Pub Date : 2024-09-21DOI: 10.1016/j.trc.2024.104858
Accurate monitoring and sensing network-wide traffic conditions under uncertainty is vital for addressing urban transportation obstacles and promoting the evolution of intelligent transportation systems (ITS). Owing to fluctuations in traffic demand, traffic conditions exhibit stochastic variations by the time of day and day of the year. The joint estimation of stochastic speed and flow is pivotal in ITS, drawing on the symbiotic relationship between these two variables to furnish comprehensive insights into traffic conditions. Nevertheless, constraints such as budgetary limitations and physical boundaries render the coverage of traffic detectors both sparse and inadequate, thereby complicating the precise assessment of network-wide traffic speeds and flows in uncertain scenarios. To address this challenging problem, this paper proposes a novel network-wide traffic speed-flow estimator (SFE) grounded in the Kullback-Leibler divergence optimization method. This SFE harnesses data derived from sparse multi-type detectors, such as point detectors and automatic vehicle identification sensors. Significantly, it leverages the statistical correlation relationships (i.e., covariance matrix) of the speed and flow between observed and unobserved links to estimate stochastic speed and flow on unobserved links (i.e., the links without traffic detectors). In addition, fundamental diagrams, modeling the interdependence between link speeds and flows, are incorporated as constraints in the proposed SFE. This inclusion markedly diminishes discrepancies and elevates estimation precision relative to individual assessments of speeds and flows. Numerical illustrations, encompassing both simulated and real-world road networks, validate the enhanced performance and applicability of the proposed SFE, suggesting its potential role in augmenting data robustness within ITS.
{"title":"Network-wide speed–flow estimation considering uncertain traffic conditions and sparse multi-type detectors: A KL divergence-based optimization approach","authors":"","doi":"10.1016/j.trc.2024.104858","DOIUrl":"10.1016/j.trc.2024.104858","url":null,"abstract":"<div><p>Accurate monitoring and sensing network-wide traffic conditions under uncertainty is vital for addressing urban transportation obstacles and promoting the evolution of intelligent transportation systems (ITS). Owing to fluctuations in traffic demand, traffic conditions exhibit stochastic variations by the time of day and day of the year. The joint estimation of stochastic speed and flow is pivotal in ITS, drawing on the symbiotic relationship between these two variables to furnish comprehensive insights into traffic conditions. Nevertheless, constraints such as budgetary limitations and physical boundaries render the coverage of traffic detectors both sparse and inadequate, thereby complicating the precise assessment of network-wide traffic speeds and flows in uncertain scenarios. To address this challenging problem, this paper proposes a novel network-wide traffic speed-flow estimator (SFE) grounded in the Kullback-Leibler divergence optimization method. This SFE harnesses data derived from sparse multi-type detectors, such as point detectors and automatic vehicle identification sensors. Significantly, it leverages the statistical correlation relationships (i.e., covariance matrix) of the speed and flow between observed and unobserved links to estimate stochastic speed and flow on unobserved links (i.e., the links without traffic detectors). In addition, fundamental diagrams, modeling the interdependence between link speeds and flows, are incorporated as constraints in the proposed SFE. This inclusion markedly diminishes discrepancies and elevates estimation precision relative to individual assessments of speeds and flows. Numerical illustrations, encompassing both simulated and real-world road networks, validate the enhanced performance and applicability of the proposed SFE, suggesting its potential role in augmenting data robustness within ITS.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-09-21DOI: 10.1016/j.trc.2024.104857
Introducing electric vehicles that tow aircraft during taxiing is an emerging technology aimed at supporting climate neutrality for aviation. Planning electric towing operations is, however, impeded by the high uncertainty in aircraft arrival and departure times. We address the question of how to plan the operation of a fleet of Electric Towing Vehicles (ETVs) to maximize environmental benefits, given the uncertainty in aircraft arrival/departure times. For this, we propose a stochastic and dynamic planning framework for ETVs, where stochastic aircraft arrival and departure times are updated during the day. With this, the assignment of the ETVs-to-aircraft to replace conventional taxiing, and ETV battery charging times are planned such that the fuel savings are maximized. At the same time, we ensure that aircraft delays induced by the use of ETVs are minimized. We illustrate our framework for a large European airport. The results show that our framework achieves 79.5% of the highest possible cost reduction (fuel and ETV-induced delay), which is obtained when full knowledge of the arrival/departure times is available in advance. Furthermore, we show that considering the uncertainty in the arrival/departure times, rather than using point estimates of these times, leads to a 17.7% additional cost reduction. Overall, our framework supports the implementation of electric aircraft towing with maximum environmental benefits while considering the dynamic, uncertain arrival and departure times of aircraft.
