Multimodal Transportation最新文献_第9页

Traffic flow theory-based modeling of bike-vehicle interactions for enhanced safety and mobility 基于交通流理论的自行车-车辆交互建模，提高安全性和机动性

Multimodal Transportation

Pub Date : 2025-01-23 DOI: 10.1016/j.multra.2025.100202

Mustafa Gadah , Xuesong Zhou , Mohammad Abbasi , Vamshi Yellisetty

This paper introduces an innovative approach to enhancing active transportation analysis and decision support by addressing the notable research gap of integrating traffic flow analysis, spatio-temporal trajectory models, and an input-output (moving queue) diagram. We establish a unique four-stage method for assessing bike-vehicle traffic interaction on designated road links: 1) Given the input of volume, we convert it to speed and density using the fundamental diagram and Q-K curves under different congestion conditions. 2) We analyze vehicle trajectories and utilize an input-output (moving queue) diagram to calculate the total exposures between bikes and vehicles as a function of speed difference and the product of bike and vehicle volume, ensuring the balance equations for both vehicle and bike exposure individually. 3) Beginning at the moment a vehicle enters a shared facility, we apply an illustrative method to determine the duration of individual exposure time, adjusting Newell’s car-following model to accommodate for various phases of driver reactions, transitioning from anticipation to overtaking/yield phase. 4) We measure the overall impact of exposure on mobility and safety using a multimodal semi-dynamic traffic assignment that focuses on both delay and exposure-based utility across various facility types and development scenarios. Our research underscores that controlling the flow of bikes and vehicles is a pivotal factor in determining the relative bike exposure to risk, offering valuable insights for the future development of transportation models and safety improvement strategies using a case study from Gilbert, AZ.

本文通过整合交通流分析、时空轨迹模型和投入-产出（移动队列）图，提出了一种创新的方法来增强主动交通分析和决策支持。我们建立了一种独特的四阶段方法来评估指定路段的自行车-车辆交通互动：1)给定输入量，利用基本图和不同拥堵条件下的Q-K曲线将其转换为速度和密度。2)分析车辆轨迹，利用输入-输出（移动队列）图计算自行车和车辆之间的总暴露作为速度差和自行车与车辆体积乘积的函数，确保车辆和自行车暴露的平衡方程。3)从车辆进入共享设施的那一刻开始，我们应用说说性方法确定个体暴露时间的持续时间，调整Newell的汽车跟随模型以适应驾驶员反应的各个阶段，从预期过渡到超车/退让阶段。4)我们使用多模式半动态交通分配来衡量暴露对移动性和安全性的总体影响，该分配侧重于各种设施类型和开发方案中基于延迟和暴露的效用。我们的研究强调，控制自行车和车辆的流动是决定自行车相对暴露于风险的关键因素，通过对亚利桑那州吉尔伯特的案例研究，为未来交通模式的发展和安全改进策略提供了有价值的见解。

{"title":"Traffic flow theory-based modeling of bike-vehicle interactions for enhanced safety and mobility","authors":"Mustafa Gadah , Xuesong Zhou , Mohammad Abbasi , Vamshi Yellisetty","doi":"10.1016/j.multra.2025.100202","DOIUrl":"10.1016/j.multra.2025.100202","url":null,"abstract":"<div><div>This paper introduces an innovative approach to enhancing active transportation analysis and decision support by addressing the notable research gap of integrating traffic flow analysis, spatio-temporal trajectory models, and an input-output (moving queue) diagram. We establish a unique four-stage method for assessing bike-vehicle traffic interaction on designated road links: 1) Given the input of volume, we convert it to speed and density using the fundamental diagram and Q-K curves under different congestion conditions. 2) We analyze vehicle trajectories and utilize an input-output (moving queue) diagram to calculate the total exposures between bikes and vehicles as a function of speed difference and the product of bike and vehicle volume, ensuring the balance equations for both vehicle and bike exposure individually. 3) Beginning at the moment a vehicle enters a shared facility, we apply an illustrative method to determine the duration of individual exposure time, adjusting Newell’s car-following model to accommodate for various phases of driver reactions, transitioning from anticipation to overtaking/yield phase. 4) We measure the overall impact of exposure on mobility and safety using a multimodal semi-dynamic traffic assignment that focuses on both delay and exposure-based utility across various facility types and development scenarios. Our research underscores that controlling the flow of bikes and vehicles is a pivotal factor in determining the relative bike exposure to risk, offering valuable insights for the future development of transportation models and safety improvement strategies using a case study from Gilbert, AZ.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 2","pages":"Article 100202"},"PeriodicalIF":0.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of COVID-19 pandemic on freight volume, revenue and expenditure of deendayal port in India: An ARIMA forecasting model COVID-19大流行对印度独立港口货运量、收入和支出的影响：ARIMA预测模型

Multimodal Transportation

Pub Date : 2025-01-18 DOI: 10.1016/j.multra.2025.100201

Deepjyoti Das , Aditya Saxena

Shipping sector is vital to Indian economy, making it crucial to understand the economic impact of the COVID-19 pandemic on port operations to develop strategies for future resilience. This study examines the effects of COVID-19 on Deendayal Port, a key Indian port, by analyzing freight volume, revenue, and expenditure data from April 2012 to October 2022. Autoregressive Integrated Moving Average (ARIMA) modeling covers pre-COVID, two COVID-19 waves, and post-COVID scenarios. Ordinary Least Squares (OLS) regression models for revenue and expenditure evaluate economic losses. The results show 6.2% decline in freight volume during the first wave, with a decrease from 123.4 million tons (Mt) to 115.8 Mt, leading to a monthly average loss of 0.6 Mt. The second wave saw recovery, with freight volume increasing from the forecasted 127.6 Mt to 129.6 Mt, resulting in a monthly gain of 0.2 Mt. Revenue losses during wave 1 were 215 crore INR, while wave 2 saw a revenue increase of 57 crore INR. The study highlights the importance of operational efficiency and managing key cost drivers like volume and manpower to maintain financial stability. These findings lay a foundation for future research to strengthen the shipping industry's resilience and sustainability in post-pandemic world.

