Pub Date : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231452
Liqiao Ning, Binglei Xie, Xi Zhang, Wenkai Xu
This study contributes to the vulnerability analysis of urban rail transit network under line interruption operation. Based on the complex network theory, the urban rail transit network model is built to provide an abstract description of the network structure. Considering the interruption influences, the measurement indicators of network vulnerability are developed to quantify and measure the influence of interruption from the perspective of both the topology structure and passenger service. Then, a vulnerability analysis framework is established to implement a comprehensive analysis of network. Finally, a case study on Shenzhen metro network is conducted and results show that the passenger service network seems more resistant than the topology structure network.
{"title":"Vulnerability Analysis of Urban Rail Transit Network under Line Interruption Operation","authors":"Liqiao Ning, Binglei Xie, Xi Zhang, Wenkai Xu","doi":"10.1109/ICITE50838.2020.9231452","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231452","url":null,"abstract":"This study contributes to the vulnerability analysis of urban rail transit network under line interruption operation. Based on the complex network theory, the urban rail transit network model is built to provide an abstract description of the network structure. Considering the interruption influences, the measurement indicators of network vulnerability are developed to quantify and measure the influence of interruption from the perspective of both the topology structure and passenger service. Then, a vulnerability analysis framework is established to implement a comprehensive analysis of network. Finally, a case study on Shenzhen metro network is conducted and results show that the passenger service network seems more resistant than the topology structure network.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125496579","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231419
Yanyan Chen, Zeqian Jin, Chen Li
Trip purpose is vital to infer travel behavior and predict travel demand for transportation planning. Therefore, trip purpose prediction has been becoming an important field of research that can improve people's travel efficiency through travel information, such as travel mode, time, location and so on. However, there are a few challenges linked with collecting data via the surveys and the spatial complexity of human travel. To solve the above problems effectively, the study adopts GPS data and land use data and proposes a machine learning method and prediction model as forecasting process. The prediction model is used to automatically predict trip purpose, while the machine learning method is used to constantly updating the prediction model, based on surveys from participants. Compared with traditional models, the method can significantly improve destination prediction accuracy by dynamically updating. In addition, the estimation model is developed employing the Markov model, the structure of model can use for a short training period. Meanwhile, the research can apply to crowded place analysis or in trip distribution prediction, which shows a broad application in transportation planning and management.
{"title":"Trip Purpose Prediction Based on Hidden Markov Model with GPS and Land Use Data","authors":"Yanyan Chen, Zeqian Jin, Chen Li","doi":"10.1109/ICITE50838.2020.9231419","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231419","url":null,"abstract":"Trip purpose is vital to infer travel behavior and predict travel demand for transportation planning. Therefore, trip purpose prediction has been becoming an important field of research that can improve people's travel efficiency through travel information, such as travel mode, time, location and so on. However, there are a few challenges linked with collecting data via the surveys and the spatial complexity of human travel. To solve the above problems effectively, the study adopts GPS data and land use data and proposes a machine learning method and prediction model as forecasting process. The prediction model is used to automatically predict trip purpose, while the machine learning method is used to constantly updating the prediction model, based on surveys from participants. Compared with traditional models, the method can significantly improve destination prediction accuracy by dynamically updating. In addition, the estimation model is developed employing the Markov model, the structure of model can use for a short training period. Meanwhile, the research can apply to crowded place analysis or in trip distribution prediction, which shows a broad application in transportation planning and management.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116388582","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 solve the problem of poor real-time performance and low accuracy of a single detection target of common driver fatigue driving detection method based on facial features in practical applications, a fatigue driving detection method based on lightweight convolutional neural network is proposed. First, the driver's facial feature point data set is made through MTCNN (multi task convolutional neural network). Then the data set is used to train a lightweight convolutional neural network to detect the accurate feature point position of the eyes and mouth. Finally, the open and close state of the driver's eyes and mouth is judged based on the feature point coordinates. According to the open and closed state of the eyes and mouth of the continuous multi-frame image, the driver is judged to be in the state of fatigue. The experimental results show that the processing time of the single frame image by the algorithm is 23.3 millisecond; the single detection accuracy is up to 99.4%, and the detection accuracy of fatigue driving can reach 95%. The algorithm is better real-time performance and higher accuracy, so it has certain engineering significance and application prospects.
