Connected vehicle(CV)is regarded as a typical feature of the future road transportation system.One core benefit of promoting CV is to improve traffic safety,and to achieve that,accurate driving risk assessment under V...Connected vehicle(CV)is regarded as a typical feature of the future road transportation system.One core benefit of promoting CV is to improve traffic safety,and to achieve that,accurate driving risk assessment under Vehicle-to-Vehicle(V2V)communications is critical.There are two main differences concluded by comparing driving risk assessment under the CV environment with traditional ones:(1)the CV environment provides high-resolution and multi-dimensional data,e.g.,vehicle trajectory data,(2)Rare existing studies can comprehensively address the heterogeneity of the vehicle operating environment,e.g.,the multiple interacting objects and the time-series variability.Hence,this study proposes a driving risk assessment framework under the CV environment.Specifically,first,a set of time-series top views was proposed to describe the CV environment data,expressing the detailed information on the vehicles surrounding the subject vehicle.Then,a hybrid CNN-LSTM model was established with the CNN component extracting the spatial interaction with multiple interacting vehicles and the LSTM component solving the time-series variability of the driving environment.It is proved that this model can reach an AUC of 0.997,outperforming the existing machine learning algorithms.This study contributes to the improvement of driving risk assessment under the CV environment.展开更多
Driving safety field(DSF) model has been proposed to represent comprehensive driving risk formed by interactions of driver-vehicle-road in mixed traffic environment. In this work, we establish an optimization model ba...Driving safety field(DSF) model has been proposed to represent comprehensive driving risk formed by interactions of driver-vehicle-road in mixed traffic environment. In this work, we establish an optimization model based on grey relation degree analysis to calibrate risk coefficients of DSF model. To solve the optimum solution, a genetic algorithm is employed. Finally, the DSF model is verified through a real-world driving experiment. Results show that the DSF model is consistent with driver's hazard perception and more sensitive than TTC. Moreover, the proposed DSF model offers a novel way for criticality assessment and decision-making of advanced driver assistance systems and intelligent connected vehicles.展开更多
Road safety has long been considered as one of the most important issues.Numerous studies have been conducted to investigate crashes with significant progress,whereas most of the work concentrates on the lifespan peri...Road safety has long been considered as one of the most important issues.Numerous studies have been conducted to investigate crashes with significant progress,whereas most of the work concentrates on the lifespan period of roadways and safety influencing factors.This paper undertakes a systematic literature review from the crash procedure to identify the state-of-the-art knowledge,advantages and disadvantages of crash risk,crash prediction,crash prevention and safety of connected and autonomous vehicles(CAVs).As a result of this literature review,substantive issues in general,data source and modeling selection are discussed,and the outcome of this study aims to provide the summary of crash knowledge with potential insight into both traditional and emerging aspects,and guide the future research direction in safety.展开更多
This paper adopts the tail-event driven network(TENET)framework to explore the connectedness and systemic risk of the banking industry along the Belt and Road(B&R)based on weekly returns of 377 publicly-listed ban...This paper adopts the tail-event driven network(TENET)framework to explore the connectedness and systemic risk of the banking industry along the Belt and Road(B&R)based on weekly returns of 377 publicly-listed banks from 2014 to 2019.We conduct the connectedness analysis from four levels(i.e.,system,region,country and institution)and identify the systemic risk contribution of banks.We find that the dynamic total connectedness reached its peak during the outbreak of the abnormal fluctuations of Chinese stock market in 2015-2016 and its trough during the Brexit vote,and subsequently experienced several periodic fluctuations at a relatively high position.In the B&R banking system,the intra-regional tail risk spillovers are remarkably stronger than the inter-regional tail risk spillovers during the post-crisis period.In addition,the panel regressions estimated by the least squares dummy variable model show that the cross-border merger and acquisitions(M&As)and the merchandise trade export are important drivers for the tail-connectedness across the B&R countries.Our study provides regulators with insightful implications on the systemic risk supervision of the B&R banking industry.展开更多
基金sponsored by the Zhejiang Province Science and Technology Major Project of China(No.2021C01011)the National Natural Science Foundation of China(NSFC)(No.52172349)the China Scholarship Council(CSC).