航运业对印度经济至关重要，因此了解2019冠状病毒病大流行对港口运营的经济影响，以制定未来抵御能力战略至关重要。本研究通过分析2012年4月至2022年10月的货运量、收入和支出数据，考察了2019冠状病毒病对印度主要港口迪恩达亚尔港的影响。自回归综合移动平均（ARIMA）模型涵盖了COVID-19前、两个COVID-19波和COVID-19后的情景。普通最小二乘（OLS）回归模型的收入和支出评估经济损失。结果显示，第一波货运量下降6.2%，从1.234亿吨减少到1.158亿吨，导致每月平均损失0.6亿吨。第二波出现复苏，货运量从预测的1.276亿吨增加到1.296亿吨，导致每月增加0.2亿吨。第1波的收入损失为2.15亿卢比，而第2波的收入增加了5.7亿卢比。该研究强调了运营效率和管理数量和人力等关键成本驱动因素对维持金融稳定的重要性。这些发现为未来的研究奠定了基础，以加强航运业在大流行后世界的复原力和可持续性。

{"title":"Effect of COVID-19 pandemic on freight volume, revenue and expenditure of deendayal port in India: An ARIMA forecasting model","authors":"Deepjyoti Das , Aditya Saxena","doi":"10.1016/j.multra.2025.100201","DOIUrl":"10.1016/j.multra.2025.100201","url":null,"abstract":"<div><div>Shipping sector is vital to Indian economy, making it crucial to understand the economic impact of the COVID-19 pandemic on port operations to develop strategies for future resilience. This study examines the effects of COVID-19 on Deendayal Port, a key Indian port, by analyzing freight volume, revenue, and expenditure data from April 2012 to October 2022. Autoregressive Integrated Moving Average (ARIMA) modeling covers pre-COVID, two COVID-19 waves, and post-COVID scenarios. Ordinary Least Squares (OLS) regression models for revenue and expenditure evaluate economic losses. The results show 6.2% decline in freight volume during the first wave, with a decrease from 123.4 million tons (Mt) to 115.8 Mt, leading to a monthly average loss of 0.6 Mt. The second wave saw recovery, with freight volume increasing from the forecasted 127.6 Mt to 129.6 Mt, resulting in a monthly gain of 0.2 Mt. Revenue losses during wave 1 were 215 crore INR, while wave 2 saw a revenue increase of 57 crore INR. The study highlights the importance of operational efficiency and managing key cost drivers like volume and manpower to maintain financial stability. These findings lay a foundation for future research to strengthen the shipping industry's resilience and sustainability in post-pandemic world.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 2","pages":"Article 100201"},"PeriodicalIF":0.0,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143099536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling the adoption of urban air mobility based on technology acceptance and risk perception theories: A case study on flying cars 基于技术接受和风险感知理论的城市空中交通采用建模——以飞行汽车为例

Multimodal Transportation

Pub Date : 2025-01-17 DOI: 10.1016/j.multra.2025.100200

Sangen Hu , Zikang Huang , Ke Wang , Haiyuan Lin , Mingyang Pei

Flying cars, a symbol of Urban Air Mobility (UAM), signify a pivotal step in revolutionizing urban transportation and play a pivotal role in shaping future transport systems. To enhance travelers' willingness to accept flying cars and promote the widespread adoption of this novel transportation mode, this study develops a comprehensive model to explore key factors determining the public's acceptance of flying cars by integrating the Technology Acceptance Model, Risk Perception Theory, and Trust Theory. The validity of the model was confirmed through a rigorous structure equation modeling analysis, utilizing 553 sample data collected from a network questionnaire survey across a diverse demographic of the Chinese market. Results revealed significant associations between the intention to use flying cars and various factors, including attitudes towards usage, perceived usefulness, and personal innovativeness. Heterogeneity analysis further uncovered how demographic factors (such as age, gender, education, and possession of a driver's license) impacted perceptions and acceptance. As the study concludes, despite general optimism, public acceptance of flying cars is strongly influenced by factors such as cost, safety, and privacy concerns play crucial roles in public acceptance. The insights from this study provide valuable implications for manufacturers, policymakers, and marketers in strategizing the introduction and promotion of flying cars.

飞行汽车是城市空中交通（UAM）的象征，标志着城市交通革命的关键一步，在塑造未来的交通系统中发挥着关键作用。为了提高旅行者对飞行汽车的接受意愿，促进这种新型交通方式的广泛采用，本研究通过整合技术接受模型、风险感知理论和信任理论，建立了一个综合模型，探讨公众对飞行汽车接受程度的关键因素。通过严格的结构方程建模分析，利用从中国市场不同人口统计的网络问卷调查中收集的553个样本数据，证实了模型的有效性。结果显示，使用飞行汽车的意愿与各种因素之间存在显著关联，包括对使用的态度、感知到的有用性和个人创新能力。异质性分析进一步揭示了人口因素（如年龄、性别、教育程度和持有驾照）如何影响人们的认知和接受度。正如研究得出的结论，尽管普遍乐观，但公众对飞行汽车的接受程度受到成本、安全和隐私等因素的强烈影响，这些因素在公众接受度中起着至关重要的作用。这项研究的见解为制造商、政策制定者和营销人员制定引入和推广飞行汽车的战略提供了有价值的启示。

