Eliseé Enselme Tuekam Bopda, J. Tamba, Armand Fopah-Lele
The objective of this article is to show the influence of mobile phone use while driving on the performance of petroleum product drivers in Cameroon. The topical questioning centered on the series of accidents and near misses in general and specifically in the petroleum products sector called for the need to look for other causes. To do so, we conceptually proposed a model derived from the literature review and adjusted by practical research, which shows that our approach of is the hypothetico-deductive type. Methodologically, the observations from the experience of 90 questionnaires were operationalized using multivariate logistic regression analyses. The results indicate that making or receiving calls while driving significantly influences the occurrence of reckless driving situations. Reading and sending Short Message Service (SMS or text messages) while driving negatively influences drivers' performance by increasing delivery times. The type of phone used has an effect on the risk of accidents or near misses. Indeed, drivers who use smartphones are 2.14 times more likely to experience crash-like events compared to those who use conventional mobile phones. In addition, with a view to reducing near-misses and accidents, it is important to organize regular appropriate road safety campaigns, to install on-board cameras in all trucks, to provide rest areas and encourage drivers to stop at these areas to check their phones and catch up on missed calls. Additionally to introduce training for drivers in defensive driving with a renewable license after a maximum of 2 years.
{"title":"Impacts of mobile phone use while driving on the performance of petroleum product drivers in Cameroon","authors":"Eliseé Enselme Tuekam Bopda, J. Tamba, Armand Fopah-Lele","doi":"10.1093/tse/tdac044","DOIUrl":"https://doi.org/10.1093/tse/tdac044","url":null,"abstract":"\u0000 The objective of this article is to show the influence of mobile phone use while driving on the performance of petroleum product drivers in Cameroon. The topical questioning centered on the series of accidents and near misses in general and specifically in the petroleum products sector called for the need to look for other causes. To do so, we conceptually proposed a model derived from the literature review and adjusted by practical research, which shows that our approach of is the hypothetico-deductive type. Methodologically, the observations from the experience of 90 questionnaires were operationalized using multivariate logistic regression analyses. The results indicate that making or receiving calls while driving significantly influences the occurrence of reckless driving situations. Reading and sending Short Message Service (SMS or text messages) while driving negatively influences drivers' performance by increasing delivery times. The type of phone used has an effect on the risk of accidents or near misses. Indeed, drivers who use smartphones are 2.14 times more likely to experience crash-like events compared to those who use conventional mobile phones.\u0000 In addition, with a view to reducing near-misses and accidents, it is important to organize regular appropriate road safety campaigns, to install on-board cameras in all trucks, to provide rest areas and encourage drivers to stop at these areas to check their phones and catch up on missed calls. Additionally to introduce training for drivers in defensive driving with a renewable license after a maximum of 2 years.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44700913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates the scale and expression of passengers’ anger from the disputes between drivers and passengers, as well as among passengers on the bus by surveying a sample of 757 undergraduate students. The bus passengers’ anger scale and expression inventory (BPASX), a newly-designed questionnaire battery, is used to analyze anger levels and resulted behavior expression of passengers in 6-item anger-provoking situations. The analysis shows that a positive correlation exists between the frequency or duration of bus rides and anger levels/ external anger expression, while self-adaptive expression is only correlated with the frequency. Gender differs only in the violent external expression where males display a greater preference. Meanwhile, the correlations of anger levels among anger-provoking situations are significantly positive. Moreover, anger expression patterns gradually shift from self-adaptation to external expression as anger levels grow in general, but the variation rules of expression frequency are different. Overall, this study provides a newly effective tool to explore characteristics of anger expression of bus passengers under different anger-provoking scenarios and demonstrates its variation features when anger levels change.
