Pub Date : 2020-09-01DOI: 10.1109/ICITE50838.2020.9231361
Xiaoxin Di, Xiangqian Li, L. Zhou, Wei Xiao, Y. Yue
In order to improve the construction level of highspeed railway business lines, ensure the quality status of highspeed rail facilities, reduce the risk of business line construction, rational evaluating the business line construction plan risk is an urgent research. This paper combines Analytic Hierarchy Process (AHP) with Bayesian network(BN) and adapts AHP to determine the weight of each indicator; Based on BN theory, constructs a probabilistic model of business line construction risk evaluation and calculates the probability of different risk factors as low, medium and high risk. Finally takes the Beijing Railway Bureau's business line as an example to conduct a comprehensive evaluation, and concludes that the overall risk factor of the project is at a medium risk level, and the evaluation results are in good agreement with the actual site, therefore indicating that this evaluation method is more comprehensive exhaustive than the existing evaluation methods, it has certain practical significance for the railway site construction plan.)
{"title":"Risk Evaluation of Railway Business Line Construction Plan Based on Analytic Hierarchy Process and Bayesian Network","authors":"Xiaoxin Di, Xiangqian Li, L. Zhou, Wei Xiao, Y. Yue","doi":"10.1109/ICITE50838.2020.9231361","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231361","url":null,"abstract":"In order to improve the construction level of highspeed railway business lines, ensure the quality status of highspeed rail facilities, reduce the risk of business line construction, rational evaluating the business line construction plan risk is an urgent research. This paper combines Analytic Hierarchy Process (AHP) with Bayesian network(BN) and adapts AHP to determine the weight of each indicator; Based on BN theory, constructs a probabilistic model of business line construction risk evaluation and calculates the probability of different risk factors as low, medium and high risk. Finally takes the Beijing Railway Bureau's business line as an example to conduct a comprehensive evaluation, and concludes that the overall risk factor of the project is at a medium risk level, and the evaluation results are in good agreement with the actual site, therefore indicating that this evaluation method is more comprehensive exhaustive than the existing evaluation methods, it has certain practical significance for the railway site construction plan.)","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"268 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":"122066930","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/ICITE50838.2020.9231346
Ruiqi Zhu, Huiyu Zhou
Rail transportation is the backbone of modern transportation. Accurate railway passenger flow forecasting can be applied to support transportation system management such as operation plan and route selection design. This paper proposes a hybrid linear + nonlinear time series analysis model, which uses the panel vector autoregression (PVAR) and neural network (NN) hybrid PVAR-NN prediction methods to predict passenger flow in the railway system. The proposed model combines the pros of both linear and non-linear model with easy-to-interpretation for stakeholders. The empirical analysis results further indicate that the proposed hybrid PVAR-NN approach performs with improved accuracy in forecasting the railway passenger flow.
{"title":"Railway Passenger Flow Forecast Based on Hybrid PVAR-NN Model","authors":"Ruiqi Zhu, Huiyu Zhou","doi":"10.1109/ICITE50838.2020.9231346","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231346","url":null,"abstract":"Rail transportation is the backbone of modern transportation. Accurate railway passenger flow forecasting can be applied to support transportation system management such as operation plan and route selection design. This paper proposes a hybrid linear + nonlinear time series analysis model, which uses the panel vector autoregression (PVAR) and neural network (NN) hybrid PVAR-NN prediction methods to predict passenger flow in the railway system. The proposed model combines the pros of both linear and non-linear model with easy-to-interpretation for stakeholders. The empirical analysis results further indicate that the proposed hybrid PVAR-NN approach performs with improved accuracy in forecasting the railway passenger flow.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"28 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":"130509835","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/ICITE50838.2020.9231438
Luji Huang
Railway Interlocking system is the most fundamental and important part of railway signaling system. It ensures the safety of train movement. With the development of railway signaling system, it has experienced three stages: mechanical interlocking system, relay interlocking system and computer-based interlocking system. On the basis of reviewing the history of railway signal development, this paper introduces the development of interlocking system and discusses the future development direction of railway interlocking system.
{"title":"The Past, Present and Future of Railway Interlocking System","authors":"Luji Huang","doi":"10.1109/ICITE50838.2020.9231438","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231438","url":null,"abstract":"Railway Interlocking system is the most fundamental and important part of railway signaling system. It ensures the safety of train movement. With the development of railway signaling system, it has experienced three stages: mechanical interlocking system, relay interlocking system and computer-based interlocking system. On the basis of reviewing the history of railway signal development, this paper introduces the development of interlocking system and discusses the future development direction of railway interlocking system.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"9 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":"129685785","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/ICITE50838.2020.9231500
Chuanli Kang, Zhenyu Zhang
As urbanization intensifies, the status of the traffic situation predict is becoming more and more prominent. The urban traffic flow is influenced by many factors and is characterized by strong randomness. This paper combines MSE and Adam to construct a linear LSTM to realize the prediction of short-term traffic flow based on time series. The experiment result shows that LSTM can gain the periodic features of the traffic flow. It has small error and high precision for the short-term prediction of the traffic flow based on time series, which verifies the validity of LSTM.
