Pub Date : 2024-09-06DOI: 10.1109/TITS.2024.3450846
Zhihuan Jiang;Ailing Huang;Qian Luo;Wei Guan
Accurate prediction of demand for traditional taxi and ride-hailing services is crucial for addressing supply-demand imbalances. However, recent studies based on global adaptive graphs, local spatial-temporal graphs, and self-attention mechanisms struggle to effectively capture the dynamic and intricate relations in demand. Moreover, existing dynamic graph generators face challenges in efficiently producing high-quality graphs to learn the diverse interactions among zones along time axis and their shared patterns spanning various time scales. To solve these challenges, we propose a novel Local-Perception-Enhanced Spatial-Temporal Evolving Graph Transformer Network (LPE-STGTN), aimed at improving the effectiveness and efficiency of extracting intricate local dependencies in taxi demand. Specifically, we elaborately design a spatial-temporal evolving graph generator to absorb shared and diversified inter-zone relations across different temporal periodicities and specific interactions among zones within each time step. Furthermore, an attention free transformer with local context (AFT-local) is introduced to effectively learn the correlations between adjacent time steps. Extensive experiments on three taxi datasets of New York and Beijing are carried out to evaluate the superior performance of our model. Compared with the most competitive baseline, our model achieves a balance between effectiveness and efficiency on three datasets, with average training time reduction of 70.66% and average performance improvement of 1.96%.
{"title":"Local-Perception-Enhanced Spatial–Temporal Evolving Graph Transformer Network: Citywide Demand Prediction of Taxi and Ride-Hailing","authors":"Zhihuan Jiang;Ailing Huang;Qian Luo;Wei Guan","doi":"10.1109/TITS.2024.3450846","DOIUrl":"10.1109/TITS.2024.3450846","url":null,"abstract":"Accurate prediction of demand for traditional taxi and ride-hailing services is crucial for addressing supply-demand imbalances. However, recent studies based on global adaptive graphs, local spatial-temporal graphs, and self-attention mechanisms struggle to effectively capture the dynamic and intricate relations in demand. Moreover, existing dynamic graph generators face challenges in efficiently producing high-quality graphs to learn the diverse interactions among zones along time axis and their shared patterns spanning various time scales. To solve these challenges, we propose a novel Local-Perception-Enhanced Spatial-Temporal Evolving Graph Transformer Network (LPE-STGTN), aimed at improving the effectiveness and efficiency of extracting intricate local dependencies in taxi demand. Specifically, we elaborately design a spatial-temporal evolving graph generator to absorb shared and diversified inter-zone relations across different temporal periodicities and specific interactions among zones within each time step. Furthermore, an attention free transformer with local context (AFT-local) is introduced to effectively learn the correlations between adjacent time steps. Extensive experiments on three taxi datasets of New York and Beijing are carried out to evaluate the superior performance of our model. Compared with the most competitive baseline, our model achieves a balance between effectiveness and efficiency on three datasets, with average training time reduction of 70.66% and average performance improvement of 1.96%.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"17105-17121"},"PeriodicalIF":7.9,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/tits.2024.3450538
Yanyan Guo, Ge Xu, Zhicai Zhang, Zengbiao Li, Xinzhe You, Guixia Kang, Lin Cai, Laurence T. Yang
{"title":"Resource Block-Based Co-Design of Trajectory and Communication in UAV-Assisted Data Collection Networks","authors":"Yanyan Guo, Ge Xu, Zhicai Zhang, Zengbiao Li, Xinzhe You, Guixia Kang, Lin Cai, Laurence T. Yang","doi":"10.1109/tits.2024.3450538","DOIUrl":"https://doi.org/10.1109/tits.2024.3450538","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"5 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/tits.2024.3450526
Xiang Li, Yuwei Zhao, Ziyan Feng
{"title":"Customized Bus Service Design With Holding Control and Heterogeneous Fleet: A Column-Generation-Based Decomposition Algorithm","authors":"Xiang Li, Yuwei Zhao, Ziyan Feng","doi":"10.1109/tits.2024.3450526","DOIUrl":"https://doi.org/10.1109/tits.2024.3450526","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"130 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/tits.2024.3450471
Mitali Sarkar, Ohhyun Kweon, Byung-In Kim, Dong Gu Choi, Duck Young Kim
{"title":"Synergizing Autonomous and Traditional Vehicles: A Systematic Review of Advances and Challenges in Traffic Flow Management With Signalized Intersections","authors":"Mitali Sarkar, Ohhyun Kweon, Byung-In Kim, Dong Gu Choi, Duck Young Kim","doi":"10.1109/tits.2024.3450471","DOIUrl":"https://doi.org/10.1109/tits.2024.3450471","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"12 1","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220418","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}
While many studies explore cascading failures on single transit network, most of them fail to interpret the spread of failures between multimodal public transportation systems. Relevant research tends to measure station coupling strength under normal conditions, but this strength would change due to the variations of network topology, transportation, and travel characteristics under cascading failures. To address the above issues, this study proposes a multimodal coupled map lattice model addressing station coupling strength during failures. This model aims to explore the spread of failures across coupled multimodal transit networks, identifying the paths and intensity of cascading failures between different public transport modes. It also examines the impacts of station coupling asymmetry, resulting from transportation efficiency and operation modes of different transit systems on cascading failures. The proposed model is then applied to the metro-bus coupled networks of Shenzhen, China. The results indicate that cascading failures on metro network would be alleviated when coupled with bus network. However, cascading failures are magnified on bus network when coupled with metro network. On the metro-bus coupled networks, failures of stations/stops with higher station coupling strength would cause more serious cascading failures than those of failures of important stations or stops on single network. In addition, the spread speed of cascading failures on metro-bus coupled networks depends largely on the number of failed metro stations. Findings of this work would offer valuable insights for the planning of robust metro-bus coupled systems and efficient emergency responses to avoid large-scale network failures.
{"title":"Cascading Failures on Multimodal Public Transportation Networks: The Role of Station Coupling Strength","authors":"Jing Li;Qing-Chang Lu;Peng-Cheng Xu;Shixin Wang;Chi Xie","doi":"10.1109/TITS.2024.3450019","DOIUrl":"10.1109/TITS.2024.3450019","url":null,"abstract":"While many studies explore cascading failures on single transit network, most of them fail to interpret the spread of failures between multimodal public transportation systems. Relevant research tends to measure station coupling strength under normal conditions, but this strength would change due to the variations of network topology, transportation, and travel characteristics under cascading failures. To address the above issues, this study proposes a multimodal coupled map lattice model addressing station coupling strength during failures. This model aims to explore the spread of failures across coupled multimodal transit networks, identifying the paths and intensity of cascading failures between different public transport modes. It also examines the impacts of station coupling asymmetry, resulting from transportation efficiency and operation modes of different transit systems on cascading failures. The proposed model is then applied to the metro-bus coupled networks of Shenzhen, China. The results indicate that cascading failures on metro network would be alleviated when coupled with bus network. However, cascading failures are magnified on bus network when coupled with metro network. On the metro-bus coupled networks, failures of stations/stops with higher station coupling strength would cause more serious cascading failures than those of failures of important stations or stops on single network. In addition, the spread speed of cascading failures on metro-bus coupled networks depends largely on the number of failed metro stations. Findings of this work would offer valuable insights for the planning of robust metro-bus coupled systems and efficient emergency responses to avoid large-scale network failures.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 11","pages":"17187-17199"},"PeriodicalIF":7.9,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142220424","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：