Transportation Research Part E-Logistics and Transportation Review最新文献

{"title":"Enhancing feeder bus service coverage with Multi-Agent Reinforcement Learning: A case study in Hong Kong","authors":"Yang Su,&nbsp;Hai Yang","doi":"10.1016/j.tre.2025.103997","DOIUrl":"10.1016/j.tre.2025.103997","url":null,"abstract":"<div><div>Public transport is a vital component of modern urban mobility, playing a significant role in reducing congestion and promoting environmental sustainability. Feeder bus services are essential for connecting residents to major public transport hubs, such as metro or rail stations. In this paper, a novel framework that enhances service coverage of the feeder bus while maintaining network efficiency is proposed. The framework integrates Multi-Agent Reinforcement Learning (MARL) to simulate and optimize route designs and frequency settings. Additionally, we introduce a Cost-based Competitive Coverage (CCC) Model to evaluate the performance of the feeder bus services by considering competition with other public transport modes. A case study conducted in two new towns in Hong Kong demonstrates the effectiveness and robustness of the proposed framework, highlighting its adaptability and potential to improve public transport accessibility.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 103997"},"PeriodicalIF":8.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453139","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}

{"title":"A comprehensive assessment of connected and automated vehicle analytical, modeling, and simulation tools","authors":"Keke Long ,&nbsp;Ke Ma ,&nbsp;Qianwen Li ,&nbsp;Xiaopeng Li ,&nbsp;Zhitong Huang ,&nbsp;Rachel James ,&nbsp;Amir Ghiasi","doi":"10.1016/j.tre.2025.104007","DOIUrl":"10.1016/j.tre.2025.104007","url":null,"abstract":"<div><div>Connected and Automated Vehicles (CAVs) promise to redefine the future of transportation. Infrastructure Owners and Operators (IOOs require advanced analytical, modeling, and simulation (AMS) tools) to grasp the impact of CAVs on their strategic goals, such as improving safety, enhancing mobility, and advancing equity, and assess policy modifications to steer the deployment of this technology effectively. Although recent research has made strides in developing models that characterize CAV behavior in mixed-traffic scenarios, significant modeling gaps persist. These gaps hinder decision-makers and policymakers from fully understanding how CAVs can serve as an instrumental force in driving desired improvements in transportation system performance. This study aims to identify these gaps by organizing two stakeholder webinars that focus on CAV AMS tools. The discussions from these webinars are categorized into three primary areas: CAV technologies, road user behaviors, and system-level modeling. This categorization helps structure an in-depth literature review designed to pinpoint existing shortcomings in CAV research. The study also provides an overview of current datasets that are both representative and capable of addressing some of these research gaps. Ultimately, this study seeks to act as a valuable reference for directing future research efforts in CAVs.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104007"},"PeriodicalIF":8.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463858","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}

{"title":"Battery degradation mitigation-oriented strategy for optimizing e-hailing electric vehicle operations","authors":"Kaize Yu ,&nbsp;Pengyu Yan ,&nbsp;Yang Liu ,&nbsp;Zhibin Chen ,&nbsp;Xiang T.R. Kong","doi":"10.1016/j.tre.2025.104006","DOIUrl":"10.1016/j.tre.2025.104006","url":null,"abstract":"<div><div>Effective management of battery degradation is crucial for electric vehicles (EVs) due to the high costs associated with replacing EV batteries. In practice, uninformed charging behaviors of EV drivers can accelerate battery wear without proper guidance. To address this challenge, this paper introduces a battery degradation mitigation-oriented charging and order-serving problem for EVs operating on the e-hailing platform. The objective is to maximize the lifespan profit for individual EVs, which encompasses order service revenue, charging expenses, and battery degradation costs. To achieve this goal, a Markov decision process model is developed to capture the dynamics of individual e-hailing EV operations, and a battery degradation cost estimation method is specifically proposed for the e-hailing scenario. Moreover, we propose a multi-agent reinforcement learning (MARL) framework with a centralized training and decentralized execution paradigm. The MARL approach integrates a reward-shaping approach and an enhanced multi-agent upper confidence bound approach to determine the optimal charging and order-serving strategy for EVs. We propose a novel order assignment method to reduce the imbalanced degradation costs across EVs during the learning process. Our simulation experiments validate that the proposed strategy can substantially prolong EV battery life while concurrently boosting driver profits. Furthermore, an explanation of the strategy is provided to ensure transparency and understanding of the decision-making process.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104006"},"PeriodicalIF":8.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444438","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}

