Jing Huang, Wei Wei, Xiaoyan Peng, Lin Hu, Huiqin Chen
Abstract Objective At present, most research on driver mental load identification is based on a single driving scene. However, the driver mental load model established in a road traffic scene is difficult to adapt to the changes of the surrounding road environment during the actual driving process. We proposed a driver mental load identification model which adapts to urban road traffic scenarios. Methods The model includes a driving scene discrimination sub-model and driver load identification sub-model, in which the driving scene discrimination sub-model can quickly and accurately determine the road traffic scene. The driver load identification sub-model selects the best feature subset and the best model algorithm in the scene based on the judgement of the driving scene classification sub-model. Results The results show that the driving scene discrimination sub-model using five vehicle features as feature subsets has the best performance. The driver load identification sub-model based on the best feature subset reduces the feature noise, and the recognition effect is better than the feature set using a single source signal and all data. The best recognition algorithm in different scenarios tends to be consistent, and the support vector machine (SVM) algorithm is better than the K-nearest neighbors (KNN) algorithm. Conclusion The proposed driver mental load identification model can discriminate the driving scene quickly and accurately, and then identify the driver mental load. In this way, our model can be more suitable for actual driving and improve the effect of driver mental load identification.
{"title":"Driver mental load identification model for adaptive urban road traffic scene","authors":"Jing Huang, Wei Wei, Xiaoyan Peng, Lin Hu, Huiqin Chen","doi":"10.1093/tse/tdac076","DOIUrl":"https://doi.org/10.1093/tse/tdac076","url":null,"abstract":"Abstract Objective At present, most research on driver mental load identification is based on a single driving scene. However, the driver mental load model established in a road traffic scene is difficult to adapt to the changes of the surrounding road environment during the actual driving process. We proposed a driver mental load identification model which adapts to urban road traffic scenarios. Methods The model includes a driving scene discrimination sub-model and driver load identification sub-model, in which the driving scene discrimination sub-model can quickly and accurately determine the road traffic scene. The driver load identification sub-model selects the best feature subset and the best model algorithm in the scene based on the judgement of the driving scene classification sub-model. Results The results show that the driving scene discrimination sub-model using five vehicle features as feature subsets has the best performance. The driver load identification sub-model based on the best feature subset reduces the feature noise, and the recognition effect is better than the feature set using a single source signal and all data. The best recognition algorithm in different scenarios tends to be consistent, and the support vector machine (SVM) algorithm is better than the K-nearest neighbors (KNN) algorithm. Conclusion The proposed driver mental load identification model can discriminate the driving scene quickly and accurately, and then identify the driver mental load. In this way, our model can be more suitable for actual driving and improve the effect of driver mental load identification.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135433412","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}
An enhanced optimal velocity model (EOVM) that considers driving safety is established to alleviate traffic congestion and ensure driving safety. Time headway is introduced as a criterion for determining whether the car is safe. When the time headway is less than the Minimum time headway (THmin ) or more than the most comfortable time headway(THcom), the acceleration constraints are discussed to ensure the model’s safety and maintain the following state. A stability analysis of the model was carried out to determine the stability conditions of the model. The EOVM is compared with the optimal velocity model (OVM) and fuzzy car-following model using the real dataset. Experiments show that the EOVM model has the smallest error in average, maximum, and median with the real dataset. To confirm the model’s safety, design fleet simulation experiments for three actual scenarios of starting, stopping, and uniform process.
