A large number of expressway traffic accident information in the traffic management information system cannot be accurately located on the map due to the lack of XY coordinate information in the data acquisition process. This paper put forward a method to realize the expressway accidents' rapidly positioning, map-matching and verification based on mileage pile, other accident collection data items and GIS road map data, providing the accurate data source for strengthening the ability of accident spatial-temporal visualization analysis, which can help the traffic management department improve accident prevention capabilities.
{"title":"Research on the Map-matching and Spatial-temporal Visualization of Expressway Traffic Accident Information","authors":"Aifen Fang, Xuan Peng, Jianning Zhou, Lihu Tang","doi":"10.1109/ICITE.2018.8492572","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492572","url":null,"abstract":"A large number of expressway traffic accident information in the traffic management information system cannot be accurately located on the map due to the lack of XY coordinate information in the data acquisition process. This paper put forward a method to realize the expressway accidents' rapidly positioning, map-matching and verification based on mileage pile, other accident collection data items and GIS road map data, providing the accurate data source for strengthening the ability of accident spatial-temporal visualization analysis, which can help the traffic management department improve accident prevention capabilities.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115036638","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}
In order to reduce ship collision and promote the safety of navigation. We investigate the fuzzy relational between various factors and the timing of collision avoidance of ships combined with the collision risk, and a method for determining the timing of ship collision avoidance is proposed. Through expert investigation, the main influencing factors and the weight of each factor are determined, and the judgement matrix model for calculating the time of collision avoidance is established. MV YuPeng is selected as an example to do the simulation of collision avoidance action in a typical case, then the simulation results are compared with the avoidance scheme determined by experts. The results show that the collision avoidance action determined by the evaluation model of the method is close to the expert's decision.
{"title":"Ship Collision Avoidance Timing Based on Subjective Collision Risk","authors":"Qin Ke, Bu Renxiang, Liu Yong, Ding Kaige","doi":"10.1109/ICITE.2018.8492546","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492546","url":null,"abstract":"In order to reduce ship collision and promote the safety of navigation. We investigate the fuzzy relational between various factors and the timing of collision avoidance of ships combined with the collision risk, and a method for determining the timing of ship collision avoidance is proposed. Through expert investigation, the main influencing factors and the weight of each factor are determined, and the judgement matrix model for calculating the time of collision avoidance is established. MV YuPeng is selected as an example to do the simulation of collision avoidance action in a typical case, then the simulation results are compared with the avoidance scheme determined by experts. The results show that the collision avoidance action determined by the evaluation model of the method is close to the expert's decision.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115077450","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}
In urban areas, the efficiency of traffic flows largely depends on signal operation and expansion of the existing signal infrastructure is not feasible due to spatial, economic and environmental constraints. In this paper, we address the problem of congestion around the road intersections. We developed our traffic simulator to optimally simulate various traffic scenarios, closely related to real-world traffic situations. We contend that adaptive real-time traffic optimization is the key to improving existing infrastructure's effectiveness by enabling the traffic control system to learn, adapt and evolve according to the environment it is exposed to. We put forward a vision-based, deep reinforcement learning approach based on a policy gradient algorithm to configure traffic light control policies. The algorithm is fed real-time traffic information and aims to optimize the flows of vehicles travelling through road intersections. Our preliminary test results demonstrate that, as compared to the traffic light control methodologies based on previously proposed models, configuration of traffic light policies through this novel method is extremely beneficial.
{"title":"Deep Reinforcement Learning for Autonomous Traffic Light Control","authors":"Deepeka Garg, Maria Chli, George Vogiatzis","doi":"10.1109/ICITE.2018.8492537","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492537","url":null,"abstract":"In urban areas, the efficiency of traffic flows largely depends on signal operation and expansion of the existing signal infrastructure is not feasible due to spatial, economic and environmental constraints. In this paper, we address the problem of congestion around the road intersections. We developed our traffic simulator to optimally simulate various traffic scenarios, closely related to real-world traffic situations. We contend that adaptive real-time traffic optimization is the key to improving existing infrastructure's effectiveness by enabling the traffic control system to learn, adapt and evolve according to the environment it is exposed to. We put forward a vision-based, deep reinforcement learning approach based on a policy gradient algorithm to configure traffic light control policies. The algorithm is fed real-time traffic information and aims to optimize the flows of vehicles travelling through road intersections. Our preliminary test results demonstrate that, as compared to the traffic light control methodologies based on previously proposed models, configuration of traffic light policies through this novel method is extremely beneficial.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128310700","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}
Metro is a common kind of rail transit system. Metro transfer station is an important node of rail transit network. In China, metro transfer station is always a limited space with crowded passengers. Currently, Intelligent Transport System and Advanced Public Transportation System have been applied to metro operation and management, but conflicts of passengers remain a problem and passenger waiting time is still very long. This paper deals with metro passenger transfer problem through coordination of different metro lines. Metro transfer optimization models are established including three scenarios: 1) single transfer station converged by two metro lines with the same scheduling plan; 2) single transfer station converged by two metro lines with different scheduling plans; 3) multiple transfer stations converged by two metro lines with different scheduling plans. All these scenarios suppose that transfer of passengers takes place in the same platform. Numerical examples are designed to validate the models. The results show that the models in this paper can provide coordination scheme of different metro lines to alleviate passenger conflicts and reduce passenger waiting time in transfer station.
