Simulation Model of Driving Behavior Based on Nonparametric Kernel Density Estimate | |
---|---|
( Volume 3 Issue 2,February 2017 ) OPEN ACCESS | |
Author(s): | |
Yaqi Liu, Zhenxue Liu, Wei Tian, Haibo Wang, Xiaoyuan Wang | |
Abstract: | |
The research on car-following behavior is an important part of microscopic research in traffic flow theory. With the continuous development of Intelligent Transportation System (ITS) and the deepening of big data research, the car-following simulation model based on a series of assumptions and the single control rule has been difficult to meet the precision requirement. In order to overcome the shortcomings of previous car-following models, a real vehicle driving test on a city road was designed and a series of data acquisition equipment, mainly including two experiment vehicles, speedometer and range sensor, were used to collect a variety of driving behavior data. The information mining technology was used to extract the valuable driving behavior information from measured data in this paper. The noise was eliminated by the Nonparametric Kernel Density Estimate (NKDE), and a new simulation model of driving behavior was established based on nonparametric regression. A simulation experiment was designed to verify the validity of the car-following model. The main contents of model validation included acceleration, velocity, relative velocity and relative distance. The measured running state was compared with the simulated result, and the comparison between the measured value and the simulated value can fit well. The simulation results showed that the model can effectively reflect the driving behavior in the car-following process. The research results of this paper can provide new ideas and methods for the study of microscopic traffic flow in the era of big data. The research results are of great significance to improve traffic safety. |
|
Paper Statistics: | Total View : 584 | Downloads : 575 | Page No: 15-19 | |
Cite this Article: | Click here to get all Styles of Citation using DOI of the article. |