摘要
应用模糊理论和机器学习方法,通过对到达车辆数目的模糊分类,将不同车辆数目到达情况下的信号控制决策方案以规则集的形式存储在知识库中,在交通信号控制过程中使用遗传算法对规则集进行改进.经过仿真实验,对该方法的控制效果与定时控制和感应控制进行了模拟比较,仿真实验的结果说明该方法的控制效果明显优于传统控制方式.
Fuzzy theory and machine learning are applied in this paper. Through fuzzy classifying the number of arrived cars, the decision schemes of signal control are put into knowledge-database in the form of rule-set under different conditions of cars' arriving. The genetic algorithm is used to improve the rule-sets during the process of traffic signal controlling. After simulating, the control effects of this new approach,the fixed-time control method and the actuated control method are compared. The result of simulating illustrates that the effect of the new approach is obviously better than the traditional ones.
出处
《系统工程学报》
CSCD
北大核心
2005年第1期23-29,共7页
Journal of Systems Engineering
关键词
交通信号控制
机器学习
遗传算法
模糊分类
traffic signal control
machine learning
genetic algorithms
fuzzy classify