{"title":"Bus passengers’ anger scale and expression in anger-provoking situations","authors":"Zhili Yuan, Qun Chen, Shi Ye","doi":"10.1093/tse/tdac038","DOIUrl":"https://doi.org/10.1093/tse/tdac038","url":null,"abstract":"\u0000 This paper investigates the scale and expression of passengers’ anger from the disputes between drivers and passengers, as well as among passengers on the bus by surveying a sample of 757 undergraduate students. The bus passengers’ anger scale and expression inventory (BPASX), a newly-designed questionnaire battery, is used to analyze anger levels and resulted behavior expression of passengers in 6-item anger-provoking situations. The analysis shows that a positive correlation exists between the frequency or duration of bus rides and anger levels/ external anger expression, while self-adaptive expression is only correlated with the frequency. Gender differs only in the violent external expression where males display a greater preference. Meanwhile, the correlations of anger levels among anger-provoking situations are significantly positive. Moreover, anger expression patterns gradually shift from self-adaptation to external expression as anger levels grow in general, but the variation rules of expression frequency are different. Overall, this study provides a newly effective tool to explore characteristics of anger expression of bus passengers under different anger-provoking scenarios and demonstrates its variation features when anger levels change.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44791954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Safety and reliability are absolutely vital for sophisticated Railway Point Machines (RPMs). Hence, various kinds of sensors and transducers are deployed on RPMs as much as possible to monitor their behaviour for detection of incipient faults and anticipation using data-driven technology. This paper firstly analyses and summarizes six RPMs’ characteristics and then reviews the data-driven algorithms applied to fault diagnosis in RPMs during the past decade. It provides not only the process and evaluation metrics but also the pros and cons of these different methods. Ultimately, regarding the characteristics of RPMs and the existing studies, eight challenging problems and promising research directions are pointed out.
{"title":"Data-driven technology of fault diagnosis in railway point machines: review and challenges","authors":"Xiaoxi Hu, Yuan Cao, T. Tang, Yongkui Sun","doi":"10.1093/tse/tdac036","DOIUrl":"https://doi.org/10.1093/tse/tdac036","url":null,"abstract":"\u0000 Safety and reliability are absolutely vital for sophisticated Railway Point Machines (RPMs). Hence, various kinds of sensors and transducers are deployed on RPMs as much as possible to monitor their behaviour for detection of incipient faults and anticipation using data-driven technology. This paper firstly analyses and summarizes six RPMs’ characteristics and then reviews the data-driven algorithms applied to fault diagnosis in RPMs during the past decade. It provides not only the process and evaluation metrics but also the pros and cons of these different methods. Ultimately, regarding the characteristics of RPMs and the existing studies, eight challenging problems and promising research directions are pointed out.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45485090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introduction to special issue on maritime safety and smart shipping","authors":"Xiaojian Xu, Xinping Yan, Di Zhang","doi":"10.1093/tse/tdac056","DOIUrl":"https://doi.org/10.1093/tse/tdac056","url":null,"abstract":"","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46472164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reinforcement learning-based traffic signal control systems (RLTSC) can enhance dynamic adaptability, save vehicle travelling time and promote intersection capacity. However, the existing RLTSC methods do not consider the driver's response time requirement, so the systems often face efficiency limitations and implementation difficulties. We propose the advance decision-making reinforcement learning traffic signal control (AD-RLTSC) algorithm to improve traffic efficiency while ensuring safety in mixed traffic environment. First, the relationship between the intersection perception range and the signal control period is established and the trust region state (TRS) is proposed. Then, the scalable state matrix is dynamically adjusted to decide the future signal light status. The decision will be displayed to the human-driven vehicles (HDVs) through the bi-countdown timer mechanism and sent to the nearby connected automated vehicles (CAVs) using the wireless network rather than be executed immediately. HDVs and CAVs optimize the driving speed based on the remaining green (or red) time. Besides, the Double Dueling Deep Q-learning Network algorithm is used for reinforcement learning training; a standardized reward is proposed to enhance the performance of intersection control and prioritized experience replay is adopted to improve sample utilization. The experimental results on vehicle micro-behaviour and traffic macro-efficiency showed that the proposed AD-RLTSC algorithm can simultaneously improve both traffic efficiency and traffic flow stability.
