Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917277
Yigu Liu, Long Yu, Kaiyi Qian
Achieving accurate fault precaution of metro overhead contact system (OCS) is of great significance for the reliability of metro system. However, the current metro maintenance strategies generally adopt the idea of condition monitoring and fault maintenance, which cannot achieve real preventive maintenance. In this paper, we propose a fault precaution model for metro OCS which mines fault sequential patterns from historical fault data. As a case study, we analyzed the historical fault data of a city in south China and formed a fault relational network out of it. At last, detailed process of precaution suggestions generation is given based on the analysis results.
{"title":"A Fault Precaution Model based on Fault Sequential Patterns for Metro Overhead Contact System","authors":"Yigu Liu, Long Yu, Kaiyi Qian","doi":"10.1109/ITSC.2019.8917277","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917277","url":null,"abstract":"Achieving accurate fault precaution of metro overhead contact system (OCS) is of great significance for the reliability of metro system. However, the current metro maintenance strategies generally adopt the idea of condition monitoring and fault maintenance, which cannot achieve real preventive maintenance. In this paper, we propose a fault precaution model for metro OCS which mines fault sequential patterns from historical fault data. As a case study, we analyzed the historical fault data of a city in south China and formed a fault relational network out of it. At last, detailed process of precaution suggestions generation is given based on the analysis results.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"48 1","pages":"394-398"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85199562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917259
Rafael Mena Yedra, J. Casas, Ricard Gavaldà
Efficient estimation of local traffic states from fundamental diagram at each detection site in urban and freeway networks is crucial for many real-time traffic management applications. Usually, these traffic states are inferred from the bivariate relationship between traffic flow and density using a deterministic approach. However, due to traffic congestion and position of detection sites especially in urban networks, this relation is highly scattered making these methods not suitable to handle the associated uncertainty in the process. We propose a probabilistic model that allows the inclusion of prior knowledge on traffic states and part of their relative parametrization according to the expert user’s judgment. The model is formulated in a Bayesian framework where we also introduce several constraints as per the fundamental diagram shape to solve the common problem of identifiability in this kind of generative models used to estimate latent variables. Derived probability distributions can be efficiently updated in real-time with new data observations. The model performance has been evaluated in three networks: M4 Western Motorway in Sydney, and urban city centers of Santander and Leicester. Results demonstrate the robustness of our approach to infer traffic states even with low data availability in some parts of the fundamental diagram.
{"title":"Probabilistic model for robust traffic state identification in urban networks","authors":"Rafael Mena Yedra, J. Casas, Ricard Gavaldà","doi":"10.1109/ITSC.2019.8917259","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917259","url":null,"abstract":"Efficient estimation of local traffic states from fundamental diagram at each detection site in urban and freeway networks is crucial for many real-time traffic management applications. Usually, these traffic states are inferred from the bivariate relationship between traffic flow and density using a deterministic approach. However, due to traffic congestion and position of detection sites especially in urban networks, this relation is highly scattered making these methods not suitable to handle the associated uncertainty in the process. We propose a probabilistic model that allows the inclusion of prior knowledge on traffic states and part of their relative parametrization according to the expert user’s judgment. The model is formulated in a Bayesian framework where we also introduce several constraints as per the fundamental diagram shape to solve the common problem of identifiability in this kind of generative models used to estimate latent variables. Derived probability distributions can be efficiently updated in real-time with new data observations. The model performance has been evaluated in three networks: M4 Western Motorway in Sydney, and urban city centers of Santander and Leicester. Results demonstrate the robustness of our approach to infer traffic states even with low data availability in some parts of the fundamental diagram.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"23 1","pages":"1934-1940"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76663452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917206
P. Damon, M. Fouka, H. Hadj-Abdelkader, Hichem Arioui
In this paper, we investigate a vision-based approach for online lane change prediction and detection dedicated Powered Two-Wheeled Vehicles. The approach is composed of two steps. First, the road geometry (clothoid model) and the motorcycle position with respect to the road markers are deduced based an inverse perspective mapping algorithm. The relative position is represented by the vehicle lateral displacement and heading estimated by means of an Inertial Measurement Unit and a monocular camera. The second step consists of predicting the Lane Crossing Point which allows to predict the distance and time before the motorcycle crosses the lane. The algorithm is achieved without the use of any steering sensor.To assess the effectiveness of the proposed approach, the estimation and the prediction schemes are validated on the BikeSim framework. To this end, two scenarios are discussed : 1- straight road with non-zero relative heading, and 2- curved road and circular vehicle trajectory.