{"title":"Application of LSTM in Short-term Traffic Flow Prediction","authors":"Chuanli Kang, Zhenyu Zhang","doi":"10.1109/ICITE50838.2020.9231500","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231500","url":null,"abstract":"As urbanization intensifies, the status of the traffic situation predict is becoming more and more prominent. The urban traffic flow is influenced by many factors and is characterized by strong randomness. This paper combines MSE and Adam to construct a linear LSTM to realize the prediction of short-term traffic flow based on time series. The experiment result shows that LSTM can gain the periodic features of the traffic flow. It has small error and high precision for the short-term prediction of the traffic flow based on time series, which verifies the validity of LSTM.","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":"130618821","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/ICITE50838.2020.9231486
Junwei You
With the continuous innovation of computer science as well as the big data acquisition technology, machine learning (ML), developed as a state-of-art framework, now has been comprehensively applied in speed prediction tasks. However, ML methods usually require intensive hyper-parameter tuning, which hinders the practical deployment of ML models. In view of this, this paper proposes an automated machine learning (AutoML) framework for speed prediction, which enables the prediction work to be accomplished in a much more timesaving and convenient way as well as in high prediction accuracy. The proposed framework utilizes the Genetic Algorithm (GA) following its four major procedures: Genome coding, Crossover, Mutation and Selection to automatically search for the optimal neural network architectures and hyperparameters. The proposed framework is examined on a real-world large-scale dataset in the city of Berlin, Germany. The experimental results demonstrate that the proposed method outperforms other benchmarking methods by a significant margin. Sensitivity analysis is also conducted to show the robustness of the proposed method. This study demonstrates the great penitential of using AutoML in traffic speed prediction and other related transportation applications.
{"title":"A Genetic Algorithm-based AutoML Approach for Large-scale Traffic Speed Prediction","authors":"Junwei You","doi":"10.1109/ICITE50838.2020.9231486","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231486","url":null,"abstract":"With the continuous innovation of computer science as well as the big data acquisition technology, machine learning (ML), developed as a state-of-art framework, now has been comprehensively applied in speed prediction tasks. However, ML methods usually require intensive hyper-parameter tuning, which hinders the practical deployment of ML models. In view of this, this paper proposes an automated machine learning (AutoML) framework for speed prediction, which enables the prediction work to be accomplished in a much more timesaving and convenient way as well as in high prediction accuracy. The proposed framework utilizes the Genetic Algorithm (GA) following its four major procedures: Genome coding, Crossover, Mutation and Selection to automatically search for the optimal neural network architectures and hyperparameters. The proposed framework is examined on a real-world large-scale dataset in the city of Berlin, Germany. The experimental results demonstrate that the proposed method outperforms other benchmarking methods by a significant margin. Sensitivity analysis is also conducted to show the robustness of the proposed method. This study demonstrates the great penitential of using AutoML in traffic speed prediction and other related transportation applications.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"59 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":"126965404","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/ICITE50838.2020.9231398
Yanyan Chen, Yuntong Zhou
Pedestrian safety is one of the research focuses all over the world. Intelligent decision-making makes it possible to provide dangerous risk prediction. This paper aims to serve as a stepping stone for avoiding serious fatal vehicle - pedestrian crash. It provides a method for intelligent vehicles to identify the factors. Business and education Point of Information (POI) data in Beijing were collected and processed to partition traffic zones into high economic zones and low economic zones used the method of k-means clustering algorithm. Then a binary logistic regression was utilized for recognition of contributing factors. The result takes several important factors into account in low economic zones needed special attention, such as fourth class road and general city road. As a result, the findings of this study could assist to design the hardware module and programming of intelligent vehicle to enable pedestrian safety be improved over the long term.