{"title":"Traffic signal control in mixed traffic environment based on advance decision and reinforcement learning","authors":"Yu Du, W. Shangguan, Linguo Chai","doi":"10.1093/tse/tdac027","DOIUrl":"https://doi.org/10.1093/tse/tdac027","url":null,"abstract":"\u0000 Reinforcement learning-based traffic signal control systems (RLTSC) can enhance dynamic adaptability, save vehicle travelling time and promote intersection capacity. However, the existing RLTSC methods do not consider the driver's response time requirement, so the systems often face efficiency limitations and implementation difficulties. We propose the advance decision-making reinforcement learning traffic signal control (AD-RLTSC) algorithm to improve traffic efficiency while ensuring safety in mixed traffic environment. First, the relationship between the intersection perception range and the signal control period is established and the trust region state (TRS) is proposed. Then, the scalable state matrix is dynamically adjusted to decide the future signal light status. The decision will be displayed to the human-driven vehicles (HDVs) through the bi-countdown timer mechanism and sent to the nearby connected automated vehicles (CAVs) using the wireless network rather than be executed immediately. HDVs and CAVs optimize the driving speed based on the remaining green (or red) time. Besides, the Double Dueling Deep Q-learning Network algorithm is used for reinforcement learning training; a standardized reward is proposed to enhance the performance of intersection control and prioritized experience replay is adopted to improve sample utilization. The experimental results on vehicle micro-behaviour and traffic macro-efficiency showed that the proposed AD-RLTSC algorithm can simultaneously improve both traffic efficiency and traffic flow stability.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43074801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiao Jing, Xinghua Pei, Song Yan, Chunyang Han, Selpi, E. Andreotti, Jishiyu Ding
The safety of heterogeneous traffic is a vital topic in the oncoming era of autonomous vehicles (AVs). The cooperative vehicle infras- tructure system (CVIS) is considered to improve heterogeneous traffic safety by connecting and controlling AVs cooperatively, and the connected AVs are so-called connected and automated vehicles (CAVs). However, the safety impact of cooperative control strategy on the heterogeneous traffic with CAVs and human-driving vehicles (HVs) has not been well investigated. In this paper, based on the traffic simulator SUMO, we designed a typical highway scenario of on-ramp merging and adopted a cooperative control method for CAVs. We then compared the safety performance for two different heterogeneous traffic systems, i.e. AV and HV, CAV and HV, respectively, to illustrate the safety benefits of the cooperative control strategy. We found that the safety performance of the CAV and HV traffic system does not always outperform that of AV and HV. With random departSpeed and higher arrival rate, the proposed cooperative control method would decrease the conflicts significantly whereas the penetration rate is over 80%. We further investigated the conflicts in terms of the leading and following vehicle types, and found that the risk of a AV/CAV followed by a HV is twice that of a HV followed by another HV. We also considered the safety effect of communication failure, and found that there is no significant impact until the packet loss probability is greater than 30%, while communication delay’s impact on safety can be ignored according to our experiments.
{"title":"Safety benefit of cooperative control for heterogeneous traffic on-ramp merging","authors":"Xiao Jing, Xinghua Pei, Song Yan, Chunyang Han, Selpi, E. Andreotti, Jishiyu Ding","doi":"10.1093/tse/tdac031","DOIUrl":"https://doi.org/10.1093/tse/tdac031","url":null,"abstract":"The safety of heterogeneous traffic is a vital topic in the oncoming era of autonomous vehicles (AVs). The cooperative vehicle infras- tructure system (CVIS) is considered to improve heterogeneous traffic safety by connecting and controlling AVs cooperatively, and the connected AVs are so-called connected and automated vehicles (CAVs). However, the safety impact of cooperative control strategy on the heterogeneous traffic with CAVs and human-driving vehicles (HVs) has not been well investigated. In this paper, based on the traffic simulator SUMO, we designed a typical highway scenario of on-ramp merging and adopted a cooperative control method for CAVs. We then compared the safety performance for two different heterogeneous traffic systems, i.e. AV and HV, CAV and HV, respectively, to illustrate the safety benefits of the cooperative control strategy. We found that the safety performance of the CAV and HV traffic system does not always outperform that of AV and HV. With random departSpeed and higher arrival rate, the proposed cooperative control method would decrease the conflicts significantly whereas the penetration rate is over 80%. We further investigated the conflicts in terms of the leading and following vehicle types, and found that the risk of a AV/CAV followed by a HV is twice that of a HV followed by another HV. We also considered the safety effect of communication failure, and found that there is no significant impact until the packet loss probability is greater than 30%, while communication delay’s impact on safety can be ignored according to our experiments.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45935423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
COVID-19 has upended the whole world. Due to travel restrictions by governments and increased perceived risks of the disease, there have been significant changes in social activities and travel patterns. This paper investigates the effects of COVID-19 on changes to individuals' travel patterns, particularly for travel purposes. An online questionnaire survey was conducted in China, which incorporates questions about individuals’ sociodemographic and travel characteristics in three different periods of COVID-19 (i.e. before the outbreak, at the peak and after the peak; the peak here refers to the peak of the pandemic in China, between the end of January and 1 May, 2020). The results show that trip frequency decreased sharply from the outbreak until the peak, and drastically increased after the peak. Nevertheless, the data from this study suggests that it has not fully recovered to the level before the outbreak. Subsequently, a series of random parameters bivariate Probit models for changes in travel patterns were estimated with personal characteristics. The findings demonstrate that during the peak of the pandemic, residents who did not live in more developed cities reached low-frequency travel patterns more quickly. For travel purposes, residents of Wuhan, China resumed travelling for work, entertainment and buy necessities at a much higher rate than other cities. After the peak, students' travel for work, entertainment and to buy necessities recovered significantly faster than for other occupations. The findings would be helpful for establishing effective policies to control individual travel and minimize disease spread in a possible future pandemic.
