基于粗糙集的区域交通控制交通量属性约简

交通量属性的有效约简能够大大减少方案选择式城市区域实时交通控制系统在线SVM分类计算的计算量,是实现这种实时交通控制方式的关键一步。在遗传算法初始种群的产生和变异中引入了混沌算法,并提出了“混沌变异”的概念,由此构造了混沌遗传算法。将混沌遗传算法用于粗糙集的属性约简,并在构造适应度函数时引入了粗糙集理论的“支持度”。在初始种群的产生、交叉和变异算法中均采用约简的可辨别下三角矩阵判断个体的可行性。最后将所开发的粗糙集混沌遗传属性约简算法用来对城市区域交通控制交通量属性进行约简。仿真计算结果表明:所开发的粗糙集混沌遗传属性约简算法能有效地解决交通量的属性约简问题。

Attribute Reduction to Traffic Flow in Area Traffic Control Based on Rough Sets

For area traffic control based on choosing project,the attribute reduction to traffic flow in an urban area could reduce the computing works in real-time,and which is a key step in carrying out this kind of control mode.A chaotic algorithm approach and a concept about chaos variation were introduced in producing population and variation algorithm of genetic algorithm approach,and then a chaotic and genetic algorithm approach was developed and used in attribute reduction in rough sets,and the support degree in rough sets theory was introduced in constructing fitness function,and the discriminability lower triangular-matrix was used to judge the feasibility of each individuals.At last,the chaotic and genetic knowledge-reduction approach was used in attribute reduction to traffic flow,and the simulation result shows that this algorithm can find the minimal reduction.