一种基于信息熵的专家随机挑选算法  

Expert random selection algorithm based on information entropy

作　　者：吴斌[1] 马继涛[1] 邬平[1] 

机构地区：[1]云南省科学技术情报研究院,昆明650051

出　　处：《计算机工程与应用》2016年第5期119-121,178,共4页Computer Engineering and Applications

基　　金：云南省公共科技服务平台建设项目(No.2013DA006)

摘　　要：为合理、公平地从备选库均匀抽取评审专家,根据专家挑选规则引入信息熵测度作为体系中专家挑选的有序度量,依据规则建立基于信息熵的计算约束条件,利用极大熵理论构造专家挑选概率分布函数,并利用拉格朗日算子计算专家挑选的全概率分布,从实际备选库抽取真实的专家挑选数据进行计算实验,年度专家挑选结果呈现随机性质,证明该方法能克服常规随机发生器的周期自相关性,实现专家的均衡挑选。For reasonably and justly selecting evaluation experts from the alternative expert database, the information entropy is introduced as a measure degree of order in the system according to expert selection rules. According to rules, computational constraint conditions are set up based on information entropy, and the probability distribution of expert selection is computed by Lagrange operators. From the practical alternative expert database, the real data of selected experts is extracted to execute computational experiments, the result of annual experts selection shows the random feature, which proves that the method can avoid the cycle-correlated issue of conventional random generators and manage to select experts evenly.

关 键 词：非均衡 极大熵 熵增加 约束条件 拉格朗日 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]