在飞机滑行过程中引入电动车辆牵引飞机是一项新兴技术,旨在支持航空业的气候中和。然而,飞机到达和起飞时间的高度不确定性阻碍了电动牵引运行的规划。我们要解决的问题是,在飞机到达/起飞时间不确定的情况下,如何规划电动拖车(ETV)车队的运营,以实现环境效益最大化。为此,我们为电动拖车提出了一个随机和动态规划框架,其中随机飞机到达和起飞时间在一天中不断更新。有了这个框架,就可以规划 ETV 对飞机的分配,以取代传统的滑行和 ETV 电池充电时间,从而最大限度地节省燃料。同时,我们还确保将因使用 ETV 而导致的飞机延误降至最低。我们以一个大型欧洲机场为例说明了我们的框架。结果表明,我们的框架实现了 79.5% 的最高可能成本降低率(燃油和 ETV 引起的延误),而这是在提前完全了解到达/出发时间的情况下实现的。此外,我们还表明,考虑到到达/出发时间的不确定性,而不是使用这些时间的点估计值,可额外降低 17.7% 的成本。总之,我们的框架支持实施电动飞机牵引,在考虑飞机动态、不确定的到达和起飞时间的同时,实现最大的环境效益。
{"title":"An environmentally-aware dynamic planning of electric vehicles for aircraft towing considering stochastic aircraft arrival and departure times","authors":"","doi":"10.1016/j.trc.2024.104857","DOIUrl":"10.1016/j.trc.2024.104857","url":null,"abstract":"<div><p>Introducing electric vehicles that tow aircraft during taxiing is an emerging technology aimed at supporting climate neutrality for aviation. Planning electric towing operations is, however, impeded by the high uncertainty in aircraft arrival and departure times. We address the question of how to plan the operation of a fleet of Electric Towing Vehicles (ETVs) to maximize environmental benefits, given the uncertainty in aircraft arrival/departure times. For this, we propose a stochastic and dynamic planning framework for ETVs, where stochastic aircraft arrival and departure times are updated during the day. With this, the assignment of the ETVs-to-aircraft to replace conventional taxiing, and ETV battery charging times are planned such that the fuel savings are maximized. At the same time, we ensure that aircraft delays induced by the use of ETVs are minimized. We illustrate our framework for a large European airport. The results show that our framework achieves 79.5% of the highest possible cost reduction (fuel and ETV-induced delay), which is obtained when full knowledge of the arrival/departure times is available in advance. Furthermore, we show that considering the uncertainty in the arrival/departure times, rather than using point estimates of these times, leads to a 17.7% additional cost reduction. Overall, our framework supports the implementation of electric aircraft towing with maximum environmental benefits while considering the dynamic, uncertain arrival and departure times of aircraft.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0968090X24003784/pdfft?md5=537acccdda5fdce76188537c9dde0b89&pid=1-s2.0-S0968090X24003784-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-20DOI: 10.1016/j.trc.2024.104861
Intercity truck transport emerged as a crucial lifeline for maintaining city operations during COVID-19 pandemic. Understanding pandemic-imposed impacts on intercity truck transport can inform policymakers in crafting more effective strategies for future crises and disruptions. However, to our best knowledge, previous research predominantly focused on freight movements under normal circumstances. Due to the data limitation, the pandemic-related studies commonly relied on freight survey and focused on specific industries, which cannot capture the full spectrum of factors influencing freight trip generation (FTG) during the pandemic. Here, a novel dataset capturing large-scale individual truck movements during the COVID-19 pandemic is provided. By leveraging the mobility dataset, pandemic-induced changes in truck transport demand structure are quantified using spatial statistical methods. Furthermore, an interpretable machine learning framework for intercity freight demand estimation is developed, revealing the complex interplay of factors that influence and shape the behavior shifts of intercity truck transport systems due to the pandemic outbreak. The findings suggest significant changes in various factors influencing intercity truck movements across local and broader regions, emphasizing city-specific challenges amidst pandemic. The developed FTG model could serve as a tool to predict freight demand between cities for future crises and to support policymaking in the practice of freight management.