{"title":"Vision-Based Lane Crossing Point Tracking for Motorcycles","authors":"P. Damon, M. Fouka, H. Hadj-Abdelkader, Hichem Arioui","doi":"10.1109/ITSC.2019.8917206","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917206","url":null,"abstract":"In this paper, we investigate a vision-based approach for online lane change prediction and detection dedicated Powered Two-Wheeled Vehicles. The approach is composed of two steps. First, the road geometry (clothoid model) and the motorcycle position with respect to the road markers are deduced based an inverse perspective mapping algorithm. The relative position is represented by the vehicle lateral displacement and heading estimated by means of an Inertial Measurement Unit and a monocular camera. The second step consists of predicting the Lane Crossing Point which allows to predict the distance and time before the motorcycle crosses the lane. The algorithm is achieved without the use of any steering sensor.To assess the effectiveness of the proposed approach, the estimation and the prediction schemes are validated on the BikeSim framework. To this end, two scenarios are discussed : 1- straight road with non-zero relative heading, and 2- curved road and circular vehicle trajectory.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"99 1","pages":"3399-3404"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76725438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917530
Andreas Hadjigeorgiou, S. Timotheou
Connected and autonomous vehicles (CAVs) have the potential to disrupt road transportation. CAVs provide several attractive features, such as seamless connectivity and fine-grained control, which can be exploited to improve the efficiency of traffic networks. In this work, the problem of CAV coordination at an unsignalized intersection crossing is considered, aiming to select the CAV trajectories that minimize fuel consumption and/or travel time. Nonetheless, the minimization of travel time implies high fuel consumption and vice-versa. For this reason, this work considers the problem of simultaneously optimizing the fuel consumption-travel time trade-off for a set of CAVs that are expected to arrive at the intersection within a specific time-window. As the resulting problem is non-convex, we construct a Mixed-Integer Programming formulation that provides tight lower and upper bounds. We also develop a heuristic convex-concave procedure that yields fast, high-quality solutions. Simulation results validate the effectiveness of the proposed approaches and highlight the importance of optimizing the fuel consumption-travel time trade-off, as small compromises in travel time produce significant fuel savings.
{"title":"Optimizing the trade-off between fuel consumption and travel time in an unsignalized autonomous intersection crossing","authors":"Andreas Hadjigeorgiou, S. Timotheou","doi":"10.1109/ITSC.2019.8917530","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917530","url":null,"abstract":"Connected and autonomous vehicles (CAVs) have the potential to disrupt road transportation. CAVs provide several attractive features, such as seamless connectivity and fine-grained control, which can be exploited to improve the efficiency of traffic networks. In this work, the problem of CAV coordination at an unsignalized intersection crossing is considered, aiming to select the CAV trajectories that minimize fuel consumption and/or travel time. Nonetheless, the minimization of travel time implies high fuel consumption and vice-versa. For this reason, this work considers the problem of simultaneously optimizing the fuel consumption-travel time trade-off for a set of CAVs that are expected to arrive at the intersection within a specific time-window. As the resulting problem is non-convex, we construct a Mixed-Integer Programming formulation that provides tight lower and upper bounds. We also develop a heuristic convex-concave procedure that yields fast, high-quality solutions. Simulation results validate the effectiveness of the proposed approaches and highlight the importance of optimizing the fuel consumption-travel time trade-off, as small compromises in travel time produce significant fuel savings.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"24 1","pages":"2443-2448"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76862561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917464
Daniel Hess, Ray Lattarulo, Joshué Pérez, T. Hesse, F. Köster
When the number of automated vehicles (AVs) deployed in public traffic reaches a significant level, their form of interaction with other AVs, human controlled vehicles and non-motorized participants will impact traffic overall safety and efficiency. While many studies have approached impact analysis on the side of efficiency and via simulation, we here elaborate on practically applicable methods for safe cooperation of AVs from the perspective of life-size experimental platforms. In a previous publication, a message set for negotiation of such a cooperation has been proposed, space-time reservation procedure (STRP), which is compatible with the investigated verification approach. This publication follows up by providing results and analysis of test drives with two cooperating, automated vehicles with differing software and hardware architectures. The reservation messages are employed to negotiate a cooperative lane change via Vehicle-to-Vehicle radio in an urban scenario with non-trivial road-geometry. The applicability of the distributed cooperation scheme to real-world conditions is demonstrated.
