会议论文集名称：
International Conference on Measuring Technology and Mechatronics Automation
关键词：
lane change;ANP;factors;early warning
摘要：
The driver lane change process is divided into two parts: lane change awareness formation and behavior implementation. Considering that the intrinsic factors of assessing the status and ability of drivers and the external traffic environment factors will affect the entire lane changing process independently rather than being independent and non-interfering, this paper chooses network AHP to analyze and identify the lane changing behaviors. The result shows that the accuracy of this method can reach 92.37% and the effect is better.
摘要：
In order to ensure that traffic capacity is stable, and avoid incident congestion is anabatic, a double-layer ramp-metering model is proposed in this paper to control the traffic flow at each on-ramp, nearby incident congestion. The function of the lower model is to recognize where the incident congestion exists, based on an adaptive neural network, whose inputs are traffic flow, velocity and density. The outputs of the lower model are the section number where the congestion occurs and the ramp number which should be controlled. If there is congestion, the upper model would be activated. The function of the upper model is to calculate the control strategy. The required control ramp number from the lower model would be transmitted to the upper model together with the real-time state of controlled section. The upper model would calculate the ramp-metering ratio for each required ramp by minimizing the main time cost, total average queue length and equity index. In order to describe the traffic state more accurately, a tailored traffic model for urban freeway in China is established in the upper model to get the prediction, which considers the speed-limited value on main roadway, and corrects the calculation method of traffic flow state on origin point and exit ramp. The simulation results show the double model is effective to control the incident congestion induced by aggressive behavior.
摘要：
Taking vehicle queue length in urban intersection, traffic flow and signal timing at the present situation as input, the intersection signal timing scheme as output, the minimum network delay as the goal, it constructs a multi - agent traffic signal control system including the execution layer, control layer and decision-making layer. When the queue length in intersection is higher than the setting threshold, the intersection agent is activated. By sending coordination request to the adjacent intersections, based on the NASH equilibrium theory, it looks for the signal timing scheme that is satisfied with the minimum delay time to coordinate intersection agent. If NASH equilibrium has no solution, the network upgrades for management agent coordination and conducts area agent timing coordination according to the historic timing scheme stored in rule base. The simulation analysis shows that TSCA (Traffic Signal Control Agent) system can effectively reduce the overall delay time of the system and the control effect is better.
摘要：
In order to improve traffic safety and protect pedestrians, an improved and efficient pedestrian detection method for auto driver assistance systems is proposed. Firstly, an improved Accumulate Binary Haar (ABH) feature extraction algorithm is proposed. In this novel feature, Haar features keep only the ordinal relationship named by binary Haar features. Then, the feature brings in the idea of a Local Binary Pattern (LBP), assembling several neighboring binary Haar features to improve discriminating power and reduce the effect of illumination. Next, a pedestrian classification method based on an improved deep belief network (DBN) classification algorithm is proposed. An improved method of input is constructed using a Restricted Bolzmann Machine (RBM) with T distribution function visible layer nodes, which can convert information on pedestrian features to a Bernoulli distribution, and the Bernoulli distribution can then be used for recognition. In addition, a middle layer of the RBM structure is created, which achieves data transfer between the hidden layer structure and keeps the key information. Finally, the cost-sensitive Support Vector Machine (SVM) classifier is used for the output of the classifier, which could address the class-imbalance problem. Extensive experiments show that the improved DBN pedestrian detection method is better than other shallow classic algorithms, and the proposed method is effective and sufficiently feasible for pedestrian detection in complex urban environments.
摘要：
Based on NS model, a mixed traffic flow on single lane is simulated in the paper, which includes two-classification vehicles owing the different max-velocity. Take the one move 5 grids for one time as quick-vehicle, which is the results of aggressive behavior, such as overtaking and closely following behavior. And take the one which moves 3 grids for one time as slow-vehicle, which is on behalf of normally driving. The relationship among discrete of traffic flow, traffic density and chaos is researched, in the hope of preparing the solid theoretic basis for eliminating the bad chaos in traffic flow. And based on the distance headway condition and velocity condition, Rear-end accident risk assessment coefficient is advanced to research the influence of aggressive behavior on traffic safety lever on the urban road and on the freeway. The results show that aggressive behavior would emphasis the chaos of traffic flow and the happen opportunity is more, the chaos character in traffic flow is more. And aggressive driving behavior would decrease the safety character of traffic flow. The happen opportunity is more, the value of Rear-end accidents is bigger.
摘要：
Based on NS model, a mixed traffic flow on single lane is simulated in the paper, which includes two-classification vehicles owing the different max-velocity. Take the one move 5 grids for one time as quick-vehicle, which is the results of aggressive behavior, such as overtaking and closely following behavior. And take the one which moves 3 grids for one time as slow-vehicle, which is on behalf of normally driving.