{"title":"Modeling the adoption of urban air mobility based on technology acceptance and risk perception theories: A case study on flying cars","authors":"Sangen Hu , Zikang Huang , Ke Wang , Haiyuan Lin , Mingyang Pei","doi":"10.1016/j.multra.2025.100200","DOIUrl":"10.1016/j.multra.2025.100200","url":null,"abstract":"<div><div>Flying cars, a symbol of Urban Air Mobility (UAM), signify a pivotal step in revolutionizing urban transportation and play a pivotal role in shaping future transport systems. To enhance travelers' willingness to accept flying cars and promote the widespread adoption of this novel transportation mode, this study develops a comprehensive model to explore key factors determining the public's acceptance of flying cars by integrating the Technology Acceptance Model, Risk Perception Theory, and Trust Theory. The validity of the model was confirmed through a rigorous structure equation modeling analysis, utilizing 553 sample data collected from a network questionnaire survey across a diverse demographic of the Chinese market. Results revealed significant associations between the intention to use flying cars and various factors, including attitudes towards usage, perceived usefulness, and personal innovativeness. Heterogeneity analysis further uncovered how demographic factors (such as age, gender, education, and possession of a driver's license) impacted perceptions and acceptance. As the study concludes, despite general optimism, public acceptance of flying cars is strongly influenced by factors such as cost, safety, and privacy concerns play crucial roles in public acceptance. The insights from this study provide valuable implications for manufacturers, policymakers, and marketers in strategizing the introduction and promotion of flying cars.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 2","pages":"Article 100200"},"PeriodicalIF":0.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143099537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mind the perception gap: Identifying differences in views among stakeholder groups of shared mobility services through bayesian best-worst method 注意感知差距：通过贝叶斯最佳-最差方法识别共享移动服务的利益相关者群体之间的观点差异

Multimodal Transportation

Pub Date : 2025-01-15 DOI: 10.1016/j.multra.2025.100198

Ehsan Amirnazmiafshar , Marco Diana

This study investigates perception gaps among stakeholders—policy-makers, operators, users, and non-users—regarding car-sharing, bike-sharing, and scooter-sharing systems in Turin, Italy. Based on 628 surveys collected between November 2021 and February 2022 and analyzed using the Bayesian Best-Worst Method (BWM) multicriteria technique, it highlights key differences in prioritizing factors influencing shared mobility demand.

Key Findings: For car-sharing, policy-makers overestimate the importance of trip purpose compared to both users and non-users, while undervaluing service availability. Operators undervalue trip-related factors, such as travel time and departure time, while overemphasizing user-friendliness. For bike-sharing, policy-makers overestimate travel time compared to users while undervaluing travel comfort and environmental friendliness compared to both users and non-users. Operators underestimate trip-related factors, including travel distance and trip purpose, while overemphasizing environmental friendliness, particularly compared to non-users. For scooter-sharing, policy-makers underestimate trip-related characteristics, such as travel time and departure time, while overestimating travel cost and user-friendliness compared to non-users. Operators undervalue travel comfort and service availability, while overestimating travel distance, especially compared to users.

Managerial Insights: For car-sharing, policy-makers should expand service coverage and incentivize vehicle deployment, while operators should use dynamic fleet management and offer flexible booking options. For bike-sharing, policy-makers should subsidize fleet expansion and improve infrastructure, while operators should transition to free-floating models and integrate navigation tools. For scooter-sharing, policy-makers should enforce safety standards and improve accessibility, while operators should invest in high-quality scooters and adopt competitive pricing models.

Bridging these perception gaps is essential for fostering shared mobility adoption and enhancing user satisfaction.

本研究调查了意大利都灵的利益相关者（政策制定者、运营商、用户和非用户）对汽车共享、自行车共享和踏板车共享系统的认知差距。基于2021年11月至2022年2月期间收集的628项调查，并使用贝叶斯最佳最差方法（BWM）多标准技术进行分析，该研究突出了影响共享出行需求的因素优先级的关键差异。主要发现：对于汽车共享，政策制定者高估了出行目的对用户和非用户的重要性，而低估了服务的可用性。运营商低估了与旅行相关的因素，如旅行时间和出发时间，而过分强调用户友好性。对于共享单车，决策者高估了用户的出行时间，而低估了用户和非用户的出行舒适度和环保性。运营商低估了旅行相关的因素，包括旅行距离和旅行目的，而过度强调环境友好性，特别是与非用户相比。对于滑板车共享，政策制定者低估了出行相关的特征，如出行时间和出发时间，同时高估了出行成本和与非用户相比的用户友好性。运营商低估了旅行的舒适性和服务的可用性，而高估了旅行距离，尤其是与用户相比。管理见解：对于汽车共享，政策制定者应该扩大服务范围，激励车辆部署，而运营商应该采用动态车队管理，并提供灵活的预订选择。对于共享单车，政策制定者应该补贴车队扩张和改善基础设施，而运营商应该过渡到自由浮动模式，并整合导航工具。对于共享滑板车，政策制定者应该加强安全标准，提高可达性，而运营商应该投资于高质量的滑板车，并采用有竞争力的定价模式。弥合这些认知差距对于促进共享出行普及和提高用户满意度至关重要。