{"title":"A car-following model based on the optimized velocity and its security analysis","authors":"Rong Fei, Lu Yang, X. Hei, Bo Hu, Aimin Li","doi":"10.1093/tse/tdac077","DOIUrl":"https://doi.org/10.1093/tse/tdac077","url":null,"abstract":"\u0000 An enhanced optimal velocity model (EOVM) that considers driving safety is established to alleviate traffic congestion and ensure driving safety. Time headway is introduced as a criterion for determining whether the car is safe. When the time headway is less than the Minimum time headway (THmin ) or more than the most comfortable time headway(THcom), the acceleration constraints are discussed to ensure the model’s safety and maintain the following state. A stability analysis of the model was carried out to determine the stability conditions of the model. The EOVM is compared with the optimal velocity model (OVM) and fuzzy car-following model using the real dataset. Experiments show that the EOVM model has the smallest error in average, maximum, and median with the real dataset. To confirm the model’s safety, design fleet simulation experiments for three actual scenarios of starting, stopping, and uniform process.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46705860","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}
Due to the limitations of railway route selection, some high-speed railways are inevitably built near or across fault zones. To study the distribution of rail-bridge interaction under different load history states of suspension bridges under three types of near-fault pulse-type earthquakes, this paper takes China's longest high-speed railway suspension bridge—Wufengshan Yangtze River Bridge as the background and establishes a spatial model of rail-bridge interaction of suspension bridge. The results show that: under the constant load state, the distribution of additional force under three types of pulse-type earthquakes are generally consistent, pulse-type earthquakes produce more significant responses than non-pulse-type earthquakes, with fling-step pulse being the largest, it is advised to specifically consider the influence of the fling-step pulse in the calculation. Under the initial condition of the main beam temperature loading history, all rail-bridge additional forces increase significantly, particularly affecting the steel rail system. The value of the rail-bridge interaction additional force under the near-fault earthquake in the initial state of the suspension bridge when the train deflection load is loaded from the tower to the mid-span is more significant and particularly unfavorable. The initial effect of the braking load will weaken the effect of the deflection load loading history. The results of the study indicate the effect of the initial state of suspension bridges is an important factor influencing the rail-bridge interaction under near-fault pulse-type earthquakes, which needs to be considered in future seismic design.
{"title":"Analysis of rail-bridge interaction of high-speed railway suspension bridge under near-fault pulse-type earthquakes","authors":"Xiangdong Yu, Bangzheng Jiang, Haiquan Jing","doi":"10.1093/tse/tdad032","DOIUrl":"https://doi.org/10.1093/tse/tdad032","url":null,"abstract":"\u0000 Due to the limitations of railway route selection, some high-speed railways are inevitably built near or across fault zones. To study the distribution of rail-bridge interaction under different load history states of suspension bridges under three types of near-fault pulse-type earthquakes, this paper takes China's longest high-speed railway suspension bridge—Wufengshan Yangtze River Bridge as the background and establishes a spatial model of rail-bridge interaction of suspension bridge. The results show that: under the constant load state, the distribution of additional force under three types of pulse-type earthquakes are generally consistent, pulse-type earthquakes produce more significant responses than non-pulse-type earthquakes, with fling-step pulse being the largest, it is advised to specifically consider the influence of the fling-step pulse in the calculation. Under the initial condition of the main beam temperature loading history, all rail-bridge additional forces increase significantly, particularly affecting the steel rail system. The value of the rail-bridge interaction additional force under the near-fault earthquake in the initial state of the suspension bridge when the train deflection load is loaded from the tower to the mid-span is more significant and particularly unfavorable. The initial effect of the braking load will weaken the effect of the deflection load loading history. The results of the study indicate the effect of the initial state of suspension bridges is an important factor influencing the rail-bridge interaction under near-fault pulse-type earthquakes, which needs to be considered in future seismic design.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45824337","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 contradiction between the increasing traffic and the relatively poor roundabout infrastructure is getting stronger. The control and optimization of the macroscopic traffic flow need to be improved to resolve congestion and safety problems at roundabouts and the connected road network. In order to better understand the gaps and trends in this field, we have systematically reviewed the main research and developments in traffic phenomena, driving behavior, autonomous vehicles (AVs), intelligent connected vehicles, and real vehicle trajectory data sets at roundabouts. The study is based on 388 papers about roundabouts, selected through a comprehensive literature search. The review demonstrates that based on a microscopic perspective, sensing, prediction, decision-making, planning, and control aspects of AVs and intelligent connected vehicles can be designed and optimized to fundamentally and significantly improve traffic capacity and driving safety at roundabouts. However, the generation mechanism of traffic conflicts among traffic participants at roundabouts is complex, which is a tremendous challenge for the systematic design of AVs. Therefore, based on naturalistic driving data and machine learning theory, it is an important research direction to build driver models by learning and imitating human driver decision-making and driving behaviors.
