In existing airport gate allocation studies, little consideration has been given to situations where gate resources are limited during peak periods. Under such circumstances, some flights may not be able to make regular stops. In this paper, the airport gate assignment problem under peak time is investigated. We propose a gate pre-assignment model to maximize the gate matching degree and the near gate passenger allocation rate. Besides, to minimize the pre-assignment gate change rate, we propose a dynamic reassignment model based on the pre-assignment model. By considering the non-deterministic polynomial hard (NP-hard) property of this problem, a gate assignment algorithm based on proximal policy optimization (GABPPO) is proposed. The simulation results show that the algorithm can effectively solve the gate shortage problem during the airport peak period. Compared with the adaptive parallel genetic, deep Q-network, and policy gradient algorithms, the target value of solutions obtained by the proposed algorithm in the near gate passenger allocation rate is increased by 5.7%, 3.6%, and 7.9%, respectively, and the target value in the gate matching degree is increased by 10.6%, 4.9%, and 11.5% respectively.
{"title":"Gate Assignment Algorithm for Airport Peak Time Based on Reinforcement Learning","authors":"Chenwei Zhu, Zhenchun Wei, Zengwei Lyu, Xiaohui Yuan, Dawei Hang, Lin Feng","doi":"10.1177/03611981241242352","DOIUrl":"https://doi.org/10.1177/03611981241242352","url":null,"abstract":"In existing airport gate allocation studies, little consideration has been given to situations where gate resources are limited during peak periods. Under such circumstances, some flights may not be able to make regular stops. In this paper, the airport gate assignment problem under peak time is investigated. We propose a gate pre-assignment model to maximize the gate matching degree and the near gate passenger allocation rate. Besides, to minimize the pre-assignment gate change rate, we propose a dynamic reassignment model based on the pre-assignment model. By considering the non-deterministic polynomial hard (NP-hard) property of this problem, a gate assignment algorithm based on proximal policy optimization (GABPPO) is proposed. The simulation results show that the algorithm can effectively solve the gate shortage problem during the airport peak period. Compared with the adaptive parallel genetic, deep Q-network, and policy gradient algorithms, the target value of solutions obtained by the proposed algorithm in the near gate passenger allocation rate is increased by 5.7%, 3.6%, and 7.9%, respectively, and the target value in the gate matching degree is increased by 10.6%, 4.9%, and 11.5% respectively.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141106850","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 : 2024-05-23DOI: 10.1177/03611981241243081
Yue Wang, Enjian Yao, Yongsheng Zhang, Long Pan, He Hao
Urban rail transit (URT) has emerged as a crucial mode of transportation in metropolitan areas. For the effective operation of expanding URT networks, accurate short-term origin–destination (OD) demand distribution predictions are essential. This study introduces a novel deep-learning-based model for predicting short-term OD distribution in extensive networks, taking destination choice behaviors into account. First, we perform a comprehensive analysis of station passenger flows and OD flows from both temporal and spatial dimensions. Then, we develop the origin–destination distribution prediction (ODDP) model, combining the destination choice model (DCM) with the deep learning model (DLM). The DCM aims to understand OD distribution patterns from a behavioral perspective by transforming real-time inflows into OD distributions. Meanwhile, the DLM, employing attention and convolution layers, effectively captures the intricate temporal and spatial dynamics of passenger flows. Our model is evaluated using data from the Guangzhou Metro network in China, showing significant enhancements in prediction accuracy, model interpretability, and overall robustness. The implementation of our model promises substantial benefits for the operational efficiency of URT systems.