{"title":"Mind the perception gap: Identifying differences in views among stakeholder groups of shared mobility services through bayesian best-worst method","authors":"Ehsan Amirnazmiafshar , Marco Diana","doi":"10.1016/j.multra.2025.100198","DOIUrl":"10.1016/j.multra.2025.100198","url":null,"abstract":"<div><div>This study investigates perception gaps among stakeholders—policy-makers, operators, users, and non-users—regarding car-sharing, bike-sharing, and scooter-sharing systems in Turin, Italy. Based on 628 surveys collected between November 2021 and February 2022 and analyzed using the Bayesian Best-Worst Method (BWM) multicriteria technique, it highlights key differences in prioritizing factors influencing shared mobility demand.</div><div>Key Findings: For car-sharing, policy-makers overestimate the importance of trip purpose compared to both users and non-users, while undervaluing service availability. Operators undervalue trip-related factors, such as travel time and departure time, while overemphasizing user-friendliness. For bike-sharing, policy-makers overestimate travel time compared to users while undervaluing travel comfort and environmental friendliness compared to both users and non-users. Operators underestimate trip-related factors, including travel distance and trip purpose, while overemphasizing environmental friendliness, particularly compared to non-users. For scooter-sharing, policy-makers underestimate trip-related characteristics, such as travel time and departure time, while overestimating travel cost and user-friendliness compared to non-users. Operators undervalue travel comfort and service availability, while overestimating travel distance, especially compared to users.</div><div>Managerial Insights: For car-sharing, policy-makers should expand service coverage and incentivize vehicle deployment, while operators should use dynamic fleet management and offer flexible booking options. For bike-sharing, policy-makers should subsidize fleet expansion and improve infrastructure, while operators should transition to free-floating models and integrate navigation tools. For scooter-sharing, policy-makers should enforce safety standards and improve accessibility, while operators should invest in high-quality scooters and adopt competitive pricing models.</div><div>Bridging these perception gaps is essential for fostering shared mobility adoption and enhancing user satisfaction.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 2","pages":"Article 100198"},"PeriodicalIF":0.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143099538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of motorcyclists crash severity using cluster correspondence and hierarchical binary logit models 基于聚类对应和层次二元logit模型的摩托车碰撞严重程度分析

Multimodal Transportation

Pub Date : 2025-01-10 DOI: 10.1016/j.multra.2025.100197

Richard Dzinyela , Bahar Dadashova , Grant Westfall , Subasish Das , Chiara Silvestri-Dobrovolny , Emmanuel Kofi Adanu , Dominique Lord

Crashes involving motorcyclists account for a significant portion of traffic-related injuries and fatalities. Despite motorcycles making only three percent of all registered vehicles, motorcyclists account for 14 percent of all roadway fatalities. As the number of motorcyclists increase, there is an urgent need to understand the factors that affect the severity of injuries they sustain in crashes. In this paper, we use cluster correspondence analysis (CCA) and hierarchical binary logit model to explore the factors associated with motorcyclists’ crash injury severities in Utah between 2016 and 2020. Cluster correspondence analysis was used to cluster the crash data into seven groups, while hierarchical binary logit model was used to identify the significant factors that contributed to the injury severity of motorcycle crashes. The results of this study indicate that among the crash-contributing factors the motorcyclist age, roadway alignment, roadside safety systems and temporal factors significantly contribute to motorcyclist crash severities. The model results further account for the correlation of variables within the clusters in the crash data. With the deeper understanding of the relationship between crash factors and injury severity in this study, the findings can help decision makers to implement targeted countermeasures to improve motorcyclist safety.

涉及摩托车手的撞车事故占交通相关伤亡事故的很大一部分。尽管摩托车只占所有登记车辆的3%，但摩托车手占所有道路死亡人数的14%。随着摩托车手人数的增加，迫切需要了解影响他们在碰撞中受伤严重程度的因素。本文采用聚类对应分析（CCA）和层次二元logit模型对2016 - 2020年犹他州摩托车手碰撞损伤严重程度的影响因素进行了研究。采用聚类对应分析方法将碰撞数据聚类为7类，并采用层次二元logit模型识别影响摩托车碰撞伤害严重程度的显著因素。研究结果表明，摩托车手年龄、道路线形、道路安全系统和时间因素对摩托车手碰撞严重程度有显著影响。模型结果进一步解释了碰撞数据中集群内变量的相关性。随着本研究中碰撞因素与伤害严重程度之间关系的深入了解，研究结果可以帮助决策者实施有针对性的对策，以提高摩托车驾驶员的安全水平。

{"title":"Analysis of motorcyclists crash severity using cluster correspondence and hierarchical binary logit models","authors":"Richard Dzinyela , Bahar Dadashova , Grant Westfall , Subasish Das , Chiara Silvestri-Dobrovolny , Emmanuel Kofi Adanu , Dominique Lord","doi":"10.1016/j.multra.2025.100197","DOIUrl":"10.1016/j.multra.2025.100197","url":null,"abstract":"<div><div>Crashes involving motorcyclists account for a significant portion of traffic-related injuries and fatalities. Despite motorcycles making only three percent of all registered vehicles, motorcyclists account for 14 percent of all roadway fatalities. As the number of motorcyclists increase, there is an urgent need to understand the factors that affect the severity of injuries they sustain in crashes. In this paper, we use cluster correspondence analysis (CCA) and hierarchical binary logit model to explore the factors associated with motorcyclists’ crash injury severities in Utah between 2016 and 2020. Cluster correspondence analysis was used to cluster the crash data into seven groups, while hierarchical binary logit model was used to identify the significant factors that contributed to the injury severity of motorcycle crashes. The results of this study indicate that among the crash-contributing factors the motorcyclist age, roadway alignment, roadside safety systems and temporal factors significantly contribute to motorcyclist crash severities. The model results further account for the correlation of variables within the clusters in the crash data. With the deeper understanding of the relationship between crash factors and injury severity in this study, the findings can help decision makers to implement targeted countermeasures to improve motorcyclist safety.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100197"},"PeriodicalIF":0.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A cost function approximation method for dynamic vehicle routing with docking and LIFO constraints 具有对接和后进先出约束的车辆动态路径的成本函数逼近方法