{"title":"Revealing the impacts of COVID-19 pandemic on intercity truck transport: New insights from big data analytics","authors":"","doi":"10.1016/j.trc.2024.104861","DOIUrl":"10.1016/j.trc.2024.104861","url":null,"abstract":"<div><p>Intercity truck transport emerged as a crucial lifeline for maintaining city operations during COVID-19 pandemic. Understanding pandemic-imposed impacts on intercity truck transport can inform policymakers in crafting more effective strategies for future crises and disruptions. However, to our best knowledge, previous research predominantly focused on freight movements under normal circumstances. Due to the data limitation, the pandemic-related studies commonly relied on freight survey and focused on specific industries, which cannot capture the full spectrum of factors influencing freight trip generation (FTG) during the pandemic. Here, a novel dataset capturing large-scale individual truck movements during the COVID-19 pandemic is provided. By leveraging the mobility dataset, pandemic-induced changes in truck transport demand structure are quantified using spatial statistical methods. Furthermore, an interpretable machine learning framework for intercity freight demand estimation is developed, revealing the complex interplay of factors that influence and shape the behavior shifts of intercity truck transport systems due to the pandemic outbreak. The findings suggest significant changes in various factors influencing intercity truck movements across local and broader regions, emphasizing city-specific challenges amidst pandemic. The developed FTG model could serve as a tool to predict freight demand between cities for future crises and to support policymaking in the practice of freight management.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-09-18DOI: 10.1016/j.trc.2024.104853
In the context of the global maritime industry, which plays a vital role in international trade, navigating vessels safely and efficiently remains a complex challenge, especially due to the absence of structured road-like networks on the open seas. This paper proposes MATNEC, a framework for constructing a data-driven Maritime Traffic Network (MTN), represented as a graph that facilitates realistic route generation. Our approach, leveraging Automatic Identification System (AIS) data along with portcall and global coastline datasets, aims to address key challenges in MTN construction from AIS data observed in the literature, particularly the imprecise placement of network nodes and sub-optimal definition of network edges. At the core of MATNEC is a novel incremental clustering algorithm that is capable of intelligently determining the placement and distribution of the graph nodes in a diverse set of environments, based on several environmental factors. To ensure that the resulting MTN generates maritime routes as realistic as possible, we design a novel edge mapping algorithm that defines the edges of the network by treating the mapping of AIS trajectories to network nodes as an optimisation problem. Finally, due to the absence of a unified approach in the literature for measuring the efficacy of an MTN’s ability to generate realistic routes, we propose a novel methodology to address this gap. Utilising our proposed evaluation methodology, we compare MATNEC with existing methods from literature. The outcome of these experiments affirm the enhanced performance of MATNEC compared to previous approaches.
{"title":"MATNEC: AIS data-driven environment-adaptive maritime traffic network construction for realistic route generation","authors":"","doi":"10.1016/j.trc.2024.104853","DOIUrl":"10.1016/j.trc.2024.104853","url":null,"abstract":"<div><p>In the context of the global maritime industry, which plays a vital role in international trade, navigating vessels safely and efficiently remains a complex challenge, especially due to the absence of structured road-like networks on the open seas. This paper proposes <span>MATNEC</span>, a framework for constructing a data-driven Maritime Traffic Network (MTN), represented as a graph that facilitates realistic route generation. Our approach, leveraging Automatic Identification System (AIS) data along with portcall and global coastline datasets, aims to address key challenges in MTN construction from AIS data observed in the literature, particularly the imprecise placement of network nodes and sub-optimal definition of network edges. At the core of <span>MATNEC</span> is a novel incremental clustering algorithm that is capable of intelligently determining the placement and distribution of the graph nodes in a diverse set of environments, based on several environmental factors. To ensure that the resulting MTN generates maritime routes as realistic as possible, we design a novel edge mapping algorithm that defines the edges of the network by treating the mapping of AIS trajectories to network nodes as an optimisation problem. Finally, due to the absence of a unified approach in the literature for measuring the efficacy of an MTN’s ability to generate realistic routes, we propose a novel methodology to address this gap. Utilising our proposed evaluation methodology, we compare <span>MATNEC</span> with existing methods from literature. The outcome of these experiments affirm the enhanced performance of <span>MATNEC</span> compared to previous approaches.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0968090X24003747/pdfft?md5=0f93587aa24aa8b2473134b6edb622fa&pid=1-s2.0-S0968090X24003747-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142240199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-16DOI: 10.1016/j.trc.2024.104797
This paper systematically analyzes the security risks associated with artificial intelligence (AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for various AV functions, from perception to control, the potential for security breaches presents a significant challenge. We focus on AI security, including attacks like adversarial examples, backdoors, privacy breaches and unauthorized model replication, reviewing over 170 papers. To evaluate the practical implications of such vulnerabilities we introduce qualitative measures for assessing the exposure and severity of potential attacks. Our findings highlight a critical need for more realistic security evaluations and a balanced focus on various sensors, learning paradigms, threat models, and studied attacks. We also pinpoint areas requiring more research, such as the study of training time attacks, transferability, system-based studies and development of effective defenses. By also outlining implications for the automotive industry and policymakers, we not only advance the understanding of AI security risks in AVs, but contribute to the development of safer and more reliable autonomous driving technologies.