城市轨道交通（URT）已成为大都市地区的重要交通方式。为了有效运营不断扩大的城市轨道交通网络，准确预测短期出发地-目的地（OD）需求分布至关重要。本研究引入了一种基于深度学习的新型模型，用于预测广泛网络中的短期始发站分布，并将目的地选择行为考虑在内。首先，我们从时间和空间两个维度对车站客流和 OD 流量进行了全面分析。然后，我们结合目的地选择模型（DCM）和深度学习模型（DLM），开发了始发站-目的地分布预测（ODDP）模型。DCM 旨在通过将实时流入量转化为 OD 分布，从行为角度理解 OD 分布模式。同时，DLM 采用注意力层和卷积层，能有效捕捉客流错综复杂的时空动态。我们使用中国广州地铁网络的数据对模型进行了评估，结果表明，我们的模型在预测准确性、模型可解释性和整体鲁棒性方面都有显著提高。我们模型的实施有望大大提高城市轨道交通系统的运营效率。
{"title":"Deep Learning Model for Short-Term Origin–Destination Distribution Prediction in Urban Rail Transit Network Considering Destination Choice Behavior","authors":"Yue Wang, Enjian Yao, Yongsheng Zhang, Long Pan, He Hao","doi":"10.1177/03611981241243081","DOIUrl":"https://doi.org/10.1177/03611981241243081","url":null,"abstract":"Urban rail transit (URT) has emerged as a crucial mode of transportation in metropolitan areas. For the effective operation of expanding URT networks, accurate short-term origin–destination (OD) demand distribution predictions are essential. This study introduces a novel deep-learning-based model for predicting short-term OD distribution in extensive networks, taking destination choice behaviors into account. First, we perform a comprehensive analysis of station passenger flows and OD flows from both temporal and spatial dimensions. Then, we develop the origin–destination distribution prediction (ODDP) model, combining the destination choice model (DCM) with the deep learning model (DLM). The DCM aims to understand OD distribution patterns from a behavioral perspective by transforming real-time inflows into OD distributions. Meanwhile, the DLM, employing attention and convolution layers, effectively captures the intricate temporal and spatial dynamics of passenger flows. Our model is evaluated using data from the Guangzhou Metro network in China, showing significant enhancements in prediction accuracy, model interpretability, and overall robustness. The implementation of our model promises substantial benefits for the operational efficiency of URT systems.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141104965","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 : 2024-05-23DOI: 10.1177/03611981241247051
Mayar Ariss, An Wang, Sadegh Sabouri, Fabio Duarte, Carlo Ratti
Monitoring environmental features, such as air pollution, carbon dioxide emissions, noise, and heat, gives cities key data-driven insights to advise sustainable policies and city design. However, given the high variability of the environmental data, achieving good spatio-temporal resolution and coverage remains a major challenge. Even in well-monitored cities, such as Amsterdam, environmental sensors are usually placed in very few fixed locations, implying limited spatial coverage and an inability to adapt to changes in the urban environment. As cities evolve, they experience shifts in pollution sources, and fixed sensors might not adequately capture these changes without a costly and time-consuming reconfiguration process. To monitor the environmental qualities of Amsterdam’s roads, we present a “drive-by” sensing solution for a structured network of vehicles, meaning that sensors are designed to be deployed on buses and tramways, the trajectories and schedules of which are known. We propose a deployment strategy that combines the available fleets to reach optimal spatio-temporal coverage for different environmental features. For example, by optimizing the deployment of sensors on public transit vehicles, our proposal significantly enhances the monitoring of pollution-sensitive areas in Amsterdam. Depending on the desired spatio-temporal granularity and noting that one vehicle only hosts one sensor, the required number of sensors to be deployed on the structured network varies between 43 and 142, with the latter achieving the finest possible resolution.