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100194

Markó Horváth, Tamás Kis, Péter Györgyi

In this paper, we study a dynamic pickup and delivery problem with docking constraints. There is a homogeneous fleet of vehicles to serve pickup-and-delivery requests at given locations. The vehicles can be loaded up to their capacity, while unloading has to follow the last-in-first-out (LIFO) rule. The locations have a limited number of docking ports for loading and unloading, which may force the vehicles to wait. The problem is dynamic since the transportation requests arrive real-time, over the day. Accordingly, the routes of the vehicles are to be determined dynamically. The goal is to satisfy all the requests such that a combination of tardiness penalties and traveling costs is minimized. We propose a cost function approximation based solution method. In each decision epoch, we solve the respective optimization problem with a perturbed objective function to ensure the solutions remain adaptable to accommodate new requests. We penalize waiting times and idle vehicles. We propose a variable neighborhood search based method for solving the optimization problems, and we apply two existing local search operators, and we also introduce a new one. We evaluate our method using a widely adopted benchmark dataset, and the results demonstrate that our approach significantly surpasses the current state-of-the-art methods.

本文研究了一个具有对接约束的动态取货问题。在给定的地点，有一个相同的车队来满足取货和送货的要求。车辆可以装载到最大容量，而卸载必须遵循后进先出（LIFO）规则。这些地点用于装卸的对接端口数量有限，这可能迫使车辆等待。这个问题是动态的，因为运输请求在一天内实时到达。因此，车辆的路线需要动态确定。我们的目标是满足所有的要求，从而将延误处罚和差旅费用的组合降到最低。我们提出了一种基于成本函数近似的求解方法。在每个决策时期，我们用摄动目标函数来解决各自的优化问题，以确保解决方案能够适应新的请求。我们惩罚等待时间和闲置车辆。提出了一种基于可变邻域搜索的优化算法，并在此基础上引入了一种新的局部搜索算子。我们使用广泛采用的基准数据集来评估我们的方法，结果表明我们的方法明显优于当前最先进的方法。

{"title":"A cost function approximation method for dynamic vehicle routing with docking and LIFO constraints","authors":"Markó Horváth, Tamás Kis, Péter Györgyi","doi":"10.1016/j.multra.2025.100194","DOIUrl":"10.1016/j.multra.2025.100194","url":null,"abstract":"<div><div>In this paper, we study a dynamic pickup and delivery problem with docking constraints. There is a homogeneous fleet of vehicles to serve pickup-and-delivery requests at given locations. The vehicles can be loaded up to their capacity, while unloading has to follow the last-in-first-out (LIFO) rule. The locations have a limited number of docking ports for loading and unloading, which may force the vehicles to wait. The problem is dynamic since the transportation requests arrive real-time, over the day. Accordingly, the routes of the vehicles are to be determined dynamically. The goal is to satisfy all the requests such that a combination of tardiness penalties and traveling costs is minimized. We propose a cost function approximation based solution method. In each decision epoch, we solve the respective optimization problem with a perturbed objective function to ensure the solutions remain adaptable to accommodate new requests. We penalize waiting times and idle vehicles. We propose a variable neighborhood search based method for solving the optimization problems, and we apply two existing local search operators, and we also introduce a new one. We evaluate our method using a widely adopted benchmark dataset, and the results demonstrate that our approach significantly surpasses the current state-of-the-art methods.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100194"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Changes in crash types and contributing factors after bus rapid transit (BRT) infrastructure installation in Albuquerque, New Mexico 新墨西哥州阿尔伯克基快速公交（BRT）基础设施安装后事故类型的变化及其影响因素

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100192

Nicholas N. Ferenchak, Brady A. Woods

Bus rapid transit (BRT) is an increasingly popular form of public transportation that seeks to achieve the speed and reliability of fixed rail with the flexibility and affordability of a bus system. In this paper, we examine safety outcomes before and after the construction of BRT infrastructure, specifically investigating how different crash types and contributing factors changed for all motor vehicle crashes and for pedestrian crashes. New Mexico Department of Transportation (NMDOT) provided crash data for the Central Avenue corridor of the Albuquerque Rapid Transit (ART) system in Albuquerque, NM. The construction of ART correlated with significant reductions in crashes attributed to excessive speed (for all modes) and left turning vehicles (for all modes and pedestrians). Crashes attributed to excessive speed decreased by 19.1 % (p = 0.059) after ART construction while crashes attributed to excessive speed resulting in fatal or serious (KA) injury decreased 100.0 % (p < 0.001). Although the number of KA pedestrian crashes increased 15.2 % (p = 0.272), KA pedestrian crashes involving a left-turning motor vehicle decreased by 80.0 % (p = 0.070). For all modes, crashes involving left-turning vehicles decreased by 34.8 % (p < 0.001) and crashes involving left-turning vehicles resulting in a KA injury decreased by 87.5 % (p = 0.009). This research provides insights into the multimodal traffic safety implications of the burgeoning public transportation mode of BRT.

