One of the most important issues in traffic control is driver behavior while on the road and the reaction to specific perscriptive signals. Driver behavior can have a great impact on both traffic safety and on flow fluidity, and it can lead to a capacity reduction of an intersection. This reduction, giving rise to spillback phenomenon, may lead to congestion. This paper discusses the development of a methodology to construct models of the relationships between driver behavior, in particular, incorrect behavior, and specific conditions in traffic flow, within the environment and the requirements of the highway code. Considered are factors such as vehicle driven, sex, age of driver, and driving habits. The tool used was multilayered feedforward artificial neural networks with backpropagation learning. Three models have been implemented and they are discussed in some detail.
{"title":"A Methodology for Modelling Driver Behaviour in Signalized Urban Intersections Using Artificial Neural Networks","authors":"L. Mussone, G. Reitani, S. Rinelli","doi":"10.4324/9780429445286-8","DOIUrl":"https://doi.org/10.4324/9780429445286-8","url":null,"abstract":"One of the most important issues in traffic control is driver behavior while on the road and the reaction to specific perscriptive signals. Driver behavior can have a great impact on both traffic safety and on flow fluidity, and it can lead to a capacity reduction of an intersection. This reduction, giving rise to spillback phenomenon, may lead to congestion. This paper discusses the development of a methodology to construct models of the relationships between driver behavior, in particular, incorrect behavior, and specific conditions in traffic flow, within the environment and the requirements of the highway code. Considered are factors such as vehicle driven, sex, age of driver, and driving habits. The tool used was multilayered feedforward artificial neural networks with backpropagation learning. Three models have been implemented and they are discussed in some detail.","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127254058","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 control systems are traditionally grouped into three main categories: fixed time, flow actuated and vehicle actuated systems. In cases actuated by flow and by traffic, detectors allow, by means of appropriate techniques, detection of flows and/or vehicles traveling on the various links leading to the junction. The paper argues that meny of the control methodologies presented as traffic responsive do not fully meet the requirements. It describes a model developed using a control system implemented by neural networks.
{"title":"A New Traffic Light Single Junction Control System Implemented by a Symbolic Neural Network","authors":"E. Burattini, M. D. Gregorio, G. Improta","doi":"10.4324/9780429445286-9","DOIUrl":"https://doi.org/10.4324/9780429445286-9","url":null,"abstract":"Traffic control systems are traditionally grouped into three main categories: fixed time, flow actuated and vehicle actuated systems. In cases actuated by flow and by traffic, detectors allow, by means of appropriate techniques, detection of flows and/or vehicles traveling on the various links leading to the junction. The paper argues that meny of the control methodologies presented as traffic responsive do not fully meet the requirements. It describes a model developed using a control system implemented by neural networks.","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126275146","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 : 2019-07-09DOI: 10.4324/9780429445286-14
Y. Chang, Chaopeng Shen
In an urban public transit system, the demand volume and the service level are affected by the transit operations plan. An effective operations plan should be drawn based on both the demand volume and the service level, and the demand volume will be affected by the service level. This paper describes the development of a two mode system of urban transit equilibrium integrating the mode choice model and the fuzzy multiobjective model. The artificial neural network will be used to establish the mode choice model. The fuzzy multiobjective model is used to formulate the optimal transit operations plan with uncertain parameters. A compensatory operator will be used to deal with the vague relationship between objectives and parameters. A supply-demand adjustment mechanism is devised to characterize the interaction of the two models. The model has been tested on a bus system.
{"title":"The Application of Fuzzy Multiobjective and Artificial Neural Networks on Urban Public Transit Equilibrium","authors":"Y. Chang, Chaopeng Shen","doi":"10.4324/9780429445286-14","DOIUrl":"https://doi.org/10.4324/9780429445286-14","url":null,"abstract":"In an urban public transit system, the demand volume and the service level are affected by the transit operations plan. An effective operations plan should be drawn based on both the demand volume and the service level, and the demand volume will be affected by the service level. This paper describes the development of a two mode system of urban transit equilibrium integrating the mode choice model and the fuzzy multiobjective model. The artificial neural network will be used to establish the mode choice model. The fuzzy multiobjective model is used to formulate the optimal transit operations plan with uncertain parameters. A compensatory operator will be used to deal with the vague relationship between objectives and parameters. A supply-demand adjustment mechanism is devised to characterize the interaction of the two models. The model has been tested on a bus system.","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129971063","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 : 2019-07-09DOI: 10.4324/9780429445286-13
M. Pursula
This paper presents a method of estimating the speed flow density relationships from locally measured data sets using an analogy of backpropagation neural networks. The examples given are based on traditional local data with dynamic fluctuations, and the relationships obtained should not be regarded as steady state estimates but only as examples of the estimation procedure.