{"title":"Research on Fatigue Driving Detection Method Based on Lightweight Convolutional Neural Network","authors":"Xiaowei Xu, Changyan Liu, Xue-Jing Yu, Hao Xiong, Feng Qian","doi":"10.1109/ICITE50838.2020.9231511","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231511","url":null,"abstract":"In order to solve the problem of poor real-time performance and low accuracy of a single detection target of common driver fatigue driving detection method based on facial features in practical applications, a fatigue driving detection method based on lightweight convolutional neural network is proposed. First, the driver's facial feature point data set is made through MTCNN (multi task convolutional neural network). Then the data set is used to train a lightweight convolutional neural network to detect the accurate feature point position of the eyes and mouth. Finally, the open and close state of the driver's eyes and mouth is judged based on the feature point coordinates. According to the open and closed state of the eyes and mouth of the continuous multi-frame image, the driver is judged to be in the state of fatigue. The experimental results show that the processing time of the single frame image by the algorithm is 23.3 millisecond; the single detection accuracy is up to 99.4%, and the detection accuracy of fatigue driving can reach 95%. The algorithm is better real-time performance and higher accuracy, so it has certain engineering significance and application prospects.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132838371","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231477
Han Wang, Y. Yue
Efficient train platforming plans at high-speed railway stations are important for the station work organization. By defining four types of train technical operation chains and their corresponding occupation times of arrival-departure tracks, this paper proposes a multi-objective optimization model to simultaneously optimize the organized and balance use of station tracks. Based on dispatching principles, train movement constraints are constructed to avoid potential conflicts at congested high-speed railway stations. The multi-objective planning model is transformed into a single object model through min-max method and finally solved by The General Algebraic Modeling System (GAMS). The proposed method is tested in Xiong'an Station to generate track operation plans from 6:00am to 9:00am.
{"title":"Optimizing Train-Platforming Plans at Arrival-Departure Tracks of High-speed Railway Stations","authors":"Han Wang, Y. Yue","doi":"10.1109/ICITE50838.2020.9231477","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231477","url":null,"abstract":"Efficient train platforming plans at high-speed railway stations are important for the station work organization. By defining four types of train technical operation chains and their corresponding occupation times of arrival-departure tracks, this paper proposes a multi-objective optimization model to simultaneously optimize the organized and balance use of station tracks. Based on dispatching principles, train movement constraints are constructed to avoid potential conflicts at congested high-speed railway stations. The multi-objective planning model is transformed into a single object model through min-max method and finally solved by The General Algebraic Modeling System (GAMS). The proposed method is tested in Xiong'an Station to generate track operation plans from 6:00am to 9:00am.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125610343","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 problem of urban road congestion is the key to be solved urgently in China's urban traffic. To effectively predict it, this paper proposes a method for predicting urban road congestion based on the Spark platform parallel Gradient Boosting Decision Tree algorithm. First, the basic principle of GBDT algorithm is briefly introduced. Secondly, the GBDT algorithm based on the parallel design of the Spark big data platform is used to predict urban road congestion. Finally, through accuracy experiments and scalability experiments, the effectiveness of the algorithm and the performance of the algorithm under different numbers of nodes are verified in the Spark cluster. Experiments prove that the method proposed in this paper can effectively predict urban road congestion, reduce the running time, improve the prediction efficiency, and provide effective help for urban road management.