快速公交（BRT）是一种越来越受欢迎的公共交通形式，它寻求实现固定轨道的速度和可靠性，以及公交系统的灵活性和可负担性。在本文中，我们研究了BRT基础设施建设前后的安全结果，特别是研究了所有机动车碰撞和行人碰撞的不同碰撞类型和影响因素的变化。新墨西哥州交通部（NMDOT）提供了新墨西哥州阿尔伯克基快速交通（ART）系统中央大道走廊的碰撞数据。ART的建设与超速（适用于所有模式）和左转车辆（适用于所有模式和行人）造成的撞车事故显著减少相关。在ART建造后，由于超速导致的撞车事故减少了19.1% (p = 0.059)，而由于超速导致致命或严重（KA）伤害的撞车事故减少了100.0% (p <；0.001)。虽然KA行人交通事故数量增加了15.2% (p = 0.272)，但涉及左转弯机动车的KA行人交通事故减少了80.0% （p = 0.070）。在所有模式下，涉及左转弯车辆的撞车事故减少了34.8% (p <；0.001)，涉及左转弯车辆的碰撞导致KA伤害减少了87.5% （p = 0.009）。本研究深入探讨了快速公交这一新兴公共交通模式对多模式交通安全的影响。

{"title":"Changes in crash types and contributing factors after bus rapid transit (BRT) infrastructure installation in Albuquerque, New Mexico","authors":"Nicholas N. Ferenchak, Brady A. Woods","doi":"10.1016/j.multra.2025.100192","DOIUrl":"10.1016/j.multra.2025.100192","url":null,"abstract":"<div><div>Bus rapid transit (BRT) is an increasingly popular form of public transportation that seeks to achieve the speed and reliability of fixed rail with the flexibility and affordability of a bus system. In this paper, we examine safety outcomes before and after the construction of BRT infrastructure, specifically investigating how different crash types and contributing factors changed for all motor vehicle crashes and for pedestrian crashes. New Mexico Department of Transportation (NMDOT) provided crash data for the Central Avenue corridor of the Albuquerque Rapid Transit (ART) system in Albuquerque, NM. The construction of ART correlated with significant reductions in crashes attributed to excessive speed (for all modes) and left turning vehicles (for all modes and pedestrians). Crashes attributed to excessive speed decreased by 19.1 % (<em>p</em> = 0.059) after ART construction while crashes attributed to excessive speed resulting in fatal or serious (KA) injury decreased 100.0 % (<em>p</em> < 0.001). Although the number of KA pedestrian crashes increased 15.2 % (<em>p</em> = 0.272), KA pedestrian crashes involving a left-turning motor vehicle decreased by 80.0 % (<em>p</em> = 0.070). For all modes, crashes involving left-turning vehicles decreased by 34.8 % (<em>p</em> < 0.001) and crashes involving left-turning vehicles resulting in a KA injury decreased by 87.5 % (<em>p</em> = 0.009). This research provides insights into the multimodal traffic safety implications of the burgeoning public transportation mode of BRT.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100192"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unveiling passenger satisfaction in rail transit through a consumption values perspective 从消费价值视角透视轨道交通乘客满意度

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100196

Siti Norida Wahab , Muhammad Iskandar Hamzah , Norazah Mohd Suki , Yueh Suan Chong , Chin Pei Kua

This study aims to investigate passenger satisfaction in rail transit systems within emerging economies, utilizing a theory of consumption values. It seeks to understand how various values, such as functional, social, emotional, conditional, and epistemic, influence passenger perceptions and experiences providing insights for enhancing rail transit services. This study employs a self-administered questionnaire distributed to 418 passenger rail transit users in Kuala Lumpur city centre over a three-month period. Smart-PLS software was utilized to examine relationships between consumption values and passenger satisfaction. The study findings reveal strong support for functional and social values in influencing passenger satisfaction within rail transit systems of emerging economies. Similarly, emotional and conditional values also play a significant role. Surprisingly, epistemic value does not exhibit substantial influence, highlighting potential disparities in passenger perceptions and priorities. Rail transit operators and regulators should focus on these facets of consumption values in order to maximize passenger satisfaction in rail transit. Conditional aspects such as safety, punctuality, frequency, and accessibility should also be given priority. What is new to the existing literature is that epistemic value was confirmed as the trivial predictor of passengers' satisfaction in rail transit. Hence, clear signage, informative announcements, or accessible digital resources provided by the transit authority will enhance passengers' knowledge and overall experience. Being among a few studies in measuring rail transit satisfaction using the consumption values approach, particularly in the context of Asia-Pacific emerging economies, the empirical results attained broadened the growing literature pertinent to consumer behaviour, consumption values, and sustainable transportation. The findings offer new insights into enhancing rail transit services, emphasizing the need for clear communication and informative resources to boost passenger satisfaction.

本研究旨在利用消费价值理论调查新兴经济体中轨道交通系统的乘客满意度。它试图了解各种价值，如功能、社会、情感、条件和认知，如何影响乘客的感知和体验，为加强轨道交通服务提供见解。本研究采用了一份自我管理的问卷，在三个月的时间里分发给吉隆坡市中心的418名客运轨道交通用户。使用Smart-PLS软件检验消费值与乘客满意度之间的关系。研究结果显示，在新兴经济体的轨道交通系统中，功能和社会价值对乘客满意度的影响得到了强有力的支持。同样，情感和条件价值观也起着重要作用。令人惊讶的是，认知价值并没有表现出实质性的影响，这突出了乘客感知和优先级的潜在差异。轨道交通运营商和监管机构应该关注这些方面的消费价值，以最大限度地提高轨道交通乘客的满意度。有条件的方面，如安全、准时、频率和可达性也应优先考虑。现有文献的创新之处在于，认知价值被证实是轨道交通乘客满意度的微不足道的预测因子。因此，交通管理部门提供的清晰标志、信息丰富的公告或可访问的数字资源将提高乘客的知识和整体体验。作为使用消费价值方法测量轨道交通满意度的少数研究之一，特别是在亚太新兴经济体的背景下，所获得的实证结果拓宽了与消费者行为、消费价值和可持续交通相关的日益增长的文献。研究结果为加强轨道交通服务提供了新的见解，强调需要明确的沟通和信息资源来提高乘客满意度。