{"title":"Developing the value of legal judgments of supply chain finance for credit risk prediction through novel ACWGAN-GPSA approach","authors":"Weiqing Wang ,&nbsp;Yuxi Chen ,&nbsp;Liukai Wang ,&nbsp;Yu Xiong","doi":"10.1016/j.tre.2025.104020","DOIUrl":"10.1016/j.tre.2025.104020","url":null,"abstract":"<div><div>Predicting the credit risk for enterprises in Supply Chain Finance (SCF) often presents substantial challenges in supply chain management community. Considering the huge information asymmetry, we introduce the Bidirectional Encoder Representations from Transformers (BERT) technology in the fields of Deep Learning and Natural Language Processing (NLP) to extract textual insights from legal judgments related to enterprises in SCF business. By integrating legal judgments-extracted information with the financial and corporate attributes of these enterprises, we aim to enhance the prediction accuracy of credit risk. Our empirical results show that the amalgamation of multi-source information significantly reinforces the predictive accuracy of credit risk. Furthermore, we effectively identify critical predictive factors for credit risk, demonstrating the important role of legal judgment content in default prediction situations. Additionally, considering the issue of imbalanced data categories, we propose a novel imbalanced data processing technique called ACWGAN-GPSA to address the generation of unrealistic samples, thereby significantly improving the performance of credit risk prediction models for enterprises in SCF. The strategic insights obtained from our findings offer valuable guidance for both lenders and financial institutions.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104020"},"PeriodicalIF":8.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436935","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}

{"title":"A critical evaluation of non-profit organizations’ contributions to disaster management: Historical perspectives and future trends in operations management research","authors":"Zahra Hosseinifard ,&nbsp;Haerold Dean Layaoen ,&nbsp;Ahmad Abareshi ,&nbsp;Babak Abbasi ,&nbsp;Jiuh-Biing Sheu","doi":"10.1016/j.tre.2025.103989","DOIUrl":"10.1016/j.tre.2025.103989","url":null,"abstract":"<div><div>As global crises and disasters continue to intensify, the importance of non-profit organizations (NPOs) in ensuring efficient coordination and optimal use of resources is becoming more critical. This systematic literature review focuses on the essential roles that NPOs play in humanitarian efforts within disaster management contexts. Adhering to PRISMA guidelines, the review compiles insights from 847 articles published in ABS-ranked journals between 1982 and April 2024. From this extensive analysis, four distinct clusters were identified to assess significant research trends in the field. These trends encompass Disaster Resilience, Emergency Relief, Humanitarian Supply Chain Management, and Post-disaster Response. Subsequently, the roles of NPOs within these clusters are analyzed in relation to the four core humanitarian principles endorsed by the United Nations in General Assembly Resolutions 46/182 and 58/114: humanity, neutrality, impartiality, and independence. Despite the extensive body of literature on the role of NPOs in humanitarian operations, several research gaps have been identified: 1) Resource Overlap: NPOs frequently depend on shared resources (such as volunteers). Future studies should focus on developing strategies to improve coordination among NPOs to maximize the efficiency and effectiveness of resource utilization; 2) Response to Man-made Disasters: Given the rise in man-made crises, such as the Ukraine conflict and the Gaza war, it is essential to investigate how NPOs can play a more effective role in humanitarian operations under these conditions. Political biases and bilateral relationships often restrict government involvement, highlighting the critical need for NPOs to step in and provide essential support during such crises. 3) Alignment with Sustainable Development Goals (SDGs): future research should explore how the actions of NPOs in humanitarian operations align with and contribute to the SDGs. Such insights would help inform policymakers, practitioners, and scholars, promoting a more strategic approach to harnessing the capabilities of NPOs in humanitarian settings. Ultimately, this systematic review aims to serve as a valuable resource for expanding knowledge, guiding future research efforts, and improving the effectiveness of NPOs in humanitarian operations.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 103989"},"PeriodicalIF":8.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429893","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}

