Pub Date : 2025-08-09DOI: 10.1080/19427867.2024.2425514
Ruijie Li , Zuduo Zheng , Daiheng Ni , Linbo Li
This paper introduces a car-following (CF) extraction algorithm to address challenges in aerial-based trajectory data extraction. The algorithm, comprising four steps – vehicle grouping, elimination of false overtaking behavior, vehicle sorting, and CF pair matching – was applied to Zen Traffic Data, extracting 246 CF pairs. Three datasets were then generated: kilopost-based, geography-based, and velocity-based. A quality analysis revealed significant inconsistencies between data fields, with the geography-based dataset being least affected by high-frequency noise. The extracted CF data also demonstrated a more comprehensive driving regime than NGSIM, with complete driving regimes identified. Furthermore, the impact of data noise on CF model calibration and heterogeneity analysis was thoroughly assessed. This study enhances our understanding of trajectory data quality and highlights the richness of driving behavior information in Zen Traffic Data.
{"title":"A method for long car-following pair extraction and comprehensive data quality assessment: a case study using Zen Traffic Data","authors":"Ruijie Li , Zuduo Zheng , Daiheng Ni , Linbo Li","doi":"10.1080/19427867.2024.2425514","DOIUrl":"10.1080/19427867.2024.2425514","url":null,"abstract":"<div><div>This paper introduces a car-following (CF) extraction algorithm to address challenges in aerial-based trajectory data extraction. The algorithm, comprising four steps – vehicle grouping, elimination of false overtaking behavior, vehicle sorting, and CF pair matching – was applied to Zen Traffic Data, extracting 246 CF pairs. Three datasets were then generated: kilopost-based, geography-based, and velocity-based. A quality analysis revealed significant inconsistencies between data fields, with the geography-based dataset being least affected by high-frequency noise. The extracted CF data also demonstrated a more comprehensive driving regime than NGSIM, with complete driving regimes identified. Furthermore, the impact of data noise on CF model calibration and heterogeneity analysis was thoroughly assessed. This study enhances our understanding of trajectory data quality and highlights the richness of driving behavior information in Zen Traffic Data.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 7","pages":"Pages 1231-1250"},"PeriodicalIF":3.3,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2403818
Sumin Zhang , Ri Bai , Rui He , Zhiwei Meng , Yupeng Chang , Yongshuai Zhi
In autonomous driving, accurately predicting the trajectories of surrounding vehicles is essential, particularly in dense and heterogeneous urban traffic. We propose a graph-structured model with a category layer to efficiently forecast the target vehicle’s trajectory. The model enables flexible selection of interacting objects based on environmental interactions and extracts spatial-temporal features using a graph convolutional network. A categorical layer is introduced to account for the different influences of dynamic agents, while vehicle dynamics constraints ensure the feasibility of predicted trajectories. We developed a new heterogeneous and dense urban unsignalized intersection dataset (HID), capturing complex urban interactions, and conducted extensive experiments on HID, ApolloScape, and TRAF datasets. Results demonstrate that our model outperforms benchmark methods across diverse urban scenarios, and the integration of key modules significantly enhances prediction accuracy and performance.
{"title":"Research on vehicle trajectory prediction methods in dense and heterogeneous urban traffic","authors":"Sumin Zhang , Ri Bai , Rui He , Zhiwei Meng , Yupeng Chang , Yongshuai Zhi","doi":"10.1080/19427867.2024.2403818","DOIUrl":"10.1080/19427867.2024.2403818","url":null,"abstract":"<div><div>In autonomous driving, accurately predicting the trajectories of surrounding vehicles is essential, particularly in dense and heterogeneous urban traffic. We propose a graph-structured model with a category layer to efficiently forecast the target vehicle’s trajectory. The model enables flexible selection of interacting objects based on environmental interactions and extracts spatial-temporal features using a graph convolutional network. A categorical layer is introduced to account for the different influences of dynamic agents, while vehicle dynamics constraints ensure the feasibility of predicted trajectories. We developed a new heterogeneous and dense urban unsignalized intersection dataset (HID), capturing complex urban interactions, and conducted extensive experiments on HID, ApolloScape, and TRAF datasets. Results demonstrate that our model outperforms benchmark methods across diverse urban scenarios, and the integration of key modules significantly enhances prediction accuracy and performance.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 968-983"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144570682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2025.2488631
Xiaofeng Pan , Ling Jin
To design an effective MaaS bundles, the weights of attributes of MaaS bundles should be first identified. The object case of best-worst scaling (i.e. BWS case 1) method is adopted, and a factor representing the degree of mobility service satisfaction is introduced to modify the weights of attributes of MaaS bundles. Based on such a modification, latent classes exploded logit models are established and estimated using samples from three cities of China. The estimation results confirm the advantage of considering people’s satisfaction toward mobility services in the model and show that heterogeneous weights of the attributes of MaaS bundles are found not only in the samples from different cities but also in the sample from a same city. These findings confirm the validity of the modified model of BWS case 1 and suggest the MaaS providers to offer tailored mobility services for specific socio-demographic groups.