{"title":"A review of traffic behavior and intelligent driving at roundabouts based on microscopic perspective","authors":"Hao Jiang, Q. Shen, Aoxue Li, Chenhui Yin","doi":"10.1093/tse/tdad031","DOIUrl":"https://doi.org/10.1093/tse/tdad031","url":null,"abstract":"\u0000 The contradiction between the increasing traffic and the relatively poor roundabout infrastructure is getting stronger. The control and optimization of the macroscopic traffic flow need to be improved to resolve congestion and safety problems at roundabouts and the connected road network. In order to better understand the gaps and trends in this field, we have systematically reviewed the main research and developments in traffic phenomena, driving behavior, autonomous vehicles (AVs), intelligent connected vehicles, and real vehicle trajectory data sets at roundabouts. The study is based on 388 papers about roundabouts, selected through a comprehensive literature search. The review demonstrates that based on a microscopic perspective, sensing, prediction, decision-making, planning, and control aspects of AVs and intelligent connected vehicles can be designed and optimized to fundamentally and significantly improve traffic capacity and driving safety at roundabouts. However, the generation mechanism of traffic conflicts among traffic participants at roundabouts is complex, which is a tremendous challenge for the systematic design of AVs. Therefore, based on naturalistic driving data and machine learning theory, it is an important research direction to build driver models by learning and imitating human driver decision-making and driving behaviors.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44978500","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}
Fan Wu, Shuaixiong Zhou, Qingmin Cui, R. Xu, Hengkui Li, Chao Yu
Contaminated surfaces play a significant role in the transmission of respiratory infectious diseases. To address this issue, we presented a novel quantitative detection method for droplets on physical surfaces, based on Laser-Induced Fluorescence (LIF) technique. The proposed detection method was demonstrated in a realistic high-speed train compartment scenario by simulating the process of droplet release during passengers' breathing and coughing. The experimental results showed that this method could offer high precision (10−1 mg/m2) for detecting minute substance concentrations, and its ease of operation makes it suitable for complex engineering environments. The results also revealed that under the combined effects of the indoor airflow and breathing airflow, the range of droplets released by breathing activity exceeded two rows in front and behind the release position. Simultaneously, we observed that a large number of droplets settled on the seat surfaces on both sides of the same row as the releaser, with over 36% of these droplets concentrated on the backrest area of the seats. As the respiratory jet velocity increased, the location with the most sediment droplets (accounting for 8% of the total sedimentation) occurred on the seat directly in front of the releaser, and approximately 48% of the droplets were found on the back of this seat. Our proposed method overcomes the shortcomings of existing experimental methods in quantitatively capturing the motion characteristics of droplets in complex flow fields.
{"title":"Quantitative measurement and application of droplets on physical surfaces based on LIF technology","authors":"Fan Wu, Shuaixiong Zhou, Qingmin Cui, R. Xu, Hengkui Li, Chao Yu","doi":"10.1093/tse/tdad030","DOIUrl":"https://doi.org/10.1093/tse/tdad030","url":null,"abstract":"\u0000 Contaminated surfaces play a significant role in the transmission of respiratory infectious diseases. To address this issue, we presented a novel quantitative detection method for droplets on physical surfaces, based on Laser-Induced Fluorescence (LIF) technique. The proposed detection method was demonstrated in a realistic high-speed train compartment scenario by simulating the process of droplet release during passengers' breathing and coughing. The experimental results showed that this method could offer high precision (10−1 mg/m2) for detecting minute substance concentrations, and its ease of operation makes it suitable for complex engineering environments. The results also revealed that under the combined effects of the indoor airflow and breathing airflow, the range of droplets released by breathing activity exceeded two rows in front and behind the release position. Simultaneously, we observed that a large number of droplets settled on the seat surfaces on both sides of the same row as the releaser, with over 36% of these droplets concentrated on the backrest area of the seats. As the respiratory jet velocity increased, the location with the most sediment droplets (accounting for 8% of the total sedimentation) occurred on the seat directly in front of the releaser, and approximately 48% of the droplets were found on the back of this seat. Our proposed method overcomes the shortcomings of existing experimental methods in quantitatively capturing the motion characteristics of droplets in complex flow fields.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45887025","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 aims to solve the finite-time trajectory tracking problem of underactuated surface ships under the influence of dynamic uncertainty, unknown external time-varying interference and limited communication resources, an event-triggered robust adaptive finite-time trajectory tracking control method for underactuated ships is designed by combing the existing trajectory tracking control methods and engineering needs in actual navigation. It can obviously improve the tracking accuracy of the ship, and complete the tracking task safely and efficiently. This scheme transforms the composite uncertain vector synthesized by uncertain parameters and external disturbances into a linear parameterized form. Next, considering the limitation of communication resources, a relative threshold event triggering mechanism is introduced to further extend the triggering time interval on the basis of the fixed threshold triggering scheme. Then, an event-triggered robust adaptive finite-time trajectory tracking control scheme is designed for underactuated ships, and a rigorous stability proof is provided for the finite-time trajectory tracking control scheme designed above through Lyapunov stability theory. Simulation experiment is carried out in MATLAB and the results show that the finite-time trajectory tracking control scheme proposed in this paper can effectively solve the problems of dynamic uncertainty, unknown time-varying interference from the outside world, and limitation of communication resources. This paper can provide theoretical support for the autonomous navigation of intelligent ships.