{"title":"Optimization of electric bus vehicle scheduling and charging strategies under Time-of-Use electricity price","authors":"Zhaoyang Lu ,&nbsp;Tianyi Xing ,&nbsp;Yanfeng Li","doi":"10.1016/j.tre.2025.104021","DOIUrl":"10.1016/j.tre.2025.104021","url":null,"abstract":"<div><div>With the growing awareness of environmental protection and energy conservation, more and more cities choose to utilize electric buses (EBs) in their public transit systems. Due to the limitations of battery technology, many fully charged EBs are not enough to complete their daily tasks, which must be charged twice or more times per day. Besides, many cities encourage the off-peak electricity power consumption, and the charging cost of EBs during peak hours is often extremely high. From an economic viewpoint, it is thus one practical and urgent problem on how to decide the fleet size of EBs and organize their charging schedules for the bus companies. To solve this problem, this manuscript builds a mixed-integer programming (MIP) model via taking the scheduling and charging constraints of EBs into consideration. Also, one dynamic label setting-based branch and price (DLS-BP) algorithm is proposed accordingly, whose efficiency is further verified and compared with two heuristic algorithms via some numerical experiments.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104021"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419292","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}

{"title":"A two-stage stochastic-robust model for supply chain network design problem under disruptions and endogenous demand uncertainty","authors":"Lan Luo,&nbsp;Xiangyong Li,&nbsp;Yuxuan Zhao","doi":"10.1016/j.tre.2025.104013","DOIUrl":"10.1016/j.tre.2025.104013","url":null,"abstract":"<div><div>A minor disruption can have a disastrous impact as it cascades through a supply chain. In addition, customer demand is uncertain and susceptible to disruption risks and supply chain management decisions, which in turn impacts how well supply chains function during disruptions. In this paper, we address these issues by studying a supply chain network design problem under disruptions and endogenous demand uncertainty. We first propose a two-stage stochastic-robust formulation where disruption risks are represented using a scenario-based approach and the demand is characterized by a box uncertainty set that depends on both facility-location decisions and disruptions. We then develop an adjusted column-and-constraint generation algorithm and conduct extensive evaluations to verify its effectiveness by comparing it with an affine decision rule method. Additionally, We perform out-of-sample tests to assess the effectiveness and robustness of our model compared to two stochastic programming models. Finally, we present managerial insights, examining how the key factors influence supply chain network performance under disruptions, providing practical guidance.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104013"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419289","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}

{"title":"Social, economic and green optimization of the distribution process of e-commerce platforms","authors":"Riccardo Tronconi,&nbsp;Francesco Pilati","doi":"10.1016/j.tre.2025.104004","DOIUrl":"10.1016/j.tre.2025.104004","url":null,"abstract":"<div><div>During the last ten years, online shopping has continuously increased while embedding growing sustainability concerns regarding environment and, especially, drivers working conditions. Therefore, this paper presents a multi-objective simulated annealing (MOSA) developed to deal with a goods distribution problem characterized by social, economic and green sustainability aspects. This contribution compares three scenarios. The first one is distinguished by diesel vehicles and it neglects the load inside them. The second scenario considers the variation of the vehicle load along its route. Finally, the third scenario employs electric vehicles instead of diesel ones. The developed MOSA is implemented in real-world instances and results show that the load-based scenario performs similar to the one which ignores it, but it is more realistic since just 30% of the route is traveled with no load inside. In addition, the load-based scenario is more reliable since the metabolic energy consumption of the drivers depends also on this feature. Regarding this social aspect, the proposed contribution shows that the solution of the Pareto frontier which optimizes this aspect provides routes more balanced among drivers in terms of metabolic energy consumption, considering the personal characteristic of each operator. Furthermore, this paper indicates that the electric vehicles are more efficient, economically and environmentally, than diesel ones just in small areas.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104004"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419291","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}

