一种基于混合决策树的调度知识获取算法  

Hybrid decision tree-based scheduling knowledge acquisition algorithm

作　　者：王伟达[1] 刘文剑[1] 

机构地区：[1]哈尔滨工业大学机电工程学院,哈尔滨150001

出　　处：《计算机应用研究》2007年第12期54-56,59,共4页Application Research of Computers

基　　金：国防科工委基础科研资助项目(20030119)

摘　　要：提出了一种基于混合决策树的调度知识获取算法。将模拟退火算法融入遗传算法中,作为一种具有自适应变概率的变异操作,构成一种混合优化方法。利用这种混合方法求解在不同调度目标下制造系统的最优特征子集,同时确定控制决策树规模的最优参数;使用决策树评价混合方法中染色体编码的适应度,在得到不同调度目标下的最优特征子集和最优决策树参数后,生成调度知识。仿真实验结果表明,该算法在性能上优于其他算法。A hybrid decision tree （DT）-based scheduling knowledge acquisition algorithm was presented. Genetic algorithm （GA） was combined with simulated annealing （SA） to develop a hybrid optimization method, in which SA was introduced to server as an adaptive mutation with changeable probability. The hybrid method was utilized to resolve the optimal attributes subset of manufacturing system and determine the optimal parameters of DT under different scheduling objectives ; DT was used to evaluate the fitness of chromosome in the method and generate the scheduling knowledge after obtaining the optimal attributes subset and optimal DT＇s parameters. The experimental results demonstrate that the proposed algorithm produces significant performance improvements over other machine learning-based algorithms.

关 键 词：调度知识 特征选取 遗传算法 模拟退火算法 决策树 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]