{"title":"Event-triggered adaptive finite time trajectory tracking control for Underactuated Vessel considering unknown time-varying disturbances","authors":"Qiwen Wang, Qiang Zhang, Yugang Wang, Yancai Hu, Shaoyi Guo","doi":"10.1093/tse/tdac078","DOIUrl":"https://doi.org/10.1093/tse/tdac078","url":null,"abstract":"\u0000 This paper aims to solve the finite-time trajectory tracking problem of underactuated surface ships under the influence of dynamic uncertainty, unknown external time-varying interference and limited communication resources, an event-triggered robust adaptive finite-time trajectory tracking control method for underactuated ships is designed by combing the existing trajectory tracking control methods and engineering needs in actual navigation. It can obviously improve the tracking accuracy of the ship, and complete the tracking task safely and efficiently. This scheme transforms the composite uncertain vector synthesized by uncertain parameters and external disturbances into a linear parameterized form. Next, considering the limitation of communication resources, a relative threshold event triggering mechanism is introduced to further extend the triggering time interval on the basis of the fixed threshold triggering scheme. Then, an event-triggered robust adaptive finite-time trajectory tracking control scheme is designed for underactuated ships, and a rigorous stability proof is provided for the finite-time trajectory tracking control scheme designed above through Lyapunov stability theory. Simulation experiment is carried out in MATLAB and the results show that the finite-time trajectory tracking control scheme proposed in this paper can effectively solve the problems of dynamic uncertainty, unknown time-varying interference from the outside world, and limitation of communication resources. This paper can provide theoretical support for the autonomous navigation of intelligent ships.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46205356","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}
A high-reliability broadband high-linearity down-converter for multi-antenna Global Navigation Satellite System (GNSS) receiver is presented in this paper. Based on direction-of-arrival estimation, the multi-antenna GNSS receiver can separate the GNSS signals from the interfering signals and suppress harmful wideband radio frequency (RF) interferences. To drive the off-chip 50Ω resistive load and meet the stringent requirements of linearity, a quad-channel down-converter with a broadband common-gate low-noise transconductance amplifier (LNTA), current-driven passive mixer and novel bridge mode transimpedance driving amplifier has been proposed to contruct the multi-antenna receiver. The operating frequency of this down-converter is from 1.15 to 1.65 GHz, covering all bands for GPS/BDS/GLONASS/Galileo. The measured results show that the proposed quad-channel down-converter achieves +38 dBm output 3rd order intercept point (OIP3) and +17 dBm OP1dB (output-referred 1 dB compression point), 9.5–12.9 dB noise Fig. (NF) across the variable gain of 10-27 dB, and approximately 47 dB channel isolation.