{"title":"Two Dimensional Estimation of Speed Flow Relationships with Backpropagation Neural Networks","authors":"M. Pursula","doi":"10.4324/9780429445286-13","DOIUrl":"https://doi.org/10.4324/9780429445286-13","url":null,"abstract":"This paper presents a method of estimating the speed flow density relationships from locally measured data sets using an analogy of backpropagation neural networks. The examples given are based on traditional local data with dynamic fluctuations, and the relationships obtained should not be regarded as steady state estimates but only as examples of the estimation procedure.","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116323096","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}
{"title":"Daily Travelling Viewed by Self-Organizing Maps","authors":"V. Himanen, Tuuli Jarvi-Nykanen, J. Raitio","doi":"10.4324/9780429445286-4","DOIUrl":"https://doi.org/10.4324/9780429445286-4","url":null,"abstract":"","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125365320","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 : 2019-07-09DOI: 10.4324/9780429445286-12
T. Nakatsuji, S. Shibuya
{"title":"Neural Network Models Applied to Traffic Flow Problems","authors":"T. Nakatsuji, S. Shibuya","doi":"10.4324/9780429445286-12","DOIUrl":"https://doi.org/10.4324/9780429445286-12","url":null,"abstract":"","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133534671","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}
{"title":"Neural Networks and Logit Models Applied to Commuters’ Mobility in The Metropolitan Area of Milan","authors":"A. Reggiani, T. Tritapepe","doi":"10.4324/9780429445286-5","DOIUrl":"https://doi.org/10.4324/9780429445286-5","url":null,"abstract":"","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"10 49","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114052295","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 : 2019-07-09DOI: 10.4324/9780429445286-11
G. Lyons, J. Hunt, S. Yousif
{"title":"Factors Influencing the Performance of a Neural Network Driver Decision Model: A Case Study Using Simulated Data","authors":"G. Lyons, J. Hunt, S. Yousif","doi":"10.4324/9780429445286-11","DOIUrl":"https://doi.org/10.4324/9780429445286-11","url":null,"abstract":"","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122058039","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}
Three inputs to a typical backpropagation based artificial neural network (ANN) modelling procedure are the number of hidden units, the learning rate (LR), and the momentum constant (MC). These three inputs have a profound effect on the ANN training as well as the resulting behavior of a trained network. This paper follows research done for the purpose of modeling trip generation using regression analysis and ANNs. The paper first presents a brief introduction to the problem of trip generation, and then explains the database used for modeling. The results of backpropagation modeling are also presented, followed by conclusions and recommendations.
{"title":"Analysis of Performance of Backpropagation ANN with Different Training Parameters","authors":"A. Faghri, A. Sandeep","doi":"10.4324/9780429445286-3","DOIUrl":"https://doi.org/10.4324/9780429445286-3","url":null,"abstract":"Three inputs to a typical backpropagation based artificial neural network (ANN) modelling procedure are the number of hidden units, the learning rate (LR), and the momentum constant (MC). These three inputs have a profound effect on the ANN training as well as the resulting behavior of a trained network. This paper follows research done for the purpose of modeling trip generation using regression analysis and ANNs. The paper first presents a brief introduction to the problem of trip generation, and then explains the database used for modeling. The results of backpropagation modeling are also presented, followed by conclusions and recommendations.","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126254048","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}
{"title":"Neural Networks as Adaptive Logit Models","authors":"L. Schintler, O. Olurotimi","doi":"10.4324/9780429445286-6","DOIUrl":"https://doi.org/10.4324/9780429445286-6","url":null,"abstract":"","PeriodicalId":393227,"journal":{"name":"Neural Networks in Transport Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129207752","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：