基于免疫量子粒子群优化的测试代价敏感属性约简算法  

A test-cost-sensitive attribute reduction algorithm based on immune quantum particle swarm optimization

作　　者：谢小军[1,2] 俞春强[3] 王博[1] 何弦[1] 徐章艳[1,2] 

机构地区：[1]广西师范大学计算机科学与信息工程学院,广西桂林541004 [2]广西多源信息挖掘与安全重点实验室,广西桂林541004 [3]广西师范大学网络信息中心,广西桂林541004

出　　处：《计算机工程与科学》2017年第7期1371-1378,共8页Computer Engineering & Science

基　　金：国家自然科学基金(61262004;61363034;60963008;61363034);广西自然科学基金(2011GXNSFA018163;2015GXNSFDA139040);八桂林学者专项基金;广西高校计算与复杂系统重点实验室项目(15202);广西信息科学实验中心项目(20130204);广西师范大学青年基金(2016QN007)

摘　　要：为了解决测试代价敏感属性约简的高效性和准确性问题,提出一种基于免疫量子粒子群优化的最小测试代价属性约简算法。依据条件信息熵和测试代价因素定义适当的适应值函数,将最小测试代价属性约简问题转化为0-1组合优化问题,提出最小属性的属性约简问题是一种具有特殊测试代价的最小测试代价属性约简问题。最后结合量子粒子群和人工免疫方法给出约简算法。实验对比已有的最小属性约简算法和测试代价敏感属性约简算法,实验结果表明本算法是有效的。In order to achieve high efficient and accurate test cost sensitive attribute reduction, we propose an algorithm for minimizing test cost reduction based on immune quantum particle swarm optimization. We define the proper fitness function according to conditional information entropy and test cost factors. The problem of the attribute reduction of the minimum test cost is converted to an optimi- zation problem of 0-1, and the problem of the minimum attribute reduction is equal to the attribute reduction problem of minimum test cost reduction with special test cost. Finally, the reduction algorithm is presented by combining the quantum particle swarm optimization and the artificial immune algorithm. We conduct experiments and compare the proposed algorithm with the existing minimum attribute reduction algorithm and test cost sensitive attribute reduction algorithm. Experimental results prove its effectiveness.

关 键 词：属性约简 测试代价敏感 粒子群优化 适应度函数 最小约简 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]