{"title":"A qualitative AI security risk assessment of autonomous vehicles","authors":"","doi":"10.1016/j.trc.2024.104797","DOIUrl":"10.1016/j.trc.2024.104797","url":null,"abstract":"<div><p>This paper systematically analyzes the security risks associated with artificial intelligence (AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for various AV functions, from perception to control, the potential for security breaches presents a significant challenge. We focus on AI security, including attacks like adversarial examples, backdoors, privacy breaches and unauthorized model replication, reviewing over 170 papers. To evaluate the practical implications of such vulnerabilities we introduce qualitative measures for assessing the exposure and severity of potential attacks. Our findings highlight a critical need for more realistic security evaluations and a balanced focus on various sensors, learning paradigms, threat models, and studied attacks. We also pinpoint areas requiring more research, such as the study of training time attacks, transferability, system-based studies and development of effective defenses. By also outlining implications for the automotive industry and policymakers, we not only advance the understanding of AI security risks in AVs, but contribute to the development of safer and more reliable autonomous driving technologies.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0968090X24003188/pdfft?md5=8f29ca6bf8794384ab2ef11352a0cf13&pid=1-s2.0-S0968090X24003188-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142240198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-12DOI: 10.1016/j.trc.2024.104801
The dial-a-ride (DAR) service is a precursor to emerging shared mobility. Service providers expect efficient management of fleet resources to improve service quality without degrading economic viability. Most existing studies overlook possible future demands that could yield better matching opportunities and scheduling benefits, and therefore have short-sighted limitations. Moreover, the effects of correlated demand and potential prediction errors were ignored. To address these gaps, this paper investigates prediction-failure-risk-aware online DAR scheduling with spatial demand correlation. Request selection and cancellation are explicitly considered. We formulate the problem as a Markov decision process (MDP) and solve it by approximate dynamic programming (ADP). We further develop a demand prediction model that can capture the characteristics of DAR travel demand (uncertainty, sparsity, and spatial correlation). Deep quantile regression is adopted to estimate the marginal distribution of each OD pair. These marginals are combined into a joint demand distribution by constructing a Gaussian Copula to capture the spatial demand correlation. A prediction error correction mechanism is proposed to eliminate prediction errors and rectify policies promptly. Based on the model properties, several families of customized pruning strategies are devised to improve the computational efficiency and solution quality of ADP. We solve policies over time in the dynamic environment mixed with actual and stochastic future demands via the ADP algorithm and scenario approach. We propose the value function rolling method and multi-scenario exploration method, to address the deviation of the value function and identify the optimal policy from multiple future demand scenarios. Numerical results demonstrate the importance and benefits of incorporating demand forecasting and spatial correlation into the DAR operation. The improvement due to prediction is significant even when the prediction is imperfect, while the demand prediction can hedge against the negative effects of request cancellation. The real-world application result shows that compared to state-of-the-practice, the overall delivery efficiency can be substantially improved, along with better service quality and fleet size savings.