文摘Connected vehicle(CV)is regarded as a typical feature of the future road transportation system.One core benefit of promoting CV is to improve traffic safety,and to achieve that,accurate driving risk assessment under Vehicle-to-Vehicle(V2V)communications is critical.There are two main differences concluded by comparing driving risk assessment under the CV environment with traditional ones:(1)the CV environment provides high-resolution and multi-dimensional data,e.g.,vehicle trajectory data,(2)Rare existing studies can comprehensively address the heterogeneity of the vehicle operating environment,e.g.,the multiple interacting objects and the time-series variability.Hence,this study proposes a driving risk assessment framework under the CV environment.Specifically,first,a set of time-series top views was proposed to describe the CV environment data,expressing the detailed information on the vehicles surrounding the subject vehicle.Then,a hybrid CNN-LSTM model was established with the CNN component extracting the spatial interaction with multiple interacting vehicles and the LSTM component solving the time-series variability of the driving environment.It is proved that this model can reach an AUC of 0.997,outperforming the existing machine learning algorithms.This study contributes to the improvement of driving risk assessment under the CV environment.
基金Projects(51475254,51625503)supported by the National Natural Science Foundation of ChinaProject(MCM20150302)supported by the Joint Project of Tsinghua and China Mobile,ChinaProject supported by the joint Project of Tsinghua and Daimler Greater China Ltd.,Beijing,China
文摘Driving safety field(DSF) model has been proposed to represent comprehensive driving risk formed by interactions of driver-vehicle-road in mixed traffic environment. In this work, we establish an optimization model based on grey relation degree analysis to calibrate risk coefficients of DSF model. To solve the optimum solution, a genetic algorithm is employed. Finally, the DSF model is verified through a real-world driving experiment. Results show that the DSF model is consistent with driver's hazard perception and more sensitive than TTC. Moreover, the proposed DSF model offers a novel way for criticality assessment and decision-making of advanced driver assistance systems and intelligent connected vehicles.
基金supported by National Natural Science Foundation of China(No:72131008)National Key Research and Development Program(No:2022YFC3800103-03).
文摘Road safety has long been considered as one of the most important issues.Numerous studies have been conducted to investigate crashes with significant progress,whereas most of the work concentrates on the lifespan period of roadways and safety influencing factors.This paper undertakes a systematic literature review from the crash procedure to identify the state-of-the-art knowledge,advantages and disadvantages of crash risk,crash prediction,crash prevention and safety of connected and autonomous vehicles(CAVs).As a result of this literature review,substantive issues in general,data source and modeling selection are discussed,and the outcome of this study aims to provide the summary of crash knowledge with potential insight into both traditional and emerging aspects,and guide the future research direction in safety.
基金supported by the National Natural Science Foundation of China(Grant nos.71871088 and 71971079 and 71850006)the National Social Science Foundation of China(Grant No.21ZDA114)the Hunan Provincial Natural Science Foundation of China(Grant No.21J20019).and the Huxiang Youth Talent Support Program,China.
文摘This paper adopts the tail-event driven network(TENET)framework to explore the connectedness and systemic risk of the banking industry along the Belt and Road(B&R)based on weekly returns of 377 publicly-listed banks from 2014 to 2019.We conduct the connectedness analysis from four levels(i.e.,system,region,country and institution)and identify the systemic risk contribution of banks.We find that the dynamic total connectedness reached its peak during the outbreak of the abnormal fluctuations of Chinese stock market in 2015-2016 and its trough during the Brexit vote,and subsequently experienced several periodic fluctuations at a relatively high position.In the B&R banking system,the intra-regional tail risk spillovers are remarkably stronger than the inter-regional tail risk spillovers during the post-crisis period.In addition,the panel regressions estimated by the least squares dummy variable model show that the cross-border merger and acquisitions(M&As)and the merchandise trade export are important drivers for the tail-connectedness across the B&R countries.Our study provides regulators with insightful implications on the systemic risk supervision of the B&R banking industry.