{"title":"Drive-by Environmental Sensing Strategy to Reach Optimal and Continuous Spatio-Temporal Coverage Using Local Transit Network","authors":"Mayar Ariss, An Wang, Sadegh Sabouri, Fabio Duarte, Carlo Ratti","doi":"10.1177/03611981241247051","DOIUrl":"https://doi.org/10.1177/03611981241247051","url":null,"abstract":"Monitoring environmental features, such as air pollution, carbon dioxide emissions, noise, and heat, gives cities key data-driven insights to advise sustainable policies and city design. However, given the high variability of the environmental data, achieving good spatio-temporal resolution and coverage remains a major challenge. Even in well-monitored cities, such as Amsterdam, environmental sensors are usually placed in very few fixed locations, implying limited spatial coverage and an inability to adapt to changes in the urban environment. As cities evolve, they experience shifts in pollution sources, and fixed sensors might not adequately capture these changes without a costly and time-consuming reconfiguration process. To monitor the environmental qualities of Amsterdam’s roads, we present a “drive-by” sensing solution for a structured network of vehicles, meaning that sensors are designed to be deployed on buses and tramways, the trajectories and schedules of which are known. We propose a deployment strategy that combines the available fleets to reach optimal spatio-temporal coverage for different environmental features. For example, by optimizing the deployment of sensors on public transit vehicles, our proposal significantly enhances the monitoring of pollution-sensitive areas in Amsterdam. Depending on the desired spatio-temporal granularity and noting that one vehicle only hosts one sensor, the required number of sensors to be deployed on the structured network varies between 43 and 142, with the latter achieving the finest possible resolution.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141106171","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 : 2024-05-21DOI: 10.1177/03611981241244793
Reza Salehfard, Sadegh Yeganeh, D. Dalmazzo, B. S. Underwood, E. Santagata
The study described in this paper aims to establish the relationship between the chemical composition and rheological properties of asphalt binders in both the linear viscoelastic (LVE) and nonlinear viscoelastic (NLVE) domains. Two asphalt binders with different penetration grades were subjected to four distinct aging treatments of varying severity, resulting in changes in their chemical fingerprints. Chemical characteristics of the asphalt binders were analyzed using thin-layer chromatography (TLC), Fourier Transform infrared spectroscopy (FTIR), and gel permeation chromatography (GPC). Frequency sweep tests were conducted to evaluate the LVE behavior of the asphalt binders, while multiple stress creep recovery (MSCR) tests were employed to assess their NLVE properties. With regard to the LVE properties, rheological index ( R) and zero shear viscosity (ZSV) derived from the Christensen-Anderson-Marasteanu (CAM) model exhibited high correlations with FTIR and molecular weight distribution (MWD) parameters. Additionally, the polydispersity index (PDI) displayed a stronger correlation with LVE-based parameters. Findings from the MSCR tests revealed that the sensitivity of the percentage recovery ( %R) to chemical composition, as opposed to nonrecoverable creep compliance ( Jnr), can be largely attributed to the degree of nonlinearity. Furthermore, it was observed that lower molecular weight molecules exert a greater influence on %R in the nonlinear domain. Finally, it was found that Jnrslope is a more reliable parameter than Jnrdiff for assessing the effects of chemical makeup on stress and temperature sensitivity.
{"title":"Linking Chemical Structure to the Linear and Nonlinear Properties of Asphalt Binders","authors":"Reza Salehfard, Sadegh Yeganeh, D. Dalmazzo, B. S. Underwood, E. Santagata","doi":"10.1177/03611981241244793","DOIUrl":"https://doi.org/10.1177/03611981241244793","url":null,"abstract":"The study described in this paper aims to establish the relationship between the chemical composition and rheological properties of asphalt binders in both the linear viscoelastic (LVE) and nonlinear viscoelastic (NLVE) domains. Two asphalt binders with different penetration grades were subjected to four distinct aging treatments of varying severity, resulting in changes in their chemical fingerprints. Chemical characteristics of the asphalt binders were analyzed using thin-layer chromatography (TLC), Fourier Transform infrared spectroscopy (FTIR), and gel permeation chromatography (GPC). Frequency sweep tests were conducted to evaluate the LVE behavior of the asphalt binders, while multiple stress creep recovery (MSCR) tests were employed to assess their NLVE properties. With regard to the LVE properties, rheological index ( R) and zero shear viscosity (ZSV) derived from the Christensen-Anderson-Marasteanu (CAM) model exhibited high correlations with FTIR and molecular weight distribution (MWD) parameters. Additionally, the polydispersity index (PDI) displayed a stronger correlation with LVE-based parameters. Findings from the MSCR tests revealed that the sensitivity of the percentage recovery ( %R) to chemical composition, as opposed to nonrecoverable creep compliance ( Jnr), can be largely attributed to the degree of nonlinearity. Furthermore, it was observed that lower molecular weight molecules exert a greater influence on %R in the nonlinear domain. Finally, it was found that Jnrslope is a more reliable parameter than Jnrdiff for assessing the effects of chemical makeup on stress and temperature sensitivity.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141115753","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 : 2024-05-21DOI: 10.1177/03611981241246993
Younis Matouq, Dmitry Manasreh, Munir D. Nazzal
Given the potential hazards and risks that potholes pose to road users, this study introduces an image-based system that utilizes a combination of a camera and GPS for real-time detection, georeferencing, and area estimation of potholes. The captured system data is processed in real-time using YOLOv8, a deep learning model proficient in object detection and segmentation. To enhance the precision and reduce the occurrence of false detections, the system is specifically trained to detect potholes, manholes, and patches. Additionally, the camera is calibrated to accurately estimate the area of identified potholes. The proposed system achieved a mean average precision of 91% in detecting potholes, 98% in detecting manholes, and 90% for detecting patches. A salient feature of this system is its capability to localize potholes with reference to pavement line lane markings. This ability could facilitate proactive lane closure planning by maintenance crews, further enhancing road safety measures. The study findings suggest that the system holds significant potential for practical implementation. Its deployment could assist transportation agencies in the prioritization of road repairs, resource allocation, and advance planning for lane closures, ultimately enhancing the efficiency of their maintenance workflows.