{"title":"Negotiation of Cooperative Maneuvers for Automated Vehicles: Experimental Results","authors":"Daniel Hess, Ray Lattarulo, Joshué Pérez, T. Hesse, F. Köster","doi":"10.1109/ITSC.2019.8917464","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917464","url":null,"abstract":"When the number of automated vehicles (AVs) deployed in public traffic reaches a significant level, their form of interaction with other AVs, human controlled vehicles and non-motorized participants will impact traffic overall safety and efficiency. While many studies have approached impact analysis on the side of efficiency and via simulation, we here elaborate on practically applicable methods for safe cooperation of AVs from the perspective of life-size experimental platforms. In a previous publication, a message set for negotiation of such a cooperation has been proposed, space-time reservation procedure (STRP), which is compatible with the investigated verification approach. This publication follows up by providing results and analysis of test drives with two cooperating, automated vehicles with differing software and hardware architectures. The reservation messages are employed to negotiate a cooperative lane change via Vehicle-to-Vehicle radio in an urban scenario with non-trivial road-geometry. The applicability of the distributed cooperation scheme to real-world conditions is demonstrated.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"286 1","pages":"1545-1551"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76894770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917400
Hideaki Uchida, H. Fujii, S. Yoshimura
In recent years, the introduction of electric vehicles (EVs) has become increasingly desirable from an environmental perspective. However, it is important to develop suitable charging equipment and infrastructure, as EVs tend to have shorter cruising distances than gasoline-powered vehicles. Various data-driven methods have been proposed for the placement of charging stations (CSs). To date, however, there have been few simulation-driven approaches that can take account of the microscale interactions among vehicles. Therefore, in this paper, we propose an efficient placement method based on multi-agent traffic simulations with an improved scoring function. In addition, as the number of CSs increase in proportion to the spread of EVs, we solve a multiple location design problem formulated as a combinatorial optimization technique. Numerical experiments were conducted on a realistic network in the central part of Wakayama Prefecture in Japan, and it was shown that the proposed method could improve the performance indicator of CS placement compared with the conventional method. Furthermore, the scenario of multiple CS installations at one time demonstrated that good combinations could be obtained.
{"title":"Combinatorial Optimal Location Design of Charging Stations based on Multi-agent Simulation","authors":"Hideaki Uchida, H. Fujii, S. Yoshimura","doi":"10.1109/ITSC.2019.8917400","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917400","url":null,"abstract":"In recent years, the introduction of electric vehicles (EVs) has become increasingly desirable from an environmental perspective. However, it is important to develop suitable charging equipment and infrastructure, as EVs tend to have shorter cruising distances than gasoline-powered vehicles. Various data-driven methods have been proposed for the placement of charging stations (CSs). To date, however, there have been few simulation-driven approaches that can take account of the microscale interactions among vehicles. Therefore, in this paper, we propose an efficient placement method based on multi-agent traffic simulations with an improved scoring function. In addition, as the number of CSs increase in proportion to the spread of EVs, we solve a multiple location design problem formulated as a combinatorial optimization technique. Numerical experiments were conducted on a realistic network in the central part of Wakayama Prefecture in Japan, and it was shown that the proposed method could improve the performance indicator of CS placement compared with the conventional method. Furthermore, the scenario of multiple CS installations at one time demonstrated that good combinations could be obtained.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"235 2 1","pages":"467-473"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77015691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917461
Maximilian Naumann, Hendrik Königshof, C. Stiller
While lane change behavior of human drivers has already been widely investigated, concepts and algorithms to plan lane changes for automated vehicles become necessary through the progress of automated driving. In this paper, we present an approach for safe and smooth lane changes in dense traffic, that consider both the cooperation of humans but also the increased need for safety compared to lane changes performed by human drivers. This real time capable approach is based on path-velocity decomposition, the intelligent driver model, a model compliance check for human machine cooperation and the concept of responsibility sensitive safety. The work is targeted towards mandatory lane changes determined by an upstream routing module, but is also applicable to optional lane changes.
