Kehong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kehong Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Juanxiu Zhu
Xihua University, School of Management, Jinniu District, Jinzhou Road 999, Chengdu, China
3 shared publications - Han Xie
Xihua University, School of Management, Jinniu District, Jinzhou Road 999, Chengdu, China
2 shared publications Han Xie
1 shared publicationHuawei Duan
1 shared publicationJin Guo
School of Information Science and Technology Southwest Jiaotong University Chengdu 610031 China
1 shared publication- Jin Guo
School of Information Science and Technology, Southwest Jiao Tong University, Chengdu, China
1 shared publication
Latest Publications
- Open Access
- 26 September 2022
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2022, 1-23
Analysis of the Relationship between Vehicle Behaviors of Changing Lane and Volume of Traffic under Different Operating Ratios of Autonomous Vehicles
The lane-changing behavior is one of the important causes in traffic accident in congest traffic, and many behaviors of change lane affect volume of traffic. When autonomous driving vehicles are running on road with human-driven vehicles, the effects of change lane on traffic are different. In all human-driven vehicles traffic, the vehicle behaviors of changing lane are more competent. When autonomous driving vehicles are running in mixed traffic, the behaviors of changing lane decrease and the volume of traffic increases. However, a few studies have involved the relationship between traffic volume and lane-change behavior. In a sense, the study of this relationship is good for understanding the operation mechanism of mixed traffic. In this paper, we proposed the linear regression model to describe the relationship between traffic volume and lane-change behavior. The model can be used to establish the basic graph model. Here, we used empirical, simulation, and data-driven methods to obtain data and established a multiple linear regression model. First, we empirically study the continuous traffic with all human-driven vehicles. Then, the corresponding simulation model is established, and the availability of the simulation model is proved by data comparison with empirical study. Finally, 9 rounds of simulation experiments are carried out with the established simulation model. The number of autonomous driving vehicles in each round of simulation experiment increases by 10%. Then, we analyze the data of the behaviors of changing lane and the volume of traffic from simulation experiments. The following was found: (1) an increase in autonomous driving vehicle leads to an increase in traffic volume and a slight decrease in lane changing behaviors; (2) the influence of different proportions of autonomous vehicles on the traffic volume of lanes at different locations is slightly different; and (3) the relationships among the rate of vehicles entering lane, the rate of vehicles exiting lane together, and the volume of traffic show obvious linear relationships with the increase in autonomous driving vehicles. We used multiple linear regression models to carry out description, and the obtained parameter value intervals are close under different operating ratios of autonomous vehicles. To sum up, on multilane roads, especially 4-lane urban expressways, autonomous driving vehicles join in the traffic, which can effectively increase the volume of traffic of each lane while reducing vehicle behaviors of changing lane. The relationships between vehicle behaviors of changing lane and the traffic volume in mixed traffic show linear relationships with the increase in autonomous driving vehicles. In the future, we will further study whether this relationship model can be used in discrete traffic flow.
- 26 September 2022
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2022, 1-23
Open AccessAnalysis of the Relationship between Vehicle Behaviors of Changing Lane and Volume of Traffic under Different Operating Ratios of Autonomous Vehicles
The lane-changing behavior is one of the important causes in traffic accident in congest traffic, and many behaviors of change lane affect volume of traffic. When autonomous driving vehicles are running on road with human-driven vehicles, the effects of change lane on traffic are different. In all human-driven vehicles traffic, the vehicle behaviors of changing lane are more competent. When autonomous driving vehicles are running in mixed traffic, the behaviors of changing lane decrease and the volume of traffic increases. However, a few studies have involved the relationship between traffic volume and lane-change behavior. In a sense, the study of this relationship is good for understanding the operation mechanism of mixed traffic. In this paper, we proposed the linear regression model to describe the relationship between traffic volume and lane-change behavior. The model can be used to establish the basic graph model. Here, we used empirical, simulation, and data-driven methods to obtain data and established a multiple linear regression model. First, we empirically study the continuous traffic with all human-driven vehicles. Then, the corresponding simulation model is established, and the availability of the simulation model is proved by data comparison with empirical study. Finally, 9 rounds of simulation experiments are carried out with the established simulation model. The number of autonomous driving vehicles in each round of simulation experiment increases by 10%. Then, we analyze the data of the behaviors of changing lane and the volume of traffic from simulation experiments. The following was found: (1) an increase in autonomous driving vehicle leads to an increase in traffic volume and a slight decrease in lane changing behaviors; (2) the influence of different proportions of autonomous vehicles on the traffic volume of lanes at different locations is slightly different; and (3) the relationships among the rate of vehicles entering lane, the rate of vehicles exiting lane together, and the volume of traffic show obvious linear relationships with the increase in autonomous driving vehicles. We used multiple linear regression models to carry out description, and the obtained parameter value intervals are close under different operating ratios of autonomous vehicles. To sum up, on multilane roads, especially 4-lane urban expressways, autonomous driving vehicles join in the traffic, which can effectively increase the volume of traffic of each lane while reducing vehicle behaviors of changing lane. The relationships between vehicle behaviors of changing lane and the traffic volume in mixed traffic show linear relationships with the increase in autonomous driving vehicles. In the future, we will further study whether this relationship model can be used in discrete traffic flow.