{"title":"Aircraft maintenance scheduling under uncertain task processing time","authors":"Matías Villafranca,&nbsp;Felipe Delgado,&nbsp;Mathias Klapp","doi":"10.1016/j.tre.2025.104012","DOIUrl":"10.1016/j.tre.2025.104012","url":null,"abstract":"<div><div>Unexpected delays while executing aircraft maintenance tasks can result in costly operational disruptions for airlines, including expensive flight delays and overtime. In this study, we address uncertainty in maintenance task processing times by designing a daily and cost-effective aircraft maintenance schedule using two-stage stochastic programming. In the first stage, we determine which daily maintenance tasks to outsource and which to complete with in-house technicians. Additionally, we schedule each task, outsourced or in-house, for its respective aircraft, specifying the start time and assigned maintenance base. In-house tasks are further assigned to a technician’s work sequence. In the second stage, the start time of each task and the departure time of each flight are adjusted based on a specific realization of task processing times. We aim to minimize the expected costs incurred for outsourced maintenance tasks, overtime, and flight delays. To solve our model, we design an <em>ad-hoc</em> Adaptive Iterated Local Search heuristic that explores first-stage solutions via an efficient evaluation of the second-stage cost. We also present a proof of concept by testing our approach in a set of computationally simulated instances. Our proposed methodology yields 74% and 34% average cost savings compared to a deterministic approach assuming expected task processing times and to a conservative solution planning ahead with maximum possible processing times for each task, respectively. Moreover, we obtain 14% average cost savings compared to a benchmark solution, which plans maintenance tasks with an optimized time buffer parameter between consecutive task assignments. Furthermore, we study the cost impact of varying structural parameters, such as task granularity, processing time variability, workload, and cost structure.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104012"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429986","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}

{"title":"Evolutionary game-based ship inspection planning considering ship competitive interactions","authors":"Hong Le ,&nbsp;Wang Ruihan ,&nbsp;Chen Hao ,&nbsp;Cui Weicheng ,&nbsp;Tsoulakos Nikolaos ,&nbsp;Yan Ran","doi":"10.1016/j.tre.2025.103994","DOIUrl":"10.1016/j.tre.2025.103994","url":null,"abstract":"<div><div>Port state control (PSC) inspection is the safety net to catch substandard ships and safeguard maritime transport. Effectively identifying high-risk foreign ships is crucial for port authorities to maximize inspection efficiency due to the scarce inspection resources. This paper proposes a data-driven evolutionary game theory-based ship inspection priority planning (EGT-SIPP) optimization approach to identify high-risk ships among the large group of visiting foreign ships while taking the ship competitive interaction into consideration. First, a data-driven evolutionary game theory (EGT) framework is adopted to assign stable and fair inspection priority coefficient to each visiting foreign ship to a port. This framework is built on real ship inspection records, ensuring that the inspection priority planning reflects both strategic interactions and real-world conditions. Then, the equilibrium optimizer (EO) algorithm is employed to solve the single-objective optimization problem, which minimizes the changes in the allocated priority coefficients based on replicator dynamics (RD) under the EGT framework. By leveraging inspection records from the Tokyo memorandum of understanding (MoU), the proposed EGT-SIPP is validated and compared with other ship selection schemes. Simulation results demonstrate that, subject to limited inspection resources at different levels, our EO-solved EGT-SIPP model can detect over 16.04%, 47.20%, and 125.27% more deficiencies on average than the particle swarm optimization (PSO)-solved EGT-SIPP model, the genetic algorithm (GA)-solved EGT-SIPP model, and the currently used ship risk profile (SRP) selection scheme, respectively.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 103994"},"PeriodicalIF":8.3,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419290","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}