{"title":"Provably Safe and Smooth Lane Changes in Mixed Trafic","authors":"Maximilian Naumann, Hendrik Königshof, C. Stiller","doi":"10.1109/ITSC.2019.8917461","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917461","url":null,"abstract":"While lane change behavior of human drivers has already been widely investigated, concepts and algorithms to plan lane changes for automated vehicles become necessary through the progress of automated driving. In this paper, we present an approach for safe and smooth lane changes in dense traffic, that consider both the cooperation of humans but also the increased need for safety compared to lane changes performed by human drivers. This real time capable approach is based on path-velocity decomposition, the intelligent driver model, a model compliance check for human machine cooperation and the concept of responsibility sensitive safety. The work is targeted towards mandatory lane changes determined by an upstream routing module, but is also applicable to optional lane changes.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"68 1","pages":"1832-1837"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85797991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917493
Soheil Mohamad Alizadeh Shabestary, B. Abdulhai
Population growth around the world has led to a challenging level of demand for transportation. Constructing new infrastructure is not always the first option due to spatial, financial, and environmental constrains. Public transit is often considered to be a more affordable and sustainable option, as one transit vehicle can carry significantly higher number of passengers compared to regular vehicles. In urban cores, a considerable portion of travel time is spent waiting at traffic signals. Transit Signal Priority (TSP) methods has emerged over the years to reduce transit delays at traffic signals. Traffic signals are often optimized for regular traffic and TSP systems are added to adjust the background signal timing plans to provide priority for transit vehicles. Therefore, these two modes seem to constantly fight for the green signal, and improving one’s travel time leads to deterioration of the other’s. In this research we introduce a new multimodal traffic signal controller that explicitly considers both regular and transit vehicles and optimizes the throughput of people rather than vehicles, irrespective of what mode they are on. For this purpose, we use deep reinforcement learning to develop and test a Multimodal iNtelligent Deep (MiND) traffic signal controller.
{"title":"Multimodal iNtelligent Deep (MiND) Traffic Signal Controller","authors":"Soheil Mohamad Alizadeh Shabestary, B. Abdulhai","doi":"10.1109/ITSC.2019.8917493","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917493","url":null,"abstract":"Population growth around the world has led to a challenging level of demand for transportation. Constructing new infrastructure is not always the first option due to spatial, financial, and environmental constrains. Public transit is often considered to be a more affordable and sustainable option, as one transit vehicle can carry significantly higher number of passengers compared to regular vehicles. In urban cores, a considerable portion of travel time is spent waiting at traffic signals. Transit Signal Priority (TSP) methods has emerged over the years to reduce transit delays at traffic signals. Traffic signals are often optimized for regular traffic and TSP systems are added to adjust the background signal timing plans to provide priority for transit vehicles. Therefore, these two modes seem to constantly fight for the green signal, and improving one’s travel time leads to deterioration of the other’s. In this research we introduce a new multimodal traffic signal controller that explicitly considers both regular and transit vehicles and optimizes the throughput of people rather than vehicles, irrespective of what mode they are on. For this purpose, we use deep reinforcement learning to develop and test a Multimodal iNtelligent Deep (MiND) traffic signal controller.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"107 1","pages":"4532-4539"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84171803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917095
Mingchang Xu, Yugong Luo, Gang Yang, W. Kong, Keqiang Li
Cooperative lane-change has received considerable attention since the rapid development of vehicle-to-vehicle communication and intelligent transportation system. In this paper a dynamic cooperative lane-change maneuver is proposed, aiming to maintain safety both on the early stage of lane-change maneuver and during the lane-change process. The variable states of surrounding vehicles are taken into consideration. To fit this condition, an improved minimum safety spacing (MSS) model is established, which can calculate safe distance between every two vehicles for each time point during the lane-change process. Based on the calculation results of MSS model, a dynamic lane-change trajectory planning and re-planning method is proposed to obtain safe trajectories and avoid collisions. To verify the validity of the maneuver, some typical lane change scenarios as well as the influence of communication are simulated. The results indicate that the proposed maneuver can achieve efficient and safe cooperative lane-change behavior under complicated conditions when there is no speed limit on the surrounding vehicles.