{"title":"AI-Driven Approach for Automated Real-Time Pothole Detection, Localization, and Area Estimation","authors":"Younis Matouq, Dmitry Manasreh, Munir D. Nazzal","doi":"10.1177/03611981241246993","DOIUrl":"https://doi.org/10.1177/03611981241246993","url":null,"abstract":"Given the potential hazards and risks that potholes pose to road users, this study introduces an image-based system that utilizes a combination of a camera and GPS for real-time detection, georeferencing, and area estimation of potholes. The captured system data is processed in real-time using YOLOv8, a deep learning model proficient in object detection and segmentation. To enhance the precision and reduce the occurrence of false detections, the system is specifically trained to detect potholes, manholes, and patches. Additionally, the camera is calibrated to accurately estimate the area of identified potholes. The proposed system achieved a mean average precision of 91% in detecting potholes, 98% in detecting manholes, and 90% for detecting patches. A salient feature of this system is its capability to localize potholes with reference to pavement line lane markings. This ability could facilitate proactive lane closure planning by maintenance crews, further enhancing road safety measures. The study findings suggest that the system holds significant potential for practical implementation. Its deployment could assist transportation agencies in the prioritization of road repairs, resource allocation, and advance planning for lane closures, ultimately enhancing the efficiency of their maintenance workflows.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141117320","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 : 2024-05-21DOI: 10.1177/03611981241242774
John W. DeSantis, Jeffery Roesler
The performance of concrete pavements and overlays is highly dependent on the uniformity, durability, and stability of the underlying support layers. Erosion of support layers can lead to pavement distresses and a reduction in pavement life. A review of existing erodibility performance tests that assessed stabilized support layers was first conducted to identify and evaluate their suitability for adaptation. The Hamburg wheel tracking device (HWTD) test was selected to assess the erosion potential of asphalt and cement stabilized support layers. Field testing with distress surveys, falling weight deflectometer, and coring was completed to obtain HWTD specimens and link laboratory results to pavement performance. The HWTD test was performed on cores obtained from in-service cement and asphalt stabilized support layers, a cold in-place recycling (CIR) mixture, and cement stabilized laboratory mixtures. As expected, an increase in cement content within cement stabilized mixtures decreases the likelihood of erosion with the HWTD. Additionally, conventional asphalt stabilized base layers were highly erosion resistant. Erosion resistant cement stabilized bases (including full-depth reclamation) should target an average HWTD erosion depth ≤2 to 4 mm (0.08 to 0.16 in.) after 10,000 load cycles based on the functional classification and expected traffic volume of the pavement section. Likewise, asphalt stabilized bases (including CIR and support layers for concrete overlays) should target an average HWTD erosion depth ≤12.5 mm (0.5 in.) after 7,500 load cycles with performance grade 64 binder.