拨号乘车(DAR)服务是新兴共享交通的先驱。服务提供商希望有效管理车队资源,在不降低经济可行性的前提下提高服务质量。大多数现有研究都忽略了未来可能出现的需求,而这些需求可能带来更好的匹配机会和调度效益,因此存在短视的局限性。此外,相关需求和潜在预测误差的影响也被忽略了。为了弥补这些不足,本文研究了具有空间需求相关性的预测失败风险感知在线 DAR 调度。其中明确考虑了请求选择和取消。我们将问题表述为马尔可夫决策过程(MDP),并通过近似动态编程(ADP)来解决。我们进一步开发了一个需求预测模型,该模型可以捕捉到 DAR 旅行需求的特点(不确定性、稀疏性和空间相关性)。我们采用深度量化回归来估算每个 OD 对的边际分布。通过构建一个高斯 Copula 来捕捉空间需求相关性,从而将这些边际值组合成一个联合需求分布。提出了一种预测误差修正机制,以消除预测误差并及时纠正政策。根据模型特性,我们设计了多个定制剪枝策略系列,以提高 ADP 的计算效率和求解质量。我们通过 ADP 算法和情景方法,在混合了实际需求和随机未来需求的动态环境中求解随时间变化的政策。我们提出了价值函数滚动法和多情景探索法,以解决价值函数的偏差问题,并从多个未来需求情景中找出最优政策。数值结果证明了将需求预测和空间相关性纳入 DAR 运行的重要性和益处。即使预测不完美,预测带来的改进也是显著的,而需求预测可以对冲请求取消带来的负面影响。实际应用结果表明,与实践状态相比,整体交付效率可以大幅提高,同时还能提高服务质量并节省车队规模。
{"title":"Prediction-failure-risk-aware online dial-a-ride scheduling considering spatial demand correlation via approximate dynamic programming and scenario approach","authors":"","doi":"10.1016/j.trc.2024.104801","DOIUrl":"10.1016/j.trc.2024.104801","url":null,"abstract":"<div><p>The dial-a-ride (DAR) service is a precursor to emerging shared mobility. Service providers expect efficient management of fleet resources to improve service quality without degrading economic viability. Most existing studies overlook possible future demands that could yield better matching opportunities and scheduling benefits, and therefore have short-sighted limitations. Moreover, the effects of correlated demand and potential prediction errors were ignored. To address these gaps, this paper investigates prediction-failure-risk-aware online DAR scheduling with spatial demand correlation. Request selection and cancellation are explicitly considered. We formulate the problem as a Markov decision process (MDP) and solve it by approximate dynamic programming (ADP). We further develop a demand prediction model that can capture the characteristics of DAR travel demand (uncertainty, sparsity, and spatial correlation). Deep quantile regression is adopted to estimate the marginal distribution of each OD pair. These marginals are combined into a joint demand distribution by constructing a Gaussian Copula to capture the spatial demand correlation. A prediction error correction mechanism is proposed to eliminate prediction errors and rectify policies promptly. Based on the model properties, several families of customized pruning strategies are devised to improve the computational efficiency and solution quality of ADP. We solve policies over time in the dynamic environment mixed with actual and stochastic future demands via the ADP algorithm and scenario approach. We propose the value function rolling method and multi-scenario exploration method, to address the deviation of the value function and identify the optimal policy from multiple future demand scenarios. Numerical results demonstrate the importance and benefits of incorporating demand forecasting and spatial correlation into the DAR operation. The improvement due to prediction is significant even when the prediction is imperfect, while the demand prediction can hedge against the negative effects of request cancellation. The real-world application result shows that compared to state-of-the-practice, the overall delivery efficiency can be substantially improved, along with better service quality and fleet size savings.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142173200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-09-12DOI: 10.1016/j.trc.2024.104843
This paper proposes a novel algorithmic framework to enhance the convergence efficiency of the alternating direction method of multipliers (ADMM) by incorporating the successive over relaxation (SOR) splitting method. The proposed framework holds applicability across various research fields for improving convergence efficiency. Currently, there exist two main methods for decomposing the separate optimization problems: Gauss-Seidel (GS) and Jacobi methods. The SOR method introduced in this paper offers a more efficient alternative. Following the original ADMM algorithm’s framework, we provide a detailed procedure for incorporating the SOR method into the ADMM framework in place of the GS splitting method. This development gives rise to a new method called ADMM-SOR, and then we apply this newly proposed algorithm to solve the deterministic user equilibrium (DUE) problem. Subsequently, to ensure the reliability of the proposed algorithm, we rigorously prove its convergence by leveraging some properties of variational inequalities. Additionally, the impact of the relaxation factor on the efficiency of the ADMM-SOR method is conducted, and we also explore a novel method to self-adjust the relaxation factor during each iteration. The new algorithm is verified based on numerical experiments, revealing that the novel ADMM-SOR framework achieves faster convergence in comparison to the original one, all the while maintaining exceptional parallel performance.
