基于PCA-FBP的绩效综合评价研究  

Research of Performance Comprehensive Evaluation Based on PCA- FBP

作　　者：朱健[1,2] 任秋阳[1,2] 卢秉亮[3] 

机构地区：[1]沈阳航空职业技术学院,沈阳110034 [2]沈阳飞机工业(集团)有限公司,沈阳110034 [3]沈阳航空航天大学计算机学院,沈阳110136

出　　处：《微处理机》2015年第5期54-56,60,共4页Microprocessors

基　　金：辽宁省教育科学"十二五"规划2014年度立项课题(JG14EB238)

摘　　要：将系统论、信息论、计算机技术、工程技术思想引入评价领域,产生了一系列新的评价方法。BP神经网络通过训练来得到被评对象的价值模型,可以有效解决非线性综合评价问题。通过合理选取评价指标,利用主成分分析降低变量的维数,提出了一种基于PCA-FBP的员工绩效评价模型,通过自组织映射网络SOM,完成了评价结果分组,提高了评价结果的客观性。实验结果表明,该方法可以较好的逼近专家评价结果,降低了神经网络模型的复杂度,提高了神经网络模型的效率。At present, the system theory, information theory, computer technology and engineering technology are referred in the evaluation method. BP neural network, getting the rated value objects by training, can effectively solve the problem of nonlinear comprehensive evaluation. In this paper, the evaluation indicators is selected reasonably, the principal component analysis is used to reduce the dimensions of the variables, and the employee performance evaluation model is proposed on the basis of PCA - FBP. With Self - Organizing feature Map （ SOM ）, the grouping of the evaluation results is completed and the objectivity of evaluation results is improved. The test results show that it approaches to the evaluation results of the experts, reduces the complexity of neural network model and improves the efficiency of the neural network model.

关 键 词：绩效评价 主成分分析 人工神经网络 BP神经网络 聚类 模糊数学 

分 类 号：TP398.1[自动化与计算机技术—计算机应用技术]