- 23 July 2022
- Published by Elsevier in Computers & Security
- Vol. 121
Few-shot IoT attack detection based on RFP-CNN and adversarial unsupervised domain-adaptive regularization
- 23 July 2022
- Published by Elsevier in Computers & Security
- Vol. 121
Few-shot IoT attack detection based on RFP-CNN and adversarial unsupervised domain-adaptive regularization
- Open Access
- 20 July 2022
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2022, 1-19
A PH i /PH i , n / C / C Queuing Model in Randomly Changing Environments for Traffic Circulation Systems
Robust optimal design of circulation systems (e.g., roads for vehicles or corridors for pedestrians) relies on an accurate steady-state traffic flow model that considers the effect of randomly changing environmental factors (e.g., daily periodicity and weather). Most analytical models assume that the customer interarrival time and service time of circulation facilities follow the exponential distribution with fixed rate parameters, which is unrealistic in most cases. In this paper, we develop a stationary PH /PH state-dependent queuing model in a randomly changing environment (RE), which is represented by a Markov chain. The model simultaneously considers the general randomness of arrival and service, the randomly varying rate parameters, and the state-dependent service (the travel time increases with the number of customers). The existing matrix analytic scheme (MAS) algorithm is extended to solve the proposed model because it avoids the explicit calculation of probability distributions. The space complexity of the algorithm is only linear in the number of RE states and is independent of the enormous (four-dimensional) state space of the Markov process. Its time complexity is a linear function of the product of the queue capacity and the number of RE states. Our model is validated versus simulation estimates. The obtained conditional performance measures can accurately capture the queue accumulation and dissipation and reveal the effect of randomly changing environments. Numerical experiments provide some interesting findings. (1) The proposed stationary model coincides with the transient M()/G// fluid queuing model under special conditions. (2) Under high traffic intensities, increasing the randomness in the duration time of the RE state leads to an obvious growth in the conditional queue length. (3) An increase in the facility length leads to an increase or a decrease in the average output rate, depending on whether the congestion dissipates effectively in one cycle. (4) A larger width is required to obtain the maximum average output rate for traffic demand with a greater nonuniformity.
- 20 July 2022
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2022, 1-19
Open AccessA PH i /PH i , n / C / C Queuing Model in Randomly Changing Environments for Traffic Circulation Systems
Robust optimal design of circulation systems (e.g., roads for vehicles or corridors for pedestrians) relies on an accurate steady-state traffic flow model that considers the effect of randomly changing environmental factors (e.g., daily periodicity and weather). Most analytical models assume that the customer interarrival time and service time of circulation facilities follow the exponential distribution with fixed rate parameters, which is unrealistic in most cases. In this paper, we develop a stationary PH /PH state-dependent queuing model in a randomly changing environment (RE), which is represented by a Markov chain. The model simultaneously considers the general randomness of arrival and service, the randomly varying rate parameters, and the state-dependent service (the travel time increases with the number of customers). The existing matrix analytic scheme (MAS) algorithm is extended to solve the proposed model because it avoids the explicit calculation of probability distributions. The space complexity of the algorithm is only linear in the number of RE states and is independent of the enormous (four-dimensional) state space of the Markov process. Its time complexity is a linear function of the product of the queue capacity and the number of RE states. Our model is validated versus simulation estimates. The obtained conditional performance measures can accurately capture the queue accumulation and dissipation and reveal the effect of randomly changing environments. Numerical experiments provide some interesting findings. (1) The proposed stationary model coincides with the transient M()/G// fluid queuing model under special conditions. (2) Under high traffic intensities, increasing the randomness in the duration time of the RE state leads to an obvious growth in the conditional queue length. (3) An increase in the facility length leads to an increase or a decrease in the average output rate, depending on whether the congestion dissipates effectively in one cycle. (4) A larger width is required to obtain the maximum average output rate for traffic demand with a greater nonuniformity.