{"title":"Coordination of Metro Lines in Transfer Station Considering Passengers' Conflicts and Waiting Time","authors":"S. Wan, Zhen Yang, Ying Shi, Yizhong Zhang, Qi Li, Yaning Geng","doi":"10.1109/ICITE.2018.8492647","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492647","url":null,"abstract":"Metro is a common kind of rail transit system. Metro transfer station is an important node of rail transit network. In China, metro transfer station is always a limited space with crowded passengers. Currently, Intelligent Transport System and Advanced Public Transportation System have been applied to metro operation and management, but conflicts of passengers remain a problem and passenger waiting time is still very long. This paper deals with metro passenger transfer problem through coordination of different metro lines. Metro transfer optimization models are established including three scenarios: 1) single transfer station converged by two metro lines with the same scheduling plan; 2) single transfer station converged by two metro lines with different scheduling plans; 3) multiple transfer stations converged by two metro lines with different scheduling plans. All these scenarios suppose that transfer of passengers takes place in the same platform. Numerical examples are designed to validate the models. The results show that the models in this paper can provide coordination scheme of different metro lines to alleviate passenger conflicts and reduce passenger waiting time in transfer station.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125242188","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}
Secondary international hub airports in China have become rising stars. Especially after 13th -Five-Year Plan, a positive policy launched by Civil Aviation Administration of China(CAAC), ten leading international hub airports are assigned officially, which seven of them are secondary hub airports. The decision is hoping these airports can play a pivotal role in connecting other regions worldwide based on their respective geographical advantages. So we want to make sense of such ten airports whether each airport has meet its role function, or having room for promotion. Applying QSI model, we do the analysis of transfer competition from China to other regions and backward through these hubs. The results show that the secondary international hub airports in China still needs to make great progress if they want to be better.
{"title":"QSI Models to Analyse the Competitiveness of China Leading Hub Airports","authors":"Fu Cong, Guo Tianwei","doi":"10.1109/ICITE.2018.8492577","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492577","url":null,"abstract":"Secondary international hub airports in China have become rising stars. Especially after 13th -Five-Year Plan, a positive policy launched by Civil Aviation Administration of China(CAAC), ten leading international hub airports are assigned officially, which seven of them are secondary hub airports. The decision is hoping these airports can play a pivotal role in connecting other regions worldwide based on their respective geographical advantages. So we want to make sense of such ten airports whether each airport has meet its role function, or having room for promotion. Applying QSI model, we do the analysis of transfer competition from China to other regions and backward through these hubs. The results show that the secondary international hub airports in China still needs to make great progress if they want to be better.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133327835","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}
Traffic congestion and collision problems had been focused widely by transportation researchers. Various traffic management strategies such as Variable Speed Limit (VSL), ramp metering (RM), etc., have been deployed to mitigate traffic congestion and collision. However, most previous studies focused on the impacts of VSL or RM control separately. Therefore, in this study, a model predictive integrated VSL and RM control strategy based on collision probability optimization was proposed. The proposed control strategy predicts future traffic states and collision probability, and considers the optimum VSL and RM input simultaneously by minimizing collision probability. To quantify the safety and mobility impact, the proposed integrated control was implemented in microscopic simulation and compared with VSL control, RM control and without any control scenario respectively. The results indicate that the integrated VSL and RM control strategy can improve safety by approximately 41% and mobility by approximately 13%. In conclusion, the proposed integrated VSL and RM control strategy was better than VSL control strategy and RM control strategy independently.
{"title":"Integrated Variable Speed Limit (VSL) and Ramp Metering (RM) Control Strategy Based on Optimal Collision Probability Prediction","authors":"Dehua Wu, Jia Wei Chen","doi":"10.1109/ICITE.2018.8492595","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492595","url":null,"abstract":"Traffic congestion and collision problems had been focused widely by transportation researchers. Various traffic management strategies such as Variable Speed Limit (VSL), ramp metering (RM), etc., have been deployed to mitigate traffic congestion and collision. However, most previous studies focused on the impacts of VSL or RM control separately. Therefore, in this study, a model predictive integrated VSL and RM control strategy based on collision probability optimization was proposed. The proposed control strategy predicts future traffic states and collision probability, and considers the optimum VSL and RM input simultaneously by minimizing collision probability. To quantify the safety and mobility impact, the proposed integrated control was implemented in microscopic simulation and compared with VSL control, RM control and without any control scenario respectively. The results indicate that the integrated VSL and RM control strategy can improve safety by approximately 41% and mobility by approximately 13%. In conclusion, the proposed integrated VSL and RM control strategy was better than VSL control strategy and RM control strategy independently.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114547699","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}
The identification of critical links is of great significance for the study of the structure and function of road networks and is also beneficial to corresponding traffic planning and management. From the perspective of the impact caused by the link failure on the overall performance, this paper studied the probability of the link failure and the impact on the road network topology and traffic redistribution after the links degradation, and evaluated the change of network efficiency and the travel time. The weight of the impact of the two indicators were calculated by the Principal Component Analysis(PCA). On this basis, the evaluation model of the links failure consequence and the link criticality recognition model were established. A small-sized road network enclosed by arterial roads, secondary roads and bypass in Xiao Shan District was selected as a case to identify the criticality of the road section. The Betweenness of the link was used as a comparative analysis indicator with the importance degree. It is found out that the link with larger value of Betweenness have a higher importance degree, which confirmed the rationality and reliability of the model and algorithm.
