintentionally exclude other DBEs. Under many challenges, one ultimate goal is to find a framework that covers all valuable DBE supportive services. This study proposes, tests, and validates a framework for providing effective and comprehensive DBE supportive services in the transportation sector. Based on discussions with DBE liaison officers and service providers, we propose the business, engineering, construction, and other (BECO) framework to provide DBE supportive services. We then use a sequential explanatory design in mixed methods, collecting quantitative and qualitative data to evaluate and validate the BECO framework. We analyze quantitative data using confirmatory factor analysis and qualitative data using pattern coding techniques. The results provide insights and reveal useful DBE supportive services using the BECO framework. The framework is useful for assessing DBE needs, informing DBE liaison officers and service providers, and offering the most useful supportive services to DBEs.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135199340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Real-time and accurate obstacle detection is a vital technology for electric locomotives, especially as driverless vehicles are introduced. A method of obstacle detection for underground electric locomotive rail based on instance segmentation is developed to solve the problems of misdetection and missing detection, low detection accuracy, and slow detection speed of rail obstacles. The method of locating the track mask, demarcating the effective driving boundary, expanding the track mask, and forming the effective driving area is adopted to verify whether the target is an obstacle based on whether the target is located in the effective driving area, to avoid the problem of misdetection and missing detection of the target obstacle. The YOLACT++ (You Only Look At CoefficienTs) model is improved, and path augmentation and target classification loss function replacement strategies are adopted to enhance the model’s ability to detect target details and increase the accuracy of target segmentation. Compared with traditional image processing, this method can detect both straight rail and turnout. The mean average precision of boundary box mAP 0.5 (box) and mask mAP 0.5 (mask) of the improved YOLACT++ model reaches 98.52% and 98.55%, which is higher than that of the YOLACT++ model, and the detection frame rate reaches 21.9 frames per second.
实时、准确的障碍物检测是电力机车的关键技术，尤其是在无人驾驶汽车时代。针对地下电机车轨道障碍物检测中存在的检测误检和漏检、检测精度低、检测速度慢等问题，提出了一种基于实例分割的轨道障碍物检测方法。采用定位轨迹掩码、划分有效驱动边界、展开轨迹掩码、形成有效驱动区域的方法，根据目标是否位于有效驱动区域来验证目标是否为障碍物，避免了目标障碍物的误检和漏检问题。对yolact++ (You Only Look At CoefficienTs)模型进行了改进，采用路径增强和目标分类损失函数替换策略，增强了模型对目标细节的检测能力，提高了目标分割的精度。与传统的图像处理方法相比，该方法可以同时检测到直轨和道岔。改进的yolact++模型的边界盒mAP 0.5 (box)和掩码mAP 0.5 (mask)的平均精度分别达到98.52%和98.55%，均高于yolact++模型，检测帧率达到21.9帧/秒。
{"title":"Obstacle Detection Method of Underground Electric Locomotive Rail Based on Instance Segmentation","authors":"Jiale Tong, Shuang Wang, Yongcun Guo, Wenshan Wang, Tun Yang, Shuqi Zong","doi":"10.1177/03611981231198842","DOIUrl":"https://doi.org/10.1177/03611981231198842","url":null,"abstract":"Real-time and accurate obstacle detection is a vital technology for electric locomotives, especially as driverless vehicles are introduced. A method of obstacle detection for underground electric locomotive rail based on instance segmentation is developed to solve the problems of misdetection and missing detection, low detection accuracy, and slow detection speed of rail obstacles. The method of locating the track mask, demarcating the effective driving boundary, expanding the track mask, and forming the effective driving area is adopted to verify whether the target is an obstacle based on whether the target is located in the effective driving area, to avoid the problem of misdetection and missing detection of the target obstacle. The YOLACT++ (You Only Look At CoefficienTs) model is improved, and path augmentation and target classification loss function replacement strategies are adopted to enhance the model’s ability to detect target details and increase the accuracy of target segmentation. Compared with traditional image processing, this method can detect both straight rail and turnout. The mean average precision of boundary box mAP 0.5 (box) and mask mAP 0.5 (mask) of the improved YOLACT++ model reaches 98.52% and 98.55%, which is higher than that of the YOLACT++ model, and the detection frame rate reaches 21.9 frames per second.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135246187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-29DOI: 10.1177/03611981231198844
Nicholas D. Weitzel, Linda M. Pierce, Eric Carroll, Jesse (Jay) U. Thompson
Current traffic speed deflectometer (TSD) analyses have focused on the application of pavement structural-condition data at the network level. Pavement management systems use the deflection data to adjust the treatment as determined from the surface deflections and ride quality, resulting in better treatment selection. However, TSD data can also be used at the project level to inform pavement design decisions, though this has yet to be well documented in the U.S. A pilot study was conducted in 2021 to develop a methodology to analyze the TSD data for the South Carolina Department of Transportation (SCDOT) based on the AASHTO 1993 overlay design methodology. The TSD analysis methodology determines the effective structural number for each TSD datapoint. The results generated from this analysis were used for an ongoing construction project to assess the structural condition of the pavement within the project limits. Grade restrictions on the project presented a challenge in determining limits of pavement reconstruction and pavement overlay. The results of the TSD analysis were used to characterize the effective structural number at a 52 ft interval, allowing for optimization of the limits of pavement reconstruction. This paper presents the TSD analysis methodology used and how SCDOT incorporated the TSD results at the project level to perform rehabilitation designs of an ongoing construction project.
{"title":"Use of Traffic Speed Deflectometer Data in Project-Level Pavement Rehabilitation Design","authors":"Nicholas D. Weitzel, Linda M. Pierce, Eric Carroll, Jesse (Jay) U. Thompson","doi":"10.1177/03611981231198844","DOIUrl":"https://doi.org/10.1177/03611981231198844","url":null,"abstract":"Current traffic speed deflectometer (TSD) analyses have focused on the application of pavement structural-condition data at the network level. Pavement management systems use the deflection data to adjust the treatment as determined from the surface deflections and ride quality, resulting in better treatment selection. However, TSD data can also be used at the project level to inform pavement design decisions, though this has yet to be well documented in the U.S. A pilot study was conducted in 2021 to develop a methodology to analyze the TSD data for the South Carolina Department of Transportation (SCDOT) based on the AASHTO 1993 overlay design methodology. The TSD analysis methodology determines the effective structural number for each TSD datapoint. The results generated from this analysis were used for an ongoing construction project to assess the structural condition of the pavement within the project limits. Grade restrictions on the project presented a challenge in determining limits of pavement reconstruction and pavement overlay. The results of the TSD analysis were used to characterize the effective structural number at a 52 ft interval, allowing for optimization of the limits of pavement reconstruction. This paper presents the TSD analysis methodology used and how SCDOT incorporated the TSD results at the project level to perform rehabilitation designs of an ongoing construction project.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135199353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：