本文提出了一种新颖的算法框架,通过结合连续过度松弛(SOR)分割法来提高交替方向乘法(ADMM)的收敛效率。所提出的框架适用于各个研究领域,以提高收敛效率。目前,有两种分解单独优化问题的主要方法:高斯-赛德尔法(GS)和雅可比法。本文介绍的 SOR 方法提供了一种更有效的替代方法。按照原始 ADMM 算法的框架,我们提供了将 SOR 方法纳入 ADMM 框架以取代 GS 分割方法的详细步骤。这一发展产生了一种名为 ADMM-SOR 的新方法,然后我们将这一新提出的算法用于解决确定性用户均衡(DUE)问题。随后,为了确保所提算法的可靠性,我们利用变分不等式的一些特性严格证明了该算法的收敛性。此外,我们还研究了松弛因子对 ADMM-SOR 方法效率的影响,并探索了一种在每次迭代中自我调整松弛因子的新方法。基于数值实验对新算法进行了验证,结果表明,与原始算法相比,新的 ADMM-SOR 框架收敛速度更快,同时保持了卓越的并行性能。
{"title":"A novel framework of the alternating direction method of multipliers with application to traffic assignment problem","authors":"","doi":"10.1016/j.trc.2024.104843","DOIUrl":"10.1016/j.trc.2024.104843","url":null,"abstract":"<div><p>This paper proposes a novel algorithmic framework to enhance the convergence efficiency of the alternating direction method of multipliers (ADMM) by incorporating the successive over relaxation (SOR) splitting method. The proposed framework holds applicability across various research fields for improving convergence efficiency. Currently, there exist two main methods for decomposing the separate optimization problems: Gauss-Seidel (GS) and Jacobi methods. The SOR method introduced in this paper offers a more efficient alternative. Following the original ADMM algorithm’s framework, we provide a detailed procedure for incorporating the SOR method into the ADMM framework in place of the GS splitting method. This development gives rise to a new method called ADMM-SOR, and then we apply this newly proposed algorithm to solve the deterministic user equilibrium (DUE) problem. Subsequently, to ensure the reliability of the proposed algorithm, we rigorously prove its convergence by leveraging some properties of variational inequalities. Additionally, the impact of the relaxation factor on the efficiency of the ADMM-SOR method is conducted, and we also explore a novel method to self-adjust the relaxation factor during each iteration. The new algorithm is verified based on numerical experiments, revealing that the novel ADMM-SOR framework achieves faster convergence in comparison to the original one, all the while maintaining exceptional parallel performance.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142167835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-09-11DOI: 10.1016/j.trc.2024.104831
The real-time crash likelihood prediction model is an essential component of the proactive traffic safety management system. Over the years, numerous studies have attempted to construct a crash likelihood prediction model in order to enhance traffic safety, but mostly on freeways. In the majority of the existing studies, researchers have primarily used a deep learning-based framework to identify crash potential. Lately, Transformers have emerged as a potential deep neural network that fundamentally operates through attention-based mechanisms. Transformers exhibit distinct functional benefits over established deep learning models like Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTMs), and Convolutional Neural Networks (CNNs). First, they employ attention mechanisms to accurately weigh the significance of different parts of input data, a dynamic functionality that is not available in RNNs, LSTMs, and CNNs. Second, they are well-equipped to handle dependencies over long-range data sequences, a feat RNNs typically struggle with. Lastly, unlike RNNs, LSTMs, and CNNs, which process data in sequence, Transformers can parallelly process data elements during training and inference, thereby enhancing their efficiency. Apprehending the immense possibility of Transformers, this paper proposes inTersection-Transformer (inTformer), a time-embedded attention-based Transformer model that can effectively predict intersection crash likelihood in real-time. The inTformer is basically a binary prediction model that predicts the occurrence or non-occurrence of crashes at intersections in the near future (i.e., next 15 min). The proposed model was developed by employing traffic data extracted from connected vehicles. Acknowledging the complex traffic operation mechanism at intersection, this study developed zone-specific models by dividing the intersection region into two distinct zones: within-intersection and approach zones, each representing the intricate flow of traffic unique to the type of intersection (i.e., three-legged and four-legged intersections). In the ‘within-intersection’ zone, the inTformer models attained a sensitivity of up to 73%, while in the ‘approach’ zone, the sensitivity peaked at 74%. Moreover, benchmarking the optimal zone-specific inTformer models against earlier studies on crash likelihood prediction at intersections and several established deep learning models trained on the same connected vehicle dataset confirmed the superiority of the proposed inTformer. Further, to quantify the impact of features on crash likelihood at intersections, the SHAP (SHapley Additive exPlanations) method was applied on the best performing inTformer models. The most critical predictors were average and maximum approach speeds, average and maximum control delays, average and maximum travel times, split failure percentage and count, and percent arrival on green.