{"title":"Integrating mobility service satisfaction into the object case of best-worst scaling method to weight attributes of MaaS bundles: findings based on samples from three cities of China","authors":"Xiaofeng Pan , Ling Jin","doi":"10.1080/19427867.2025.2488631","DOIUrl":"10.1080/19427867.2025.2488631","url":null,"abstract":"<div><div>To design an effective MaaS bundles, the weights of attributes of MaaS bundles should be first identified. The object case of best-worst scaling (i.e. BWS case 1) method is adopted, and a factor representing the degree of mobility service satisfaction is introduced to modify the weights of attributes of MaaS bundles. Based on such a modification, latent classes exploded logit models are established and estimated using samples from three cities of China. The estimation results confirm the advantage of considering people’s satisfaction toward mobility services in the model and show that heterogeneous weights of the attributes of MaaS bundles are found not only in the samples from different cities but also in the sample from a same city. These findings confirm the validity of the modified model of BWS case 1 and suggest the MaaS providers to offer tailored mobility services for specific socio-demographic groups.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1138-1154"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ride-hailing services are booming in our daily lives, but it is unclear that how the platforms should set prices to maximize their profits when facing one kind of rationally inattentive passengers in a two-sided market. To fill this gap, we establish a profit maximization model for the ride-hailing platform based on queuing theory and rational inattention theory and analyze the properties of the model. Numerical examples are presented to demonstrate the impacts of perceived high and low service levels, information cost and prior belief on the optimal price and commission rate of the ride-hailing platform. The results show that (1) for different cities, there is always an optimal pricing strategy to maximize the profit of the platform. (2) To ensure maximum profit, the platform should disclose the service information of ride-hailing as much as possible, but also maintain the unknownness of ride-hailing services appropriately.
{"title":"Pricing model of ride-hailing platform considering rationally inattentive passengers","authors":"Chuan-Lin Zhao , Yangqi Sun , Haijuan Wu , Dongbao Niu","doi":"10.1080/19427867.2024.2400820","DOIUrl":"10.1080/19427867.2024.2400820","url":null,"abstract":"<div><div>The ride-hailing services are booming in our daily lives, but it is unclear that how the platforms should set prices to maximize their profits when facing one kind of rationally inattentive passengers in a two-sided market. To fill this gap, we establish a profit maximization model for the ride-hailing platform based on queuing theory and rational inattention theory and analyze the properties of the model. Numerical examples are presented to demonstrate the impacts of perceived high and low service levels, information cost and prior belief on the optimal price and commission rate of the ride-hailing platform. The results show that (1) for different cities, there is always an optimal pricing strategy to maximize the profit of the platform. (2) To ensure maximum profit, the platform should disclose the service information of ride-hailing as much as possible, but also maintain the unknownness of ride-hailing services appropriately.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 931-941"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2408923
Yue Zhang , Bin Shuai , Jing Zhou , Dezhi Yin , Wencheng Huang
The increasing diversity of transportation modes and the rapid expansion of transportation networks present significant challenges for modeling multi-layer comprehensive transportation networks. It is crucial to determine whether aggregating certain layers is a viable option for balancing complexity reduction and information preservation. This decision defines the layered structures and informs subsequent analyses of these networks. Two-dimensional factors, namely topological structures and transportation attributes, are considered to enhance understanding of the similarities among network layers. The relative entropy and the Gini index are employed as metrics to assess information gain or loss resulting from layer aggregation or segregation, guiding decisions on network reduction. Furthermore, an integrated similarity measure, based on the quantum Jensen-Shannon divergence and the Gower distance, is utilized to identify the optimal aggregation sequences. Two real-world transportation networks serve as case studies. Results demonstrate that these transportation networks are more effectively maintained with layer-separated structures, preserving maximum information.