作者机构：
School of Traffic Transportation Engineering,Changsha University of Science & Technology,45 Chiling;Engineering Research Center of Electric Power &Traffic Safety Monitoring & Control and Energy Conser;School of Traffic Transportation Engineering,Changsha University of Science & Technology,Chiling Roa
会议名称：
COTA International Conference of Transportation Professionals(第14届COTA国际交通会议)
会议时间：
2014-07-04
会议地点：
上海
会议论文集名称：
COTA International Conference of Transportation Professionals(第14届COTA国际交通会议)论文集
摘要：
Based on the Traffic-Flow Wave Theory, a traffic flow wave model applicable to urban road incident congestion is proposed in this paper. The model is based on the discrete characteristics of urban congestion traffic flow and is derived from a Velocity-Density linear model. The queuing and dissipation of incident congestion is analyzed based on the new model - both on the existence of traffic controlling measures and on situations without traffic controlling measures - in which the influence from traffic controlling measures is described as interference wave. The results showed that the correct traffic controlling measures could avoid "Domino" phenomenon, prevent the congestion drifting, and reduce the queuing and delay-time.
作者机构：
[Yihu Wu; Wei Yu; Tao Qin; Yifen Li] School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha, Hunan, China;[Dan Yu] Engineering Research Center of Electric Power & Traffic Safety Monitoring & Control and Energy Conservation Technology, Ministry of Education, Changsha University of Science and Technology, Changsha, Hunan, China
通讯机构：
Engineering Research Center of Electric Power & Traffic Safety Monitoring & Control and Energy Conservation Technology, Ministry of Education, Changsha University of Science and Technology, Changsha, Hunan, China
摘要：
In order to ensure stable traffic capacity and avoid incident congestion,a double-layer ramp metering model is proposed in this paper,based on coordination control theory,to predict and control the traffic flow at each on-ramp,when there is incident congestion on the expressway.The function of the lower model is to recognize where the incident congestion exists,based on an adaptive neural network with inputs of traffic flow,velocity and density.The outputs of the lower model are the number of section where the congestion occurs,the number of ramp which should be controlled,and real-time traffic flow information.These outputs should be transmitted to the upper model.The function of the upper model is to design the ramp-metering strategy based on nonlinear theory.The outputs of the upper model are a ramp-metering rate and traffic-flow state after ramp controlling on the expressway.The results of the simulation show that the double-layer ramp metering model could shorten the delay by about 25%,and the variance of the model results is 0.002,which could certify the control strategy is equitable.
作者机构：
School of Traffic Transportation Engineering,Changsha University of Science & Technology,45 Chiling;Engineering Research Center of Electric Power & Traffic Safety Monitoring & Control and Energy Conse
会议名称：
COTA International Conference of Transportation Professionals(第14届COTA国际交通会议)
会议时间：
2014-07-04
会议地点：
上海
会议论文集名称：
COTA International Conference of Transportation Professionals(第14届COTA国际交通会议)论文集
摘要：
Ramp metering is one of the most important parts of freeway traffic control. In this paper, a prediction method based on a nonlinear model is adopted to avoid rapid congestion and big-scale spreading and to predicatively control neighboring ramp traffic volume at congested road sections. Simulated results show that this method has maintained stable vehicle flow of the main line. It not only effectively avoids spreading of traffic congestion, but also maintains a smooth ramp regulation rate.
作者机构：
[Yu, Dan; Cao, Juanjuan; Wu, Yihu; Song, Minglei] School of Traffic Transportation Engineering, Changsha University of Science and Technology, Research Center of Catastrophic Prophylaxis and Treatment of Road and Traffic Safety, Changsha University of Science and Technology, Changsha, 410076, China
通讯机构：
[Yu, D.] S;School of Traffic Transportation Engineering, Changsha University of Science and Technology, Research Center of Catastrophic Prophylaxis and Treatment of Road and Traffic Safety, Changsha University of Science and Technology, China
关键词：
Bus priority;Mixed traffic flow;Newton algorithm;Nonlinear complementarity;Signal timing optimization
期刊：
Research Journal of Applied Sciences, Engineering and Technology,2012年4(20):4022-4027 ISSN：2040-7459
通讯作者：
Yu, D.
作者机构：
[Ma, Jingjing; Song, Minglei; Yu, Dan; Wu, Yihu] Traffic Transportation Engineering, Changsha University of Science and Technology, Changsha, China
通讯机构：
Traffic Transportation Engineering, Changsha University of Science and Technology, China
关键词：
Gauss density function;Overtaking;P-2D-HMM;SMM