{"title":"Four-channel broadband compact multi-antenna GNSS downconverter for high-reliability navigation","authors":"Riyan Wang, Bin Li, Hongyin He, Kunming Yang, Wei Feng, Zhijian Chen","doi":"10.1093/tse/tdad029","DOIUrl":"https://doi.org/10.1093/tse/tdad029","url":null,"abstract":"\u0000 A high-reliability broadband high-linearity down-converter for multi-antenna Global Navigation Satellite System (GNSS) receiver is presented in this paper. Based on direction-of-arrival estimation, the multi-antenna GNSS receiver can separate the GNSS signals from the interfering signals and suppress harmful wideband radio frequency (RF) interferences. To drive the off-chip 50Ω resistive load and meet the stringent requirements of linearity, a quad-channel down-converter with a broadband common-gate low-noise transconductance amplifier (LNTA), current-driven passive mixer and novel bridge mode transimpedance driving amplifier has been proposed to contruct the multi-antenna receiver. The operating frequency of this down-converter is from 1.15 to 1.65 GHz, covering all bands for GPS/BDS/GLONASS/Galileo. The measured results show that the proposed quad-channel down-converter achieves +38 dBm output 3rd order intercept point (OIP3) and +17 dBm OP1dB (output-referred 1 dB compression point), 9.5–12.9 dB noise Fig. (NF) across the variable gain of 10-27 dB, and approximately 47 dB channel isolation.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43575362","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}
Previous studies have found that drivers’ physiological conditions can deteriorate under noise conditions, which poses a potential hazard when driving. As a result, it is crucial to identify the status of drivers when exposed to different noises. However, such explorations are rarely discussed with short-term physiological indicators, especially for rail transit drivers. In this study, an experiment involving 42 railway transit drivers was conducted with a driving simulator to assess the impact of noise on drivers’ physiological responses. Considering the individuals’ heterogeneity, this study introduced drivers’ noise annoyance to measure their self-noise-adaption. The variances of drivers’ heart rate variability (HRV) along with different noise adaptions are explored when exposed to different noise conditions. Several machine learning approaches (Support Vector Machines, K-nearest Neighbors, and Random Forests) were then used to classify their physiological status under different noise conditions according to the HRV and drivers’ self-noise adaptions. Results indicate that the volume of traffic noise negatively affects drivers’ performance in their routines. Drivers with different noise adaptions but exposed to a fixed noise were found with discrepant HRV, demonstrating that noise adaption is highly associated with drivers’ physiological status under noises. It is also found that noise adaption inclusion could raise the accuracy of classifications. Overall, the Random Forests classifier performed the best in identifying the physiological status when exposed to noise conditions for drivers with different noise adaptions.
{"title":"Machine learning noise exposure detection of rail transit driver using heart rate variability","authors":"Zhiqiang Sun, Haiyue Liu, Yubo Jiao, Chenyang Zhang, Fang Xu, Chaozhe Jiang, Xiaozhuo Yu, Gang Wu","doi":"10.1093/tse/tdad028","DOIUrl":"https://doi.org/10.1093/tse/tdad028","url":null,"abstract":"\u0000 Previous studies have found that drivers’ physiological conditions can deteriorate under noise conditions, which poses a potential hazard when driving. As a result, it is crucial to identify the status of drivers when exposed to different noises. However, such explorations are rarely discussed with short-term physiological indicators, especially for rail transit drivers. In this study, an experiment involving 42 railway transit drivers was conducted with a driving simulator to assess the impact of noise on drivers’ physiological responses. Considering the individuals’ heterogeneity, this study introduced drivers’ noise annoyance to measure their self-noise-adaption. The variances of drivers’ heart rate variability (HRV) along with different noise adaptions are explored when exposed to different noise conditions. Several machine learning approaches (Support Vector Machines, K-nearest Neighbors, and Random Forests) were then used to classify their physiological status under different noise conditions according to the HRV and drivers’ self-noise adaptions. Results indicate that the volume of traffic noise negatively affects drivers’ performance in their routines. Drivers with different noise adaptions but exposed to a fixed noise were found with discrepant HRV, demonstrating that noise adaption is highly associated with drivers’ physiological status under noises. It is also found that noise adaption inclusion could raise the accuracy of classifications. Overall, the Random Forests classifier performed the best in identifying the physiological status when exposed to noise conditions for drivers with different noise adaptions.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47075315","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}
Tram systems with the advantages of reliable operation, comfort, low emissions, and moderate capacity have been quite popular in recent years in China. However, there are still problems with tram signal control (e.g. evaluation model, signal control strategies). In-depth analysis on existing operational issues of trams, calculation of two evaluation indexes, as well as a flexible model-free tram signal priority method, were developed to deal with tram problems. Empirical research in Songjiang District, Shanghai, shows that: (1) Function of green extension strategy is limited with c.a.10% tram priority improvement, while the optimal one can reach to 85% even higher in average. (2) The scheme with the benefit of trams but no negative impacts, even benefits on general traffic can be realized. (3)Optimal solution is beneficial for intersections with maximum c.a.70% melioration with delay decreasing from 132.7 s/vehicle to 40.89 s/vehicle, or from 104.77 s/capita to 22.31 s/capita. This paper has great significance for signal optimization and safety of tram systems, even the development of a comprehensive transportation system for a city.