{"title":"Should the multi-layer transportation network structure be reduced?","authors":"Yue Zhang , Bin Shuai , Jing Zhou , Dezhi Yin , Wencheng Huang","doi":"10.1080/19427867.2024.2408923","DOIUrl":"10.1080/19427867.2024.2408923","url":null,"abstract":"<div><div>The increasing diversity of transportation modes and the rapid expansion of transportation networks present significant challenges for modeling multi-layer comprehensive transportation networks. It is crucial to determine whether aggregating certain layers is a viable option for balancing complexity reduction and information preservation. This decision defines the layered structures and informs subsequent analyses of these networks. Two-dimensional factors, namely topological structures and transportation attributes, are considered to enhance understanding of the similarities among network layers. The relative entropy and the Gini index are employed as metrics to assess information gain or loss resulting from layer aggregation or segregation, guiding decisions on network reduction. Furthermore, an integrated similarity measure, based on the quantum Jensen-Shannon divergence and the Gower distance, is utilized to identify the optimal aggregation sequences. Two real-world transportation networks serve as case studies. Results demonstrate that these transportation networks are more effectively maintained with layer-separated structures, preserving maximum information.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1079-1090"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2416304
Changjian Zhang , Jie He , Haifeng Wang , Yuntao Ye , Xintong Yan , Chenwei Wang , Xiazhi Zhang
Blackspot identification is a global concern in road safety. The accident-based method has been widely employed over the past few decades but remains reactive, as it depends on accidents occurring and causing harm. To overcome its limitations, proactive methods based on surrogate indicators have emerged. However, apart from Traffic Conflict Technology (TCT), other surrogate indicators lack a comprehensive framework spanning from extraction to practical application, emphasizing a key priority for future research. Despite numerous proposed methods, critical evaluation of their strengths, limitations, and application contexts remains limited. Additionally, the literature often overlooks the measurement of ‘potential accident risk’ in blackspot identification. Due to the rarity and randomness of accidents, even high-risk sections may record accident counts below the threshold during observation. This paper reviews 182 studies, examining blackspot identification methods and exploring potential accident risk through surrogate indicators. It underscores the importance of integrating potential risk into identification processes and summarizes the application of these methods across countries with varying income levels. Finally, it outlines the connection between blackspot identification and accident severity analysis, offering recommendations for future research.
{"title":"A systematic review of the application and prospect of road accident blackspots identification approaches","authors":"Changjian Zhang , Jie He , Haifeng Wang , Yuntao Ye , Xintong Yan , Chenwei Wang , Xiazhi Zhang","doi":"10.1080/19427867.2024.2416304","DOIUrl":"10.1080/19427867.2024.2416304","url":null,"abstract":"<div><div>Blackspot identification is a global concern in road safety. The accident-based method has been widely employed over the past few decades but remains reactive, as it depends on accidents occurring and causing harm. To overcome its limitations, proactive methods based on surrogate indicators have emerged. However, apart from Traffic Conflict Technology (TCT), other surrogate indicators lack a comprehensive framework spanning from extraction to practical application, emphasizing a key priority for future research. Despite numerous proposed methods, critical evaluation of their strengths, limitations, and application contexts remains limited. Additionally, the literature often overlooks the measurement of ‘potential accident risk’ in blackspot identification. Due to the rarity and randomness of accidents, even high-risk sections may record accident counts below the threshold during observation. This paper reviews 182 studies, examining blackspot identification methods and exploring potential accident risk through surrogate indicators. It underscores the importance of integrating potential risk into identification processes and summarizes the application of these methods across countries with varying income levels. Finally, it outlines the connection between blackspot identification and accident severity analysis, offering recommendations for future research.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1114-1137"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2408920
Chamroeun Se , Jirapon Sunkpho , Warit Wipulanusat , Kevin Tantisevi , Thanapong Champahom , Vatanavongs Ratanavaraha
Motorcycle crashes remain a significant public safety concern, requiring diverse analytical approaches to inform countermeasures. This study uses machine learning to analyze injury severity in crashes in Thailand from 2018 to 2020. Traditional and advanced models, including including random forest (RF), support vector machine (SVM), deep neural network (DNN), recurrent neural network (RNN), long short-term memory (LSTM), and eXtreme gradient boosting (XGBoost), were compared. Hyperparameter tuning via GridSearchCV optimized performance. XGBoost, with a tradeoff score of 105.65%, outperformed other models in predicting severe and fatal injuries. SHapley Additive exPlanations (SHAPs) identified significant risk factors including speeding, drunk driving, two-lane roads, unlit conditions, head-on and truck collisions, and nighttime crashes. Conversely, factors such as barrier medians, flashing traffic signals, sideswipes, rear-end crashes, and wet roads were associated with reduced severity. These findings suggest opportunities for integrated infrastructure improvements and expanded rider training and education programs to address behavioral risks.