{"title":"Dynamic Cooperative Automated Lane-Change Maneuver Based on Minimum Safety Spacing Model*","authors":"Mingchang Xu, Yugong Luo, Gang Yang, W. Kong, Keqiang Li","doi":"10.1109/ITSC.2019.8917095","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917095","url":null,"abstract":"Cooperative lane-change has received considerable attention since the rapid development of vehicle-to-vehicle communication and intelligent transportation system. In this paper a dynamic cooperative lane-change maneuver is proposed, aiming to maintain safety both on the early stage of lane-change maneuver and during the lane-change process. The variable states of surrounding vehicles are taken into consideration. To fit this condition, an improved minimum safety spacing (MSS) model is established, which can calculate safe distance between every two vehicles for each time point during the lane-change process. Based on the calculation results of MSS model, a dynamic lane-change trajectory planning and re-planning method is proposed to obtain safe trajectories and avoid collisions. To verify the validity of the maneuver, some typical lane change scenarios as well as the influence of communication are simulated. The results indicate that the proposed maneuver can achieve efficient and safe cooperative lane-change behavior under complicated conditions when there is no speed limit on the surrounding vehicles.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"26 1","pages":"1537-1544"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78310258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8917523
Bin Hu, Kun Xie, Haipeng Cui, Hangfei Lin
Bus speed modeling is essential for effective operation and management of public transit systems. Space-time interaction patterns are being ignored when modeling bus speed, and this would lead to biased statistical inferences. This paper proposed a spatiotemporal Bayesian model to characterize space-time interaction patterns among road segments using large-scale bus GPS data and to further develop the bus speed prediction model based on that. Results showed that a type II interaction pattern existed in the data, and the mean absolute percentage errors (MAPEs) of the test sets were 11.3% for the AM peak and 22.5% for the PM peak. Results were further compared with existing work. It was found that the proposed model presented a superior predictive performance while keeping the interpretability of contributing factors and space-time interaction patterns.
{"title":"A Bayesian Spatiotemporal Approach for Bus Speed Modeling*","authors":"Bin Hu, Kun Xie, Haipeng Cui, Hangfei Lin","doi":"10.1109/ITSC.2019.8917523","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917523","url":null,"abstract":"Bus speed modeling is essential for effective operation and management of public transit systems. Space-time interaction patterns are being ignored when modeling bus speed, and this would lead to biased statistical inferences. This paper proposed a spatiotemporal Bayesian model to characterize space-time interaction patterns among road segments using large-scale bus GPS data and to further develop the bus speed prediction model based on that. Results showed that a type II interaction pattern existed in the data, and the mean absolute percentage errors (MAPEs) of the test sets were 11.3% for the AM peak and 22.5% for the PM peak. Results were further compared with existing work. It was found that the proposed model presented a superior predictive performance while keeping the interpretability of contributing factors and space-time interaction patterns.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"22 1","pages":"497-502"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78546367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：