{"title":"Erosion Potential of Stabilized Support Layers for Concrete Pavements and Overlays","authors":"John W. DeSantis, Jeffery Roesler","doi":"10.1177/03611981241242774","DOIUrl":"https://doi.org/10.1177/03611981241242774","url":null,"abstract":"The performance of concrete pavements and overlays is highly dependent on the uniformity, durability, and stability of the underlying support layers. Erosion of support layers can lead to pavement distresses and a reduction in pavement life. A review of existing erodibility performance tests that assessed stabilized support layers was first conducted to identify and evaluate their suitability for adaptation. The Hamburg wheel tracking device (HWTD) test was selected to assess the erosion potential of asphalt and cement stabilized support layers. Field testing with distress surveys, falling weight deflectometer, and coring was completed to obtain HWTD specimens and link laboratory results to pavement performance. The HWTD test was performed on cores obtained from in-service cement and asphalt stabilized support layers, a cold in-place recycling (CIR) mixture, and cement stabilized laboratory mixtures. As expected, an increase in cement content within cement stabilized mixtures decreases the likelihood of erosion with the HWTD. Additionally, conventional asphalt stabilized base layers were highly erosion resistant. Erosion resistant cement stabilized bases (including full-depth reclamation) should target an average HWTD erosion depth ≤2 to 4 mm (0.08 to 0.16 in.) after 10,000 load cycles based on the functional classification and expected traffic volume of the pavement section. Likewise, asphalt stabilized bases (including CIR and support layers for concrete overlays) should target an average HWTD erosion depth ≤12.5 mm (0.5 in.) after 7,500 load cycles with performance grade 64 binder.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141118339","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 : 2024-05-21DOI: 10.1177/03611981241243078
Chao Fan, Xiao Wang, Zhixiang Chen, Bincheng Peng
To maintain robustness in complex and uncontrollable real-world driving scenarios, this paper proposes a new segmentation-based coarse-to-fine lane line model (CTFNet). Which embeds dual-pathway attention (DPA) in the coarse segmentation encoder-decoder architecture to fuse high and low-level features with dual inputs, taking the strengths and complementing the weaknesses, and at the same time being able to capture more spatial detail information. However, the extracted lane line cues are limited in extreme conditions. As a result, a feature localization module (FLM) is proposed which extracts the global contextual information of the occluded region along the vertical and horizontal axes and determines lane line location by predicting the confidence of the lane lines based on the extracted information. Additionally, some regions of the initial feature map of the coarse segmentation network are difficult to distinguish between classes, the uncertain region refinement module (URRM) is designed in the fine stage to gradually refine the uncertain pixels using the relationship between adjacent features. Finally, the model is extensively tested on the tvtLANE data set, and the results show that CTFNet outperforms most state-of-the-art methods with an F1-measure of 91.48%, which not only reduces false detection but also maintains good robustness in extremely difficult scenarios.
为了在复杂、不可控的真实世界驾驶场景中保持鲁棒性，本文提出了一种新的基于细分的粗到细车道线模型（CTFNet）。该模型将双通道注意力（DPA）嵌入到粗分割编码器-解码器架构中，通过双输入融合高低级特征，取长补短，同时能够捕捉到更多的空间细节信息。然而，在极端条件下，提取的车道线线索是有限的。因此，我们提出了一个特征定位模块（FLM），该模块可沿纵轴和横轴提取闭塞区域的全局上下文信息，并根据提取的信息预测车道线的置信度，从而确定车道线的位置。此外，粗分割网络的初始特征图中有些区域难以区分类别，因此在精细阶段设计了不确定区域细化模块（URRM），利用相邻特征之间的关系逐步细化不确定像素。最后，在 tvtLANE 数据集上对该模型进行了广泛测试，结果表明 CTFNet 的 F1 测量值为 91.48%，优于大多数最先进的方法，不仅降低了误检率，而且在极端困难的场景下保持了良好的鲁棒性。
{"title":"CTFNet: Coarse-to-Fine Segmented Lane Line Detection in Complex Road Conditions","authors":"Chao Fan, Xiao Wang, Zhixiang Chen, Bincheng Peng","doi":"10.1177/03611981241243078","DOIUrl":"https://doi.org/10.1177/03611981241243078","url":null,"abstract":"To maintain robustness in complex and uncontrollable real-world driving scenarios, this paper proposes a new segmentation-based coarse-to-fine lane line model (CTFNet). Which embeds dual-pathway attention (DPA) in the coarse segmentation encoder-decoder architecture to fuse high and low-level features with dual inputs, taking the strengths and complementing the weaknesses, and at the same time being able to capture more spatial detail information. However, the extracted lane line cues are limited in extreme conditions. As a result, a feature localization module (FLM) is proposed which extracts the global contextual information of the occluded region along the vertical and horizontal axes and determines lane line location by predicting the confidence of the lane lines based on the extracted information. Additionally, some regions of the initial feature map of the coarse segmentation network are difficult to distinguish between classes, the uncertain region refinement module (URRM) is designed in the fine stage to gradually refine the uncertain pixels using the relationship between adjacent features. Finally, the model is extensively tested on the tvtLANE data set, and the results show that CTFNet outperforms most state-of-the-art methods with an F1-measure of 91.48%, which not only reduces false detection but also maintains good robustness in extremely difficult scenarios.