{"title":"Modeling motorcycle crash-injury severity utilizing explainable data-driven approaches","authors":"Chamroeun Se , Jirapon Sunkpho , Warit Wipulanusat , Kevin Tantisevi , Thanapong Champahom , Vatanavongs Ratanavaraha","doi":"10.1080/19427867.2024.2408920","DOIUrl":"10.1080/19427867.2024.2408920","url":null,"abstract":"<div><div>Motorcycle crashes remain a significant public safety concern, requiring diverse analytical approaches to inform countermeasures. This study uses machine learning to analyze injury severity in crashes in Thailand from 2018 to 2020. Traditional and advanced models, including including random forest (RF), support vector machine (SVM), deep neural network (DNN), recurrent neural network (RNN), long short-term memory (LSTM), and eXtreme gradient boosting (XGBoost), were compared. Hyperparameter tuning via GridSearchCV optimized performance. XGBoost, with a tradeoff score of 105.65%, outperformed other models in predicting severe and fatal injuries. SHapley Additive exPlanations (SHAPs) identified significant risk factors including speeding, drunk driving, two-lane roads, unlit conditions, head-on and truck collisions, and nighttime crashes. Conversely, factors such as barrier medians, flashing traffic signals, sideswipes, rear-end crashes, and wet roads were associated with reduced severity. These findings suggest opportunities for integrated infrastructure improvements and expanded rider training and education programs to address behavioral risks.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1053-1078"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2404358
Wenxiao Song , Lu Wang , Chao Wang , Chengcheng Shen , Jie Zhao , Nenggang Xie , Kang Hao Cheong
This paper addresses the safety issues of pedestrian-vehicle interactions at unsignalized pedestrian crossings by proposing a Hybrid Mountain Gazelle Optimizer-Long Short-Term Memory (HMGO-LSTM) model. The proposed model combines the Hybrid Mountain Gazelle Optimizer (HMGO) algorithm with a Long Short-Term Memory (LSTM) network, using HMGO as an LSTM hyperparameter optimizer. Real-world datasets of pedestrian and vehicle crossings from Ma’anshan were used to train and evaluate the model. The HMGO-LSTM model was compared with traditional classifiers such as K-Nearest Neighbors (KNN), Random Forest (RF), and Genetic Algorithm-Backpropagation (GA-BP). The results show that the HMGO-LSTM model outperforms these classifiers in predicting pedestrian-vehicle interaction behaviors, achieving higher classification accuracy and F1 score. The model also optimizes safety intervals for crossings, leading to new speed limit recommendations. Overall, the HMGO-LSTM model provides a robust theoretical foundation for managing and designing safer pedestrian and vehicle crossings.
{"title":"Predictive classification of pedestrian-vehicle crossing behaviors using a hybrid mountain gazelle optimizer-enhanced Long Short-Term Memory model","authors":"Wenxiao Song , Lu Wang , Chao Wang , Chengcheng Shen , Jie Zhao , Nenggang Xie , Kang Hao Cheong","doi":"10.1080/19427867.2024.2404358","DOIUrl":"10.1080/19427867.2024.2404358","url":null,"abstract":"<div><div>This paper addresses the safety issues of pedestrian-vehicle interactions at unsignalized pedestrian crossings by proposing a Hybrid Mountain Gazelle Optimizer-Long Short-Term Memory (HMGO-LSTM) model. The proposed model combines the Hybrid Mountain Gazelle Optimizer (HMGO) algorithm with a Long Short-Term Memory (LSTM) network, using HMGO as an LSTM hyperparameter optimizer. Real-world datasets of pedestrian and vehicle crossings from Ma’anshan were used to train and evaluate the model. The HMGO-LSTM model was compared with traditional classifiers such as K-Nearest Neighbors (KNN), Random Forest (RF), and Genetic Algorithm-Backpropagation (GA-BP). The results show that the HMGO-LSTM model outperforms these classifiers in predicting pedestrian-vehicle interaction behaviors, achieving higher classification accuracy and F1 score. The model also optimizes safety intervals for crossings, leading to new speed limit recommendations. Overall, the HMGO-LSTM model provides a robust theoretical foundation for managing and designing safer pedestrian and vehicle crossings.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1017-1029"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2407184
Hao Li , Zhengwu Wang , Shuiwang Chen , Weiyao Xu , Yan Li , Jie Wang
This study explores enhancing carsharing services by integrating gasoline and electric vehicles into a one-way mixed fleet carsharing system (OMFCS). The focus is on optimizing configurations (fleet and staff size, initial deployment) and operational strategies (vehicle relocation and staff rebalancing) while considering carbon emission costs. Employing a space-time-electricity network modeling approach, we developed an integer linear programming model to tackle the configurations and operational strategies optimization problem. For solving this model, we introduce a Lagrangian relaxation-branch bound approach, which integrates subgradient, dynamic programming and greedy-based heuristics algorithm. An illustrative case and a real-world case are conducted to demonstrate the efficiency of the proposed solution method and the analysis sheds light on the configurations and operational strategies of OMFCS. The sensitive analysis results suggest that OMFCS is more profitable and balances user service quality and carbon emissions better than carsharing systems using only one type of vehicle.