{"title":"Unveiling passenger satisfaction in rail transit through a consumption values perspective","authors":"Siti Norida Wahab , Muhammad Iskandar Hamzah , Norazah Mohd Suki , Yueh Suan Chong , Chin Pei Kua","doi":"10.1016/j.multra.2025.100196","DOIUrl":"10.1016/j.multra.2025.100196","url":null,"abstract":"<div><div>This study aims to investigate passenger satisfaction in rail transit systems within emerging economies, utilizing a theory of consumption values. It seeks to understand how various values, such as functional, social, emotional, conditional, and epistemic, influence passenger perceptions and experiences providing insights for enhancing rail transit services. This study employs a self-administered questionnaire distributed to 418 passenger rail transit users in Kuala Lumpur city centre over a three-month period. Smart-PLS software was utilized to examine relationships between consumption values and passenger satisfaction. The study findings reveal strong support for functional and social values in influencing passenger satisfaction within rail transit systems of emerging economies. Similarly, emotional and conditional values also play a significant role. Surprisingly, epistemic value does not exhibit substantial influence, highlighting potential disparities in passenger perceptions and priorities. Rail transit operators and regulators should focus on these facets of consumption values in order to maximize passenger satisfaction in rail transit. Conditional aspects such as safety, punctuality, frequency, and accessibility should also be given priority. What is new to the existing literature is that epistemic value was confirmed as the trivial predictor of passengers' satisfaction in rail transit. Hence, clear signage, informative announcements, or accessible digital resources provided by the transit authority will enhance passengers' knowledge and overall experience. Being among a few studies in measuring rail transit satisfaction using the consumption values approach, particularly in the context of Asia-Pacific emerging economies, the empirical results attained broadened the growing literature pertinent to consumer behaviour, consumption values, and sustainable transportation. The findings offer new insights into enhancing rail transit services, emphasizing the need for clear communication and informative resources to boost passenger satisfaction.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100196"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal adaptive traffic signal control: A decentralized multiagent reinforcement learning approach 多模式自适应交通信号控制：一种分散的多智能体强化学习方法

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100190

Kareem Othman , Xiaoyu Wang , Amer Shalaby , Baher Abdulhai

Public transit is considered a compelling alternative to the car, renowned for its affordability and sustainability, given that a single transit vehicle can accommodate a substantially higher number of passengers compared to regular passenger vehicles. In urban areas, a significant portion of the travel time spent by street-running transit vehicles is consumed waiting at traffic signals. Thus, transit signal priority (TSP) strategies have evolved over the years to give preference to transit vehicles at signalized intersections. Traffic signals are usually optimized for the general vehicular traffic flow, with TSP logic subsequently inserted as an add-on to modify the underlying signal timing plans, thereby granting priority to transit vehicles. However, one major issue associated with the implementation of TSP is its negative impact on the surrounding traffic, creating a conflict between prioritizing passenger vehicles versus transit vehicles. This paper proposes a novel decentralized multimodal multiagent reinforcement learning signal controller that simultaneously optimizes the total person delays for both traffic and transit. The controller, named embedding communicated Multi-Agent Reinforcement Learning for Integrated Network-Multi Modal (eMARLIN-MM), consists of two components: the encoder that is responsible for transforming the observations into latent space and the executor that serves as the Q-network making timing decisions. eMARLIN-MM establishes communication between the control agents by sharing information between neighboring intersections. eMARLIN-MM was tested in a simulation model of five intersections in North York, Ontario, Canada. The results show that eMARLIN-MM can substantially reduce the total person delays by 54 % to 66 % compared to pre-timed signals at different levels of bus occupancy, outperforming the independent Deep Q-Networks (DQN) agents. eMARLIN-MM also outperforms eMARLIN which does not incorporate buses and bus passengers in the signal timing optimization process.

公共交通被认为是汽车的一个令人信服的替代品，以其可负担性和可持续性而闻名，因为与普通乘用车相比，一辆公共交通工具可以容纳更多的乘客。在城市地区，在街道上运行的交通车辆的很大一部分时间都花在了等待交通信号上。因此，多年来，交通信号优先（TSP）策略已经发展到优先考虑信号交叉口的交通车辆。交通信号通常针对一般车辆交通流进行优化，随后插入TSP逻辑作为附加组件来修改底层信号授时计划，从而赋予过境车辆优先权。然而，与TSP实施相关的一个主要问题是它对周围交通的负面影响，造成了优先考虑客运车辆与公交车辆之间的冲突。提出了一种新的分散多模态多智能体强化学习信号控制器，该控制器可以同时优化交通和公交的总延误。该控制器名为嵌入通信多智能体强化学习集成网络-多模态（eMARLIN-MM），由两个部分组成：负责将观测值转换为潜在空间的编码器和作为q网络进行时序决策的执行器。eMARLIN-MM通过在相邻的交叉口之间共享信息来建立控制代理之间的通信。eMARLIN-MM在加拿大安大略省北约克的五个十字路口的仿真模型中进行了测试。结果表明，eMARLIN-MM在不同的公交占用率水平下，与预定时信号相比，可以显著减少54%至66%的总人员延误，优于独立的深度q网络（DQN）代理。eMARLIN- mm在信号配时优化过程中也优于不考虑公交车和公交车乘客的eMARLIN。