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141118698","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 : 2024-05-21DOI: 10.1177/03611981241245673
Greg Erhardt, David Hensle, Mark Bradley, Michelle Imarah, Joel Freedman, Max Gardner, B. Stabler
Characteristics of household vehicles can influence daily travel behavior and can vary greatly by vehicle type. Vehicle type is defined here as a combination of body type, fuel type, and age. Using data compiled primarily from the National Household Travel Survey, a multinomial logit model was developed to predict vehicle type based on characteristics of the household that owns the vehicle. The model was then implemented for the San Francisco Bay Area in the ActivitySim activity-based modeling framework and validated against observed data. The ActivitySim project’s goal is to create and maintain advanced, open-source, activity-based travel behavior modeling software, based on best software development practices, for distribution to the public, free of charge. A naïve 2030 scenario was analyzed to show model response to changes in the vehicle fleet.
{"title":"Estimating and Implementing a Vehicle-Type Model in an Activity-Based Travel Model Framework","authors":"Greg Erhardt, David Hensle, Mark Bradley, Michelle Imarah, Joel Freedman, Max Gardner, B. Stabler","doi":"10.1177/03611981241245673","DOIUrl":"https://doi.org/10.1177/03611981241245673","url":null,"abstract":"Characteristics of household vehicles can influence daily travel behavior and can vary greatly by vehicle type. Vehicle type is defined here as a combination of body type, fuel type, and age. Using data compiled primarily from the National Household Travel Survey, a multinomial logit model was developed to predict vehicle type based on characteristics of the household that owns the vehicle. The model was then implemented for the San Francisco Bay Area in the ActivitySim activity-based modeling framework and validated against observed data. The ActivitySim project’s goal is to create and maintain advanced, open-source, activity-based travel behavior modeling software, based on best software development practices, for distribution to the public, free of charge. A naïve 2030 scenario was analyzed to show model response to changes in the vehicle fleet.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141114759","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 : 2024-05-21DOI: 10.1177/03611981241245987
Syed Faizan Husain, Robert Wiggins, Youngdae Kim, Yusra I. Alhadidi, E. Tutumluer
Extreme weather events driven by climate change pose significant threats to our transportation infrastructure, particularly road pavements, in the United States. This paper proposes a guiding framework for designing resilient pavements. The framework was established after comprehensive reviews of the state of practice from pavement design manuals and construction-, implementation-, and practice documents publicly available on websites of state departments of transportation (DOTs) across the country. The objective of this study was to evaluate the infrastructure flood readiness and awareness of transportation agencies based on the state DOT website surveys. Qualitative analyses of transportation agency engineering and construction manuals revealed a varying degree of consideration among the different states for resiliency in transportation infrastructure design policies. Web scraping of state DOT websites highlighted the awareness levels of resiliency and sustainability issues concerning pavements. The importance of constructing permeable pavement base layers to alleviate flood-induced damage was investigated for assessing moisture infiltration effects on pavement performance and how to incorporate these improvements into mechanistic-empirical pavement design concepts. The findings underscored the need to incorporate climate change stressors and predictive climate data modeling in pavement design to enhance infrastructure resilience. Through study findings and considering implementation of the guidelines proposed in this paper, transportation engineers and state agencies are anticipated to be able to better prepare for future extreme weather challenges and safeguard the nation’s transportation assets.