{"title":"A flexible model-free tram signal priority method with a large coordination scope in China","authors":"Shan Wang","doi":"10.1093/tse/tdad027","DOIUrl":"https://doi.org/10.1093/tse/tdad027","url":null,"abstract":"\u0000 Tram systems with the advantages of reliable operation, comfort, low emissions, and moderate capacity have been quite popular in recent years in China. However, there are still problems with tram signal control (e.g. evaluation model, signal control strategies). In-depth analysis on existing operational issues of trams, calculation of two evaluation indexes, as well as a flexible model-free tram signal priority method, were developed to deal with tram problems. Empirical research in Songjiang District, Shanghai, shows that: (1) Function of green extension strategy is limited with c.a.10% tram priority improvement, while the optimal one can reach to 85% even higher in average. (2) The scheme with the benefit of trams but no negative impacts, even benefits on general traffic can be realized. (3)Optimal solution is beneficial for intersections with maximum c.a.70% melioration with delay decreasing from 132.7 s/vehicle to 40.89 s/vehicle, or from 104.77 s/capita to 22.31 s/capita. This paper has great significance for signal optimization and safety of tram systems, even the development of a comprehensive transportation system for a city.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44519153","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}
As a complex driving behavior, lane-changing (LC) behavior has a great influence on traffic flow. Improper lane-changing behavior often leads to traffic accidents. Numerous studies are currently being conducted to predict lane change trajectories to minimize dangers. However, most of their models focus on how to optimize input variables without considering the interaction between output variables. This study proposes a LC trajectory prediction model based on a multi-task deep learning framework to improve driving safety. Concretely, in this work, the coupling effect of lateral and longitudinal movement is considered in the LC process. Trajectory changes in two directions will be modeled separately, and the information interaction is completed under the multi-task learning framework. In addition, the trajectory fragments are clustered by the driving features, and trajectory type recognition is added to the trajectory prediction framework as an auxiliary task. Finally, the prediction process of lateral and longitudinal trajectory and LC style is completed by Long Short-Term Memory (LSTM). The model training and testing are conducted with the data collected by the driving simulator, and that the proposed method expresses better performance in the LC trajectory prediction compared with several traditional models. The result showed in this study can enhance the trajectory prediction accuracy of Advanced Driving Assistance System (ADAS) and reduce the traffic accidents caused by lane changes.
{"title":"Lane-changing trajectory prediction based on multi-task learning","authors":"Xianwei Meng, Jinjun Tang, Fang Yang, Zhe Wang","doi":"10.1093/tse/tdac073","DOIUrl":"https://doi.org/10.1093/tse/tdac073","url":null,"abstract":"\u0000 As a complex driving behavior, lane-changing (LC) behavior has a great influence on traffic flow. Improper lane-changing behavior often leads to traffic accidents. Numerous studies are currently being conducted to predict lane change trajectories to minimize dangers. However, most of their models focus on how to optimize input variables without considering the interaction between output variables. This study proposes a LC trajectory prediction model based on a multi-task deep learning framework to improve driving safety. Concretely, in this work, the coupling effect of lateral and longitudinal movement is considered in the LC process. Trajectory changes in two directions will be modeled separately, and the information interaction is completed under the multi-task learning framework. In addition, the trajectory fragments are clustered by the driving features, and trajectory type recognition is added to the trajectory prediction framework as an auxiliary task. Finally, the prediction process of lateral and longitudinal trajectory and LC style is completed by Long Short-Term Memory (LSTM). The model training and testing are conducted with the data collected by the driving simulator, and that the proposed method expresses better performance in the LC trajectory prediction compared with several traditional models. The result showed in this study can enhance the trajectory prediction accuracy of Advanced Driving Assistance System (ADAS) and reduce the traffic accidents caused by lane changes.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43799074","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：