{"title":"Factor Recognition of Regional Serious Pedestrian-vehicle Crash Using Big Data for Intelligent Vehicles","authors":"Yanyan Chen, Yuntong Zhou","doi":"10.1109/ICITE50838.2020.9231398","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231398","url":null,"abstract":"Pedestrian safety is one of the research focuses all over the world. Intelligent decision-making makes it possible to provide dangerous risk prediction. This paper aims to serve as a stepping stone for avoiding serious fatal vehicle - pedestrian crash. It provides a method for intelligent vehicles to identify the factors. Business and education Point of Information (POI) data in Beijing were collected and processed to partition traffic zones into high economic zones and low economic zones used the method of k-means clustering algorithm. Then a binary logistic regression was utilized for recognition of contributing factors. The result takes several important factors into account in low economic zones needed special attention, such as fourth class road and general city road. As a result, the findings of this study could assist to design the hardware module and programming of intelligent vehicle to enable pedestrian safety be improved over the long term.","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":"121823075","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 : 2020-07-22DOI: 10.1109/ICITE50838.2020.9231378
Yi Liu, Feijie Wang, Shengmao Xie
─ The Communication Based Train Control (CBTC) system has been widely employed in rail transit train control systems with its conspicuous technological advantages. As the brain of the CBTC system, the Automatic Train Supervision (ATS) system plays an important role. The route control function is one of the major functions of the ATS system. This article describes a route search algorithm with a binary tree generated in a directional non-ring diagram. Through the route control technology, it is possible to satisfy to the largest extent various operational demands in divergent complex operational scenarios of mixed large and small loops and Y-type loops, etc. and lay solid foundation for safe and highly efficient train operation.
{"title":"Research on ATS Route Control Based on the Binary Tree Algorithm","authors":"Yi Liu, Feijie Wang, Shengmao Xie","doi":"10.1109/ICITE50838.2020.9231378","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231378","url":null,"abstract":"─ The Communication Based Train Control (CBTC) system has been widely employed in rail transit train control systems with its conspicuous technological advantages. As the brain of the CBTC system, the Automatic Train Supervision (ATS) system plays an important role. The route control function is one of the major functions of the ATS system. This article describes a route search algorithm with a binary tree generated in a directional non-ring diagram. Through the route control technology, it is possible to satisfy to the largest extent various operational demands in divergent complex operational scenarios of mixed large and small loops and Y-type loops, etc. and lay solid foundation for safe and highly efficient train operation.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133143656","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 : 2020-06-20DOI: 10.1109/ICITE50838.2020.9231396
M. Vallati
One of the pivotal challenges presented to urban road traffic controllers is the effective utilisation of transport infrastructure, as a result of growing urbanisation, the finite network capacity, and of the increasing number of road vehicles. In this context, the arrival of connected autonomous vehicles (CAVs) represents a unique opportunity for a fundamental change in urban traffic optimisation, and urban traffic control should take an active role in integrating CAVs into the mobility ecosystem in order to maximise benefits. Traditional approaches, commonly exploited by SATNAVs, are based on a decentralised logic, where each vehicle decides the route to follow in isolation, possibly by considering the current network conditions. The arrival of connected vehicles would allow the exploitation of centralised traffic optimisation, where a central urban traffic controller can suggest routes to vehicles by taking into account the current network conditions, and predicted future evolution. This paper introduces a centralised approach for traffic optimisation of urban road networks, and presents an extensive evaluation of the capabilities of centralised and decentralised approaches. Evaluation is based on a validated and calibrated SUMO simulation model of the town centre of Milton Keynes, United Kingdom.
{"title":"Centralised Versus Decentralised Traffic Optimisation of Urban Road Networks: A Simulation Study","authors":"M. Vallati","doi":"10.1109/ICITE50838.2020.9231396","DOIUrl":"https://doi.org/10.1109/ICITE50838.2020.9231396","url":null,"abstract":"One of the pivotal challenges presented to urban road traffic controllers is the effective utilisation of transport infrastructure, as a result of growing urbanisation, the finite network capacity, and of the increasing number of road vehicles. In this context, the arrival of connected autonomous vehicles (CAVs) represents a unique opportunity for a fundamental change in urban traffic optimisation, and urban traffic control should take an active role in integrating CAVs into the mobility ecosystem in order to maximise benefits. Traditional approaches, commonly exploited by SATNAVs, are based on a decentralised logic, where each vehicle decides the route to follow in isolation, possibly by considering the current network conditions. The arrival of connected vehicles would allow the exploitation of centralised traffic optimisation, where a central urban traffic controller can suggest routes to vehicles by taking into account the current network conditions, and predicted future evolution. This paper introduces a centralised approach for traffic optimisation of urban road networks, and presents an extensive evaluation of the capabilities of centralised and decentralised approaches. Evaluation is based on a validated and calibrated SUMO simulation model of the town centre of Milton Keynes, United Kingdom.","PeriodicalId":112371,"journal":{"name":"2020 IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124332866","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：