- Open Access
- 1 March 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (5) , 1300
Game Modelling and Strategy Research on the System Dynamics–Based Quadruplicate Evolution for High–Speed Railway Operational Safety Supervision System
In view of the entrusted transportation management model (ETMM) of China’s high–speed railway (HSR), the supervision strategy of an HSR company for its multiple agents plays a very important role in ensuring the safety and sustainable development of HSR. Due to the existence of multiple agents in ETMM, the supervision strategy for these agents is usually difficult to formulate. In this study, a quadruplicate HSR safety supervision system evolutionary game model composed of an HSR company and three agents was established through the analysis of the complex game relationship existing in the system. The behavioral characteristics and the steady state of decision–making of all stakeholders involved in the system are proved by evolutionary game theory and system dynamics simulation. The results show that there will be long–term fluctuations in the strategies selected by the four stakeholders in the static reward–penalty control scenario (RPCS), which indicates that an evolutionary stable strategy does not exist. With increases in the reward–penalty coefficient, the fluctuations are intensified. Therefore, the dynamic RPCS was proposed to control the fluctuations, and the simulation was repeated. The results show that the fluctuations can be effectively restrained by adopting the dynamic RPCS, but if the coefficients are the same, the static RPCS is better than the dynamic RPCS for increasing the safety investment rate of the three agents. This demonstrates that the HSR company should apply these two control scenarios flexibly according to the actual situation when formulating a supervision strategy in order to effectively control and enhance the safety level of HSR operations when multiple agents are involved.
- 1 March 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (5) , 1300
Open AccessGame Modelling and Strategy Research on the System Dynamics–Based Quadruplicate Evolution for High–Speed Railway Operational Safety Supervision System
In view of the entrusted transportation management model (ETMM) of China’s high–speed railway (HSR), the supervision strategy of an HSR company for its multiple agents plays a very important role in ensuring the safety and sustainable development of HSR. Due to the existence of multiple agents in ETMM, the supervision strategy for these agents is usually difficult to formulate. In this study, a quadruplicate HSR safety supervision system evolutionary game model composed of an HSR company and three agents was established through the analysis of the complex game relationship existing in the system. The behavioral characteristics and the steady state of decision–making of all stakeholders involved in the system are proved by evolutionary game theory and system dynamics simulation. The results show that there will be long–term fluctuations in the strategies selected by the four stakeholders in the static reward–penalty control scenario (RPCS), which indicates that an evolutionary stable strategy does not exist. With increases in the reward–penalty coefficient, the fluctuations are intensified. Therefore, the dynamic RPCS was proposed to control the fluctuations, and the simulation was repeated. The results show that the fluctuations can be effectively restrained by adopting the dynamic RPCS, but if the coefficients are the same, the static RPCS is better than the dynamic RPCS for increasing the safety investment rate of the three agents. This demonstrates that the HSR company should apply these two control scenarios flexibly according to the actual situation when formulating a supervision strategy in order to effectively control and enhance the safety level of HSR operations when multiple agents are involved.
- 2 October 2018
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 31 (10) , e4743
System dynamics model for high‐speed railway operation safety supervision system based on evolutionary game theory
Summary: In view of the entrusted transportation management model of High‐Speed Railways (HSR) in China, some questions have been exposed during its operation (eg, the supervision and inspection power of HSR company is not fully implemented, the poor management of safety investments, and no incentive and restraint mechanism). Through the analysis of the current situation of the HSR safety supervision system, a system dynamics (SD) model that is composed of an HSR company, the State Railway Administration (SRA) and the commissioned Railways Bureau (RB) have been established based on evolutionary game theory. The behavioral characteristics and the steady state of the decision‐making of all parties involved in the system are proved by the combination of evolutionary game theory and a system dynamics simulation. The results show that, under the clear incentive and restraint mechanism assumptions, the safety supervision and inspection rate of the system has been effectively improved and the supervision power of HSR company has been implemented.
- 2 October 2018
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 31 (10) , e4743
System dynamics model for high‐speed railway operation safety supervision system based on evolutionary game theory
Summary: In view of the entrusted transportation management model of High‐Speed Railways (HSR) in China, some questions have been exposed during its operation (eg, the supervision and inspection power of HSR company is not fully implemented, the poor management of safety investments, and no incentive and restraint mechanism). Through the analysis of the current situation of the HSR safety supervision system, a system dynamics (SD) model that is composed of an HSR company, the State Railway Administration (SRA) and the commissioned Railways Bureau (RB) have been established based on evolutionary game theory. The behavioral characteristics and the steady state of the decision‐making of all parties involved in the system are proved by the combination of evolutionary game theory and a system dynamics simulation. The results show that, under the clear incentive and restraint mechanism assumptions, the safety supervision and inspection rate of the system has been effectively improved and the supervision power of HSR company has been implemented.