{"title":"Identification of Critical Links Based on the Failure Consequence Evaluation","authors":"Jian Sun, Q. Xiang","doi":"10.1109/ICITE.2018.8492704","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492704","url":null,"abstract":"The identification of critical links is of great significance for the study of the structure and function of road networks and is also beneficial to corresponding traffic planning and management. From the perspective of the impact caused by the link failure on the overall performance, this paper studied the probability of the link failure and the impact on the road network topology and traffic redistribution after the links degradation, and evaluated the change of network efficiency and the travel time. The weight of the impact of the two indicators were calculated by the Principal Component Analysis(PCA). On this basis, the evaluation model of the links failure consequence and the link criticality recognition model were established. A small-sized road network enclosed by arterial roads, secondary roads and bypass in Xiao Shan District was selected as a case to identify the criticality of the road section. The Betweenness of the link was used as a comparative analysis indicator with the importance degree. It is found out that the link with larger value of Betweenness have a higher importance degree, which confirmed the rationality and reliability of the model and algorithm.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"625 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123638502","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}
Evaluating the evacuation capacity of metro station under emergencies such as fires, as well as improving the emergency protection capability of rail transit system, is an important part of rail transit operation management. Based on the analysis of the impact of different factors on passenger's behavior under fire evacuation in metro station, this study models the facilities in metro station including gates, stairs, passageways, entrances and exits, and simulates the process of fire spread and the passenger evacuation scenarios by the model of cellular automata. A case study is brought out to illustrate the impact of different factors on evacuation capacity and evaluate the rationality of the station layout. The simulation result can provide basis for reconstruction of station facilities and layout design of the station.
{"title":"Simulation of Fire Emergency Evacuation in Metro Station Based on Cellular Automata","authors":"Xiongfei Zhang, Qi Zhong, Yaqian Li, Wei Li, Q. Luo","doi":"10.1109/ICITE.2018.8492555","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492555","url":null,"abstract":"Evaluating the evacuation capacity of metro station under emergencies such as fires, as well as improving the emergency protection capability of rail transit system, is an important part of rail transit operation management. Based on the analysis of the impact of different factors on passenger's behavior under fire evacuation in metro station, this study models the facilities in metro station including gates, stairs, passageways, entrances and exits, and simulates the process of fire spread and the passenger evacuation scenarios by the model of cellular automata. A case study is brought out to illustrate the impact of different factors on evacuation capacity and evaluate the rationality of the station layout. The simulation result can provide basis for reconstruction of station facilities and layout design of the station.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125448441","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}
This paper describes a method for automated detection of temporary cars in Mobile LiDAR point clouds. It consists of a segment-based classification of static cars and a comparison of data from two sensors to identify moving cars. Two segmentation methods are used to extract the ground and group the above-ground points into objects. From each segmented object a number of features are extracted, and a classification strengthened by feature selection is performed to classify temporary cars. We evaluate the performance of two different classifiers trained with a training set including 117 temporary cars, and show classification accuracies of up to 92%. We also investigate a method for identifying moving cars based on the distance between corresponding segments in the point clouds captured by the two scanning sensors, and report an overall accuracy of 61%.
{"title":"Detection of Cars in Mobile Lidar Point Clouds","authors":"Guorui Li, X. Fang, K. Khoshelham, S. O. Elberink","doi":"10.1109/ICITE.2018.8492695","DOIUrl":"https://doi.org/10.1109/ICITE.2018.8492695","url":null,"abstract":"This paper describes a method for automated detection of temporary cars in Mobile LiDAR point clouds. It consists of a segment-based classification of static cars and a comparison of data from two sensors to identify moving cars. Two segmentation methods are used to extract the ground and group the above-ground points into objects. From each segmented object a number of features are extracted, and a classification strengthened by feature selection is performed to classify temporary cars. We evaluate the performance of two different classifiers trained with a training set including 117 temporary cars, and show classification accuracies of up to 92%. We also investigate a method for identifying moving cars based on the distance between corresponding segments in the point clouds captured by the two scanning sensors, and report an overall accuracy of 61%.","PeriodicalId":336951,"journal":{"name":"2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126280836","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：