{"title":"Multimodal adaptive traffic signal control: A decentralized multiagent reinforcement learning approach","authors":"Kareem Othman , Xiaoyu Wang , Amer Shalaby , Baher Abdulhai","doi":"10.1016/j.multra.2025.100190","DOIUrl":"10.1016/j.multra.2025.100190","url":null,"abstract":"<div><div>Public transit is considered a compelling alternative to the car, renowned for its affordability and sustainability, given that a single transit vehicle can accommodate a substantially higher number of passengers compared to regular passenger vehicles. In urban areas, a significant portion of the travel time spent by street-running transit vehicles is consumed waiting at traffic signals. Thus, transit signal priority (TSP) strategies have evolved over the years to give preference to transit vehicles at signalized intersections. Traffic signals are usually optimized for the general vehicular traffic flow, with TSP logic subsequently inserted as an add-on to modify the underlying signal timing plans, thereby granting priority to transit vehicles. However, one major issue associated with the implementation of TSP is its negative impact on the surrounding traffic, creating a conflict between prioritizing passenger vehicles versus transit vehicles. This paper proposes a novel decentralized multimodal multiagent reinforcement learning signal controller that simultaneously optimizes the total person delays for both traffic and transit. The controller, named embedding communicated Multi-Agent Reinforcement Learning for Integrated Network-Multi Modal (eMARLIN-MM), consists of two components: the encoder that is responsible for transforming the observations into latent space and the executor that serves as the Q-network making timing decisions. eMARLIN-MM establishes communication between the control agents by sharing information between neighboring intersections. eMARLIN-MM was tested in a simulation model of five intersections in North York, Ontario, Canada. The results show that eMARLIN-MM can substantially reduce the total person delays by 54 % to 66 % compared to pre-timed signals at different levels of bus occupancy, outperforming the independent Deep Q-Networks (DQN) agents. eMARLIN-MM also outperforms eMARLIN which does not incorporate buses and bus passengers in the signal timing optimization process.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100190"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maritime vessel movement prediction: A temporal convolutional network model with optimal look-back window size determination 船舶运动预测：具有最佳回望窗大小确定的时间卷积网络模型

Multimodal Transportation

Pub Date : 2025-01-09 DOI: 10.1016/j.multra.2025.100191

Farshad Farahnakian, Paavo Nevalainen, Fahimeh Farahnakian, Tanja Vähämäki, Jukka Heikkonen

Ship movement prediction models are crucial for improving safety and situational awareness in complex maritime shipping networks. Current prediction models that utilize Automatic Identification System (AIS) data to forecast ship movements typically rely on a fixed look-back window size. This approach does not effectively consider the necessary amount of data required to train the models properly. This paper presents a framework that dynamically determines the optimal look-back window size for AIS data, tailored to user-defined prediction intervals. Initially, a DBSCAN clustering method, along with various pre-processing techniques, has been employed to efficiently eliminate non-essential data points and address noise in the raw AIS data. Following this, Temporal Convolutional Networks (TCNs) have been trained using the dynamic characteristics of ship movements based on one month of AIS data (April 2023) collected from the Baltic Sea, evaluating various look-back window sizes to identify the optimal size required for predictions. Subsequently, the framework has been tested using an additional AIS dataset in two scenarios: 1-hour and 5-hour predictions. The experimental results indicate that the proposed framework can effectively select the necessary AIS samples for forecasting a ship’s future movements. This framework has the potential to optimize prediction services by identifying the ideal look-back window size, thereby providing maritime agents with high-quality and accurate predictions to enhance their decision-making processes.

在复杂的海上航运网络中，船舶运动预测模型对于提高安全性和态势感知至关重要。目前利用自动识别系统（AIS）数据预测船舶运动的预测模型通常依赖于固定的后视窗口大小。这种方法没有有效地考虑正确训练模型所需的必要数据量。本文提出了一个框架，动态确定AIS数据的最佳回望窗口大小，根据用户自定义的预测间隔量身定制。最初，采用DBSCAN聚类方法以及各种预处理技术，有效地消除非必要数据点并处理原始AIS数据中的噪声。在此之后，基于从波罗的海收集的一个月的AIS数据（2023年4月），使用船舶运动的动态特征对时间卷积网络（tcn）进行了训练，评估了各种回看窗口的大小，以确定预测所需的最佳大小。随后，使用额外的AIS数据集在两种情况下对该框架进行了测试：1小时和5小时预测。实验结果表明，该框架可以有效地选择所需的AIS样本来预测船舶的未来运动。该框架有可能通过确定理想的回望窗口大小来优化预测服务，从而为海事代理提供高质量和准确的预测，以提高他们的决策过程。

{"title":"Maritime vessel movement prediction: A temporal convolutional network model with optimal look-back window size determination","authors":"Farshad Farahnakian, Paavo Nevalainen, Fahimeh Farahnakian, Tanja Vähämäki, Jukka Heikkonen","doi":"10.1016/j.multra.2025.100191","DOIUrl":"10.1016/j.multra.2025.100191","url":null,"abstract":"<div><div>Ship movement prediction models are crucial for improving safety and situational awareness in complex maritime shipping networks. Current prediction models that utilize Automatic Identification System (AIS) data to forecast ship movements typically rely on a fixed look-back window size. This approach does not effectively consider the necessary amount of data required to train the models properly. This paper presents a framework that dynamically determines the optimal look-back window size for AIS data, tailored to user-defined prediction intervals. Initially, a DBSCAN clustering method, along with various pre-processing techniques, has been employed to efficiently eliminate non-essential data points and address noise in the raw AIS data. Following this, Temporal Convolutional Networks (TCNs) have been trained using the dynamic characteristics of ship movements based on one month of AIS data (April 2023) collected from the Baltic Sea, evaluating various look-back window sizes to identify the optimal size required for predictions. Subsequently, the framework has been tested using an additional AIS dataset in two scenarios: 1-hour and 5-hour predictions. The experimental results indicate that the proposed framework can effectively select the necessary AIS samples for forecasting a ship’s future movements. This framework has the potential to optimize prediction services by identifying the ideal look-back window size, thereby providing maritime agents with high-quality and accurate predictions to enhance their decision-making processes.</div></div>","PeriodicalId":100933,"journal":{"name":"Multimodal Transportation","volume":"4 1","pages":"Article 100191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0