{"title":"Optimizing fleet, staff configuration and operational strategies in one-way mixed fleet carsharing systems: a Lagrangian relaxation-based approach","authors":"Hao Li , Zhengwu Wang , Shuiwang Chen , Weiyao Xu , Yan Li , Jie Wang","doi":"10.1080/19427867.2024.2407184","DOIUrl":"10.1080/19427867.2024.2407184","url":null,"abstract":"<div><div>This study explores enhancing carsharing services by integrating gasoline and electric vehicles into a one-way mixed fleet carsharing system (OMFCS). The focus is on optimizing configurations (fleet and staff size, initial deployment) and operational strategies (vehicle relocation and staff rebalancing) while considering carbon emission costs. Employing a space-time-electricity network modeling approach, we developed an integer linear programming model to tackle the configurations and operational strategies optimization problem. For solving this model, we introduce a Lagrangian relaxation-branch bound approach, which integrates subgradient, dynamic programming and greedy-based heuristics algorithm. An illustrative case and a real-world case are conducted to demonstrate the efficiency of the proposed solution method and the analysis sheds light on the configurations and operational strategies of OMFCS. The sensitive analysis results suggest that OMFCS is more profitable and balances user service quality and carbon emissions better than carsharing systems using only one type of vehicle.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1030-1052"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2025-07-03DOI: 10.1080/19427867.2024.2416309
Pushkin Kachroo , Anil Koushik , M. Manoj
Activity schedule results from a complex decision-making process characterized by several interrelated decisions. Different facets of an activity schedule such as activity type, timing, duration, etc. influence each other and this makes modeling activity schedules a complex task. This complexity has compelled researchers to explore different approaches for modeling activity schedules, among which two predominant approaches can be identified: the utility-maximization theory based econometric approach and the computational process modeling approach. Despite their advantages and a few successful practical applications, challenges still remain leaving avenues for exploration of new approaches. This paper contributes in this direction by reviewing the relationship between language, grammar, and machines in the context of sequence analysis for activity sequence generation. Following that, the paper presents a stochastic Finite State Machine that can generate activity sequences to match the frequency distribution of sequences from a given data set. Our results show that the proposed algorithm can not only generate activity sequences with a distribution similar to that of original data but can also efficiently generate new patterns not in the original data.
{"title":"Automatic activity-travel sequence generator using language, grammar, and machine theory","authors":"Pushkin Kachroo , Anil Koushik , M. Manoj","doi":"10.1080/19427867.2024.2416309","DOIUrl":"10.1080/19427867.2024.2416309","url":null,"abstract":"<div><div>Activity schedule results from a complex decision-making process characterized by several interrelated decisions. Different facets of an activity schedule such as activity type, timing, duration, etc. influence each other and this makes modeling activity schedules a complex task. This complexity has compelled researchers to explore different approaches for modeling activity schedules, among which two predominant approaches can be identified: the utility-maximization theory based econometric approach and the computational process modeling approach. Despite their advantages and a few successful practical applications, challenges still remain leaving avenues for exploration of new approaches. This paper contributes in this direction by reviewing the relationship between language, grammar, and machines in the context of sequence analysis for activity sequence generation. Following that, the paper presents a stochastic Finite State Machine that can generate activity sequences to match the frequency distribution of sequences from a given data set. Our results show that the proposed algorithm can not only generate activity sequences with a distribution similar to that of original data but can also efficiently generate new patterns not in the original data.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 6","pages":"Pages 1091-1100"},"PeriodicalIF":3.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号