{"title":"How has COVID-19 changed trip patterns by purpose in China?","authors":"Enru Zhou, Jaeyoung Lee","doi":"10.1093/tse/tdac030","DOIUrl":"https://doi.org/10.1093/tse/tdac030","url":null,"abstract":"\u0000 COVID-19 has upended the whole world. Due to travel restrictions by governments and increased perceived risks of the disease, there have been significant changes in social activities and travel patterns. This paper investigates the effects of COVID-19 on changes to individuals' travel patterns, particularly for travel purposes. An online questionnaire survey was conducted in China, which incorporates questions about individuals’ sociodemographic and travel characteristics in three different periods of COVID-19 (i.e. before the outbreak, at the peak and after the peak; the peak here refers to the peak of the pandemic in China, between the end of January and 1 May, 2020). The results show that trip frequency decreased sharply from the outbreak until the peak, and drastically increased after the peak. Nevertheless, the data from this study suggests that it has not fully recovered to the level before the outbreak. Subsequently, a series of random parameters bivariate Probit models for changes in travel patterns were estimated with personal characteristics. The findings demonstrate that during the peak of the pandemic, residents who did not live in more developed cities reached low-frequency travel patterns more quickly. For travel purposes, residents of Wuhan, China resumed travelling for work, entertainment and buy necessities at a much higher rate than other cities. After the peak, students' travel for work, entertainment and to buy necessities recovered significantly faster than for other occupations. The findings would be helpful for establishing effective policies to control individual travel and minimize disease spread in a possible future pandemic.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42209280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Discomfort caused by long-term sitting decreases the passenger experience and may lead to musculoskeletal diseases, and this has become one of the main problems for passengers of high-speed railways. However, the comfort degradation mechanism during long-term sitting in high-speed railways is still unknown. This study aimed to reveal passengers’ sitting comfort degradation mechanism in high-speed railways. By carrying out long-term sitting tests on high-speed trains running on the Shanghai-Kunming line, the dynamic interface pressure and subjective comfort including overall and regional comfort of seven participants were obtained. Machine learning models and statistical analysis methods were combined for data analysis to reveal the effect of regional comfort and the contribution of sitting duration during the process of sitting comfort degradation. The results show that overall comfort is most significantly influenced by the comfort of the shoulders, waist and buttocks. The seats play different roles before and after 20 minutes during long-term sitting and there is a lag between the fatigue occurring and being offset. Therefore, the structure of seats affects overall comfort by affecting important regional comfort, and a long-term sitting test is necessary for accurate seat assessment. The comfort degradation mechanism can be used to define standards for long-term sitting comfort or provide guidance for seat evaluation, and the design and evaluation plan mentioned in this article for second-class seats can be applied to other cases with limited accommodating space.