{"title":"Resiliency Against Flooding in Pavement Geotechnics: Practice Review of State Transportation Agencies","authors":"Syed Faizan Husain, Robert Wiggins, Youngdae Kim, Yusra I. Alhadidi, E. Tutumluer","doi":"10.1177/03611981241245987","DOIUrl":"https://doi.org/10.1177/03611981241245987","url":null,"abstract":"Extreme weather events driven by climate change pose significant threats to our transportation infrastructure, particularly road pavements, in the United States. This paper proposes a guiding framework for designing resilient pavements. The framework was established after comprehensive reviews of the state of practice from pavement design manuals and construction-, implementation-, and practice documents publicly available on websites of state departments of transportation (DOTs) across the country. The objective of this study was to evaluate the infrastructure flood readiness and awareness of transportation agencies based on the state DOT website surveys. Qualitative analyses of transportation agency engineering and construction manuals revealed a varying degree of consideration among the different states for resiliency in transportation infrastructure design policies. Web scraping of state DOT websites highlighted the awareness levels of resiliency and sustainability issues concerning pavements. The importance of constructing permeable pavement base layers to alleviate flood-induced damage was investigated for assessing moisture infiltration effects on pavement performance and how to incorporate these improvements into mechanistic-empirical pavement design concepts. The findings underscored the need to incorporate climate change stressors and predictive climate data modeling in pavement design to enhance infrastructure resilience. Through study findings and considering implementation of the guidelines proposed in this paper, transportation engineers and state agencies are anticipated to be able to better prepare for future extreme weather challenges and safeguard the nation’s transportation assets.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141114266","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 : 2024-05-20DOI: 10.1177/03611981241239970
Seyed Mehdi Meshkani, S. Farazmand, Nizar Bouguila, Zachary Patterson
As a result of the lack of access to efficient public transit in suburban areas, residents often have to use their own vehicles to commute either within the area, to neighboring regions, or to a public transit hub (PTH). Thanks to information and communication technologies, on-demand transit (ODT) is a potential solution being proposed and considered by transit agencies. Although ODT has shown the potential to enhance transit level of service, its efficiency depends on different parameters such as demand spatial and temporal distribution or the configuration of the service. In this study, we propose a novel configuration for an ODT service and apply it to the first part of a commuter’s trip, or the commuter’s “first mile.” The proposed configuration depends on the availability of smart devices installed at bus stops. Passengers request their rides via smart devices and receive real-time and personalized information about their ride requests to travel to a PTH. The proposed ODT service is modeled with the Simulation of Urban Mobility or SUMO simulation framework. To evaluate the performance of the ODT service, it is applied to the city of Terrebonne in Quebec, Canada. The proposed service is compared with existing bus transit operating in the area as well as a door-to-PTH service. The results of the comparison analysis reveal that the proposed ODT service may result in a significant 36% reduction in total travel time as well as a 41% reduction in detour time compared with the existing bus transit service. A detailed sensitivity analysis is also conducted to capture the impacts of different parameters, variables, and dispatching algorithms on the service performance.
{"title":"Innovative On-Demand Transit for First-Mile Trips: A Cutting-Edge Approach","authors":"Seyed Mehdi Meshkani, S. Farazmand, Nizar Bouguila, Zachary Patterson","doi":"10.1177/03611981241239970","DOIUrl":"https://doi.org/10.1177/03611981241239970","url":null,"abstract":"As a result of the lack of access to efficient public transit in suburban areas, residents often have to use their own vehicles to commute either within the area, to neighboring regions, or to a public transit hub (PTH). Thanks to information and communication technologies, on-demand transit (ODT) is a potential solution being proposed and considered by transit agencies. Although ODT has shown the potential to enhance transit level of service, its efficiency depends on different parameters such as demand spatial and temporal distribution or the configuration of the service. In this study, we propose a novel configuration for an ODT service and apply it to the first part of a commuter’s trip, or the commuter’s “first mile.” The proposed configuration depends on the availability of smart devices installed at bus stops. Passengers request their rides via smart devices and receive real-time and personalized information about their ride requests to travel to a PTH. The proposed ODT service is modeled with the Simulation of Urban Mobility or SUMO simulation framework. To evaluate the performance of the ODT service, it is applied to the city of Terrebonne in Quebec, Canada. The proposed service is compared with existing bus transit operating in the area as well as a door-to-PTH service. The results of the comparison analysis reveal that the proposed ODT service may result in a significant 36% reduction in total travel time as well as a 41% reduction in detour time compared with the existing bus transit service. A detailed sensitivity analysis is also conducted to capture the impacts of different parameters, variables, and dispatching algorithms on the service performance.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120516","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：