{"title":"A time-embedded attention-based transformer for crash likelihood prediction at intersections using connected vehicle data","authors":"","doi":"10.1016/j.trc.2024.104831","DOIUrl":"10.1016/j.trc.2024.104831","url":null,"abstract":"<div><p>The real-time crash likelihood prediction model is an essential component of the proactive traffic safety management system. Over the years, numerous studies have attempted to construct a crash likelihood prediction model in order to enhance traffic safety, but mostly on freeways. In the majority of the existing studies, researchers have primarily used a deep learning-based framework to identify crash potential. Lately, Transformers have emerged as a potential deep neural network that fundamentally operates through attention-based mechanisms. Transformers exhibit distinct functional benefits over established deep learning models like Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTMs), and Convolutional Neural Networks (CNNs). First, they employ attention mechanisms to accurately weigh the significance of different parts of input data, a dynamic functionality that is not available in RNNs, LSTMs, and CNNs. Second, they are well-equipped to handle dependencies over long-range data sequences, a feat RNNs typically struggle with. Lastly, unlike RNNs, LSTMs, and CNNs, which process data in sequence, Transformers can parallelly process data elements during training and inference, thereby enhancing their efficiency. Apprehending the immense possibility of Transformers, this paper proposes inTersection-Transformer (inTformer), a time-embedded attention-based Transformer model that can effectively predict intersection crash likelihood in real-time. The inTformer is basically a binary prediction model that predicts the occurrence or non-occurrence of crashes at intersections in the near future (i.e., next 15 min). The proposed model was developed by employing traffic data extracted from connected vehicles. Acknowledging the complex traffic operation mechanism at intersection, this study developed zone-specific models by dividing the intersection region into two distinct zones: within-intersection and approach zones, each representing the intricate flow of traffic unique to the type of intersection (i.e., three-legged and four-legged intersections). In the ‘within-intersection’ zone, the inTformer models attained a sensitivity of up to 73%, while in the ‘approach’ zone, the sensitivity peaked at 74%. Moreover, benchmarking the optimal zone-specific inTformer models against earlier studies on crash likelihood prediction at intersections and several established deep learning models trained on the same connected vehicle dataset confirmed the superiority of the proposed inTformer. Further, to quantify the impact of features on crash likelihood at intersections, the SHAP (SHapley Additive exPlanations) method was applied on the best performing inTformer models. The most critical predictors were average and maximum approach speeds, average and maximum control delays, average and maximum travel times, split failure percentage and count, and percent arrival on green.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142167838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2024-09-10DOI: 10.1016/j.trc.2024.104834
High demand, rising customer expectations, and government regulations are forcing companies to increase the efficiency and sustainability of urban (last-mile) distribution. Consequently, several new delivery concepts have been proposed that increase flexibility for customers and other stakeholders. One of these innovations is crowdsourced delivery, where deliveries are made by occasional drivers who wish to utilize their surplus resources (unused transport capacity) by making deliveries in exchange for some compensation. The potential benefits of crowdsourced delivery include reduced delivery costs and increased flexibility (by scaling delivery capacity up and down as needed). The use of occasional drivers poses new challenges because (unlike traditional couriers) neither their availability nor their behavior in accepting delivery offers is certain. The relationship between the compensation offered to occasional drivers and the probability that they will accept a task has been largely neglected in the scientific literature. Therefore, we consider a setting in which compensation-dependent acceptance probabilities are explicitly considered in the process of assigning delivery tasks to occasional drivers. We propose a mixed-integer nonlinear model that minimizes the expected delivery costs while identifying optimal assignments of tasks to a mix of professional and occasional drivers and their compensation. We propose an exact two-stage solution algorithm that allows to decompose compensation and assignment decisions for generic acceptance probability functions and show that the runtime of this algorithm is polynomial under mild conditions. Finally, we also study a more general case of the considered problem setting, show that it is NP-hard and propose an approximate linearization scheme of our mixed-integer nonlinear model. The results of our computational study show clear advantages of our new approach over existing ones. They also indicate that these advantages remain in dynamic settings when tasks and drivers are revealed over time and in which case our method constitutes a fast, yet powerful heuristic.