{"title":"Research on Prediction of Urban Road Congestion Based on Spark-GBDT","authors":"Xiao Bai, Yongxiang Feng, Leixiao Li, Liping Zhang","doi":"10.1109/ICITE50838.2020.9231416","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231416","url":null,"abstract":"The problem of urban road congestion is the key to be solved urgently in China's urban traffic. To effectively predict it, this paper proposes a method for predicting urban road congestion based on the Spark platform parallel Gradient Boosting Decision Tree algorithm. First, the basic principle of GBDT algorithm is briefly introduced. Secondly, the GBDT algorithm based on the parallel design of the Spark big data platform is used to predict urban road congestion. Finally, through accuracy experiments and scalability experiments, the effectiveness of the algorithm and the performance of the algorithm under different numbers of nodes are verified in the Spark cluster. Experiments prove that the method proposed in this paper can effectively predict urban road congestion, reduce the running time, improve the prediction efficiency, and provide effective help for urban road management.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131133918","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231446
Ye Li, W. Tian, Xin You, Kang Li, Jinhui Yuan, Xiaobo Chen, Linjie Pan
This paper applies a method to obtain the extrinsic calibration parameters between a Camera and a 3D-LiDAR using 3D point-to-point correspondences. We use a calibration board with ArUco marker as a reference to obtain features of interest in both sensor frames. Through a manual method which is easy to operate, the calibration board planar and edge will be extracted from the LiDAR point cloud by exploiting the geometry of the board. And then the vertices will be calculated by using nonlinear optimization. The corresponding vertices in the Camera image are detected by ArUco Marker API. Once we get the point-to-point correspondences, we use Kabsch algorithm to get the final rotation and transition. The calibration accuracy is demonstrated by evaluating it in real application scenarios.
{"title":"Application of 3D-LiDAR & Camera Extrinsic Calibration in Urban Rail Transit","authors":"Ye Li, W. Tian, Xin You, Kang Li, Jinhui Yuan, Xiaobo Chen, Linjie Pan","doi":"10.1109/ICITE50838.2020.9231446","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231446","url":null,"abstract":"This paper applies a method to obtain the extrinsic calibration parameters between a Camera and a 3D-LiDAR using 3D point-to-point correspondences. We use a calibration board with ArUco marker as a reference to obtain features of interest in both sensor frames. Through a manual method which is easy to operate, the calibration board planar and edge will be extracted from the LiDAR point cloud by exploiting the geometry of the board. And then the vertices will be calculated by using nonlinear optimization. The corresponding vertices in the Camera image are detected by ArUco Marker API. Once we get the point-to-point correspondences, we use Kabsch algorithm to get the final rotation and transition. The calibration accuracy is demonstrated by evaluating it in real application scenarios.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115751147","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231404
Jie Deng, Wei Zhao, Yifan Tan, Keli Huang, Haibo Zhang
With the continuously increasing popularity of the tourism in western mountainous areas, the travelling passenger volume leads to a higher entropy, leading to the instability and constant evolution, of local tourism accommodation system. Since the traffic accessibility is a crucial factor in tourists' choice of accommodation, the evolution of accommodation system must be affected by traffic lines. This article, based on the ArcGIS neighbor analysis, suggests a linear random aggregation dimension analytical method, which analyzes the aggregation characteristics of the accommodation industry affected by traffic lines in the mountainous tourism cities, combined with methods of symbolized geographic spatial data, buffer zone analysis, neighbor analysis provided by software ArcGIS. The results indicate: (1) the stay points in the urban area of Kangding City has self-organization evolution with a linear accumulation center of National Road 318. Its evolution is in a group mode and grows in leaps;(2) the distribution density of the stay points in the urban area of Luding County progressively increase from National Road 318 towards the surrounding hinterland, when the traffic lines do not have a central function.