{"title":"Research on the comfort degradation mechanism of high-speed railway passengers: a field study using dynamic interface pressure","authors":"Yong Peng, Dayan Sun, Chaojie Fan, Zhifa Wu, Shengen Yi, Yuexiang Peng, Yingjun Liu","doi":"10.1093/tse/tdac022","DOIUrl":"https://doi.org/10.1093/tse/tdac022","url":null,"abstract":"\u0000 Discomfort caused by long-term sitting decreases the passenger experience and may lead to musculoskeletal diseases, and this has become one of the main problems for passengers of high-speed railways. However, the comfort degradation mechanism during long-term sitting in high-speed railways is still unknown. This study aimed to reveal passengers’ sitting comfort degradation mechanism in high-speed railways. By carrying out long-term sitting tests on high-speed trains running on the Shanghai-Kunming line, the dynamic interface pressure and subjective comfort including overall and regional comfort of seven participants were obtained. Machine learning models and statistical analysis methods were combined for data analysis to reveal the effect of regional comfort and the contribution of sitting duration during the process of sitting comfort degradation. The results show that overall comfort is most significantly influenced by the comfort of the shoulders, waist and buttocks. The seats play different roles before and after 20 minutes during long-term sitting and there is a lag between the fatigue occurring and being offset. Therefore, the structure of seats affects overall comfort by affecting important regional comfort, and a long-term sitting test is necessary for accurate seat assessment. The comfort degradation mechanism can be used to define standards for long-term sitting comfort or provide guidance for seat evaluation, and the design and evaluation plan mentioned in this article for second-class seats can be applied to other cases with limited accommodating space.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48708276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To address situations in which the bus lanes at intersections are idle for long periods, this paper proposes a changeable shared bus lane scheme for intersections based on lane signals. This scheme set up two GPS monitoring points for buses in the bus lane of the intersection to monitor the bus approaching the intersection. The lane signals linked to the monitoring points provide car drivers with a signal of whether they can enter the bus lane. This paper establishes an optimization model to maximize the number of vehicles entering the bus lane and uses numerical example simulations to discuss in detail the optimal monitoring point locations in different situations. Without affecting the bus, we obtain the optimal monitoring point setting schemes for several common situations and compare the total delay for ordinary vehicles in the bus lane of the lane-based signal scheme and a baseline case (without the lane-based signal). The results show that this scheme can effectively reduce vehicle delays at intersections. Finally, we discuss the limitations of this scheme and directions for future research.
{"title":"Changeable shared bus lane scheme for intersections based on lane signals","authors":"Jiahui Liu, Dawei Chen, Qun Chen","doi":"10.1093/tse/tdac024","DOIUrl":"https://doi.org/10.1093/tse/tdac024","url":null,"abstract":"\u0000 To address situations in which the bus lanes at intersections are idle for long periods, this paper proposes a changeable shared bus lane scheme for intersections based on lane signals. This scheme set up two GPS monitoring points for buses in the bus lane of the intersection to monitor the bus approaching the intersection. The lane signals linked to the monitoring points provide car drivers with a signal of whether they can enter the bus lane. This paper establishes an optimization model to maximize the number of vehicles entering the bus lane and uses numerical example simulations to discuss in detail the optimal monitoring point locations in different situations. Without affecting the bus, we obtain the optimal monitoring point setting schemes for several common situations and compare the total delay for ordinary vehicles in the bus lane of the lane-based signal scheme and a baseline case (without the lane-based signal). The results show that this scheme can effectively reduce vehicle delays at intersections. Finally, we discuss the limitations of this scheme and directions for future research.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44333106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The LaneGCN proposed by Uber has achieved good performance in trajectory prediction, but it has shortcomings in capturing long range information, expressing road information and modelling the strong and weak relationships of interaction between actors. In this paper, the LaneGCN is improved from three parts. Firstly, multi-scale long short-term memory is introduced to encode multi-scale trajectory information. Secondly, relative distance information is added to enhance the spatial expressive capacity of the model in the process of road information encoding. Finally, we build a weighted interaction model based on Graph Attention Networks in the process of road information encoding. In order to verify the performance of the improved model, ablation and comparison experiments are designed in this paper. The results showed that all the evaluation metrics are lower than the LaneGCN and the overall performance of the model is improved.
{"title":"Research on the improvement of the LaneGCN trajectory prediction algorithm","authors":"Bing Zhou, Junjun Zou, Xiaojian Wu, Tian Chai, Renjie Zhou, Qianxi Pan, R. Zhou","doi":"10.1093/tse/tdac034","DOIUrl":"https://doi.org/10.1093/tse/tdac034","url":null,"abstract":"\u0000 The LaneGCN proposed by Uber has achieved good performance in trajectory prediction, but it has shortcomings in capturing long range information, expressing road information and modelling the strong and weak relationships of interaction between actors. In this paper, the LaneGCN is improved from three parts. Firstly, multi-scale long short-term memory is introduced to encode multi-scale trajectory information. Secondly, relative distance information is added to enhance the spatial expressive capacity of the model in the process of road information encoding. Finally, we build a weighted interaction model based on Graph Attention Networks in the process of road information encoding. In order to verify the performance of the improved model, ablation and comparison experiments are designed in this paper. The results showed that all the evaluation metrics are lower than the LaneGCN and the overall performance of the model is improved.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46247680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：