{"title":"The role of individual compensation and acceptance decisions in crowdsourced delivery","authors":"","doi":"10.1016/j.trc.2024.104834","DOIUrl":"10.1016/j.trc.2024.104834","url":null,"abstract":"<div><p>High demand, rising customer expectations, and government regulations are forcing companies to increase the efficiency and sustainability of urban (last-mile) distribution. Consequently, several new delivery concepts have been proposed that increase flexibility for customers and other stakeholders. One of these innovations is crowdsourced delivery, where deliveries are made by occasional drivers who wish to utilize their surplus resources (unused transport capacity) by making deliveries in exchange for some compensation. The potential benefits of crowdsourced delivery include reduced delivery costs and increased flexibility (by scaling delivery capacity up and down as needed). The use of occasional drivers poses new challenges because (unlike traditional couriers) neither their availability nor their behavior in accepting delivery offers is certain. The relationship between the compensation offered to occasional drivers and the probability that they will accept a task has been largely neglected in the scientific literature. Therefore, we consider a setting in which compensation-dependent acceptance probabilities are explicitly considered in the process of assigning delivery tasks to occasional drivers. We propose a mixed-integer nonlinear model that minimizes the expected delivery costs while identifying optimal assignments of tasks to a mix of professional and occasional drivers and their compensation. We propose an exact two-stage solution algorithm that allows to decompose compensation and assignment decisions for generic acceptance probability functions and show that the runtime of this algorithm is polynomial under mild conditions. Finally, we also study a more general case of the considered problem setting, show that it is NP-hard and propose an approximate linearization scheme of our mixed-integer nonlinear model. The results of our computational study show clear advantages of our new approach over existing ones. They also indicate that these advantages remain in dynamic settings when tasks and drivers are revealed over time and in which case our method constitutes a fast, yet powerful heuristic.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0968090X24003553/pdfft?md5=a3cf9eb6d9094ae5aa67e8b3ad1ac966&pid=1-s2.0-S0968090X24003553-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-09DOI: 10.1016/j.trc.2024.104830
Population synthesis involves generating synthetic yet realistic representations of a target population of micro-agents for behavioral modeling and simulation. Traditional methods, often reliant on target population samples, such as census data or travel surveys, face limitations due to high costs and small sample sizes, particularly at smaller geographical scales. We propose a novel framework based on copulas to generate synthetic data for target populations where only empirical marginal distributions are known. This method utilizes samples from different populations with similar marginal dependencies, introduces a spatial component into population synthesis, and considers various information sources for more realistic generators. Concretely, the process involves normalizing the data and treating it as realizations of a given copula, and then training a generative model before incorporating the information on the marginals of the target population. Utilizing American Community Survey data, we assess our framework’s performance through standardized root mean squared error (SRMSE) and so-called sampled zeros. We focus on its capacity to transfer a model learned from one population to another. Our experiments include transfer tests between regions at the same geographical level as well as to lower geographical levels, hence evaluating the framework’s adaptability in varied spatial contexts. We compare Bayesian Networks, Variational Autoencoders, and Generative Adversarial Networks, both individually and combined with our copula framework. Results show that the copula enhances machine learning methods in matching the marginals of the reference data. Furthermore, it consistently surpasses Iterative Proportional Fitting in terms of SRMSE in the transferability experiments, while introducing unique observations not found in the original training sample.
{"title":"Copula-based transferable models for synthetic population generation","authors":"","doi":"10.1016/j.trc.2024.104830","DOIUrl":"10.1016/j.trc.2024.104830","url":null,"abstract":"<div><p>Population synthesis involves generating synthetic yet realistic representations of a target population of micro-agents for behavioral modeling and simulation. Traditional methods, often reliant on target population samples, such as census data or travel surveys, face limitations due to high costs and small sample sizes, particularly at smaller geographical scales. We propose a novel framework based on copulas to generate synthetic data for target populations where only empirical marginal distributions are known. This method utilizes samples from different populations with similar marginal dependencies, introduces a spatial component into population synthesis, and considers various information sources for more realistic generators. Concretely, the process involves normalizing the data and treating it as realizations of a given copula, and then training a generative model before incorporating the information on the marginals of the target population. Utilizing American Community Survey data, we assess our framework’s performance through standardized root mean squared error (SRMSE) and so-called sampled zeros. We focus on its capacity to transfer a model learned from one population to another. Our experiments include transfer tests between regions at the same geographical level as well as to lower geographical levels, hence evaluating the framework’s adaptability in varied spatial contexts. We compare Bayesian Networks, Variational Autoencoders, and Generative Adversarial Networks, both individually and combined with our copula framework. Results show that the copula enhances machine learning methods in matching the marginals of the reference data. Furthermore, it consistently surpasses Iterative Proportional Fitting in terms of SRMSE in the transferability experiments, while introducing unique observations not found in the original training sample.</p></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":7.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}