{"title":"Research on the Spatial Distribution Characteristics of Traffic-accommodation in Mountain Tourism Cities","authors":"Jie Deng, Wei Zhao, Yifan Tan, Keli Huang, Haibo Zhang","doi":"10.1109/ICITE50838.2020.9231404","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231404","url":null,"abstract":"With the continuously increasing popularity of the tourism in western mountainous areas, the travelling passenger volume leads to a higher entropy, leading to the instability and constant evolution, of local tourism accommodation system. Since the traffic accessibility is a crucial factor in tourists' choice of accommodation, the evolution of accommodation system must be affected by traffic lines. This article, based on the ArcGIS neighbor analysis, suggests a linear random aggregation dimension analytical method, which analyzes the aggregation characteristics of the accommodation industry affected by traffic lines in the mountainous tourism cities, combined with methods of symbolized geographic spatial data, buffer zone analysis, neighbor analysis provided by software ArcGIS. The results indicate: (1) the stay points in the urban area of Kangding City has self-organization evolution with a linear accumulation center of National Road 318. Its evolution is in a group mode and grows in leaps;(2) the distribution density of the stay points in the urban area of Luding County progressively increase from National Road 318 towards the surrounding hinterland, when the traffic lines do not have a central function.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122452264","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231505
Bin Zhang, Y. Yue
In order to improve the market competitiveness of urban rail transit and make train timetables better serve passengers, the problem of train timetable optimization under time-varying passenger demand is studied. The cubic spline interpolation method is used to fit the passenger flow demand function, and then the obtained results are applied to the train timetable optimization model that minimizes the weighted sum of passenger waiting time, total train running time, and number of trains. Use simulated annealing algorithm to solve. Taking Xi'an Metro Line 2 as an example for analysis, the results show the feasibility of the model and algorithm.
{"title":"Optimal Design of Train Schedule of Urban Rail Transit Based on Time-varying Demand","authors":"Bin Zhang, Y. Yue","doi":"10.1109/ICITE50838.2020.9231505","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231505","url":null,"abstract":"In order to improve the market competitiveness of urban rail transit and make train timetables better serve passengers, the problem of train timetable optimization under time-varying passenger demand is studied. The cubic spline interpolation method is used to fit the passenger flow demand function, and then the obtained results are applied to the train timetable optimization model that minimizes the weighted sum of passenger waiting time, total train running time, and number of trains. Use simulated annealing algorithm to solve. Taking Xi'an Metro Line 2 as an example for analysis, the results show the feasibility of the model and algorithm.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"298 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127563431","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 : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231370
W. Guan, Xudong Zhou
With the development of computer industrial control technology, all-electronic interlocking system has become a main development direction of computer interlocking system in our country because of its richer system functions, larger control ranges, smaller volumes, simpler structures, more flexible configurations, and higher electronic levels. The intelligent control of wayside equipment in distributed all-electronic interlocking architecture will greatly improve the function,machine lerning of big data with artificial intelligence, control and maintenance level of wayside basic equipment of railway signaling, so as to fully realize the “revolutionary” improvement of wayside equipment that is still mainly used in the era of electric interlocking system at this stage. This paper summarizes the application scenarios of the all-electronic interlocking system and the industry's main requirements for operation and maintenance, then puts forward four stages and corresponding scenarios of the all-electronic interlocking system on intelligent operation and maintenance. Finally, the future development trend and opportunities of intelligent operation and maintenance in the signaling system are explained.
{"title":"The Influence of All-electronic Interlocking System on Intelligent Operation and Maintenance","authors":"W. Guan, Xudong Zhou","doi":"10.1109/ICITE50838.2020.9231370","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231370","url":null,"abstract":"With the development of computer industrial control technology, all-electronic interlocking system has become a main development direction of computer interlocking system in our country because of its richer system functions, larger control ranges, smaller volumes, simpler structures, more flexible configurations, and higher electronic levels. The intelligent control of wayside equipment in distributed all-electronic interlocking architecture will greatly improve the function,machine lerning of big data with artificial intelligence, control and maintenance level of wayside basic equipment of railway signaling, so as to fully realize the “revolutionary” improvement of wayside equipment that is still mainly used in the era of electric interlocking system at this stage. This paper summarizes the application scenarios of the all-electronic interlocking system and the industry's main requirements for operation and maintenance, then puts forward four stages and corresponding scenarios of the all-electronic interlocking system on intelligent operation and maintenance. Finally, the future development trend and opportunities of intelligent operation and maintenance in the signaling system are explained.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125724460","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：