Computer Aided Decision-Making System for Staff Promotion Based on Fuzzy Neural Network
-
摘要: 为定量地分析企业员工晋升决策过程的影响因素,用基于实例的模糊神经网络方法,通过划分非模糊化和模糊化输入变量,改进了Takagi-Sugeno模糊模型.用包含求和、求积和求极小运算节点的扩展的pi-sigma神经网络学习算法确定结论参数和前提参数,自适应地从员工数据库中归纳出模糊逻辑关系,建立企业晋升决策的辅助系统.经算例验证准确率达75%以上.Abstract: To analyze the factors influencing staff promotion,the Takagi-Sugen model,a method of fuzzy neural network,was modified.The input variables in the modified model include fuzzy and non-fuzzy ones.An extended pi-sigma artificial neural network algorithm,in which summation,multiplication and minimization nodes are available,was used to determine conclusion and premise parameters,and to summarize the fuzzy logic from staff databases adaptively.An example shows that the accurate rate of the method is over 75%.
-
Key words:
- human resource /
- promotion /
- fuzzy logic /
- neural network /
- decision-making
-
MARCO F.Determinants and consequences of promotions in Britain[J].Oxford Bulletin of Economics and Statistics,2001,63:279-310.[2] LAZEARR P,ROSEN S.Rank-order tournaments as optimum labor contracts[J].Journal of Political Economy,1981,89:841-864.[3] WALDMAN M.Job assignments signalling and efficiency[J].Rand Journal of Economics,1984,15:255-267.[4] MIGROM P,OSTER S.Job discrimination,market forces and the invisibility hypothesis[J].Quarterly Journal of Economics,1987,52:453-476.[5] BERBNHARDT D.Strategic promotion and compensation[J].Review of Economic Studies,1995,62:315-339.[6] PRENDERGAST C.The insurance effect of groups[J].International Economic Review,1992,33:567-581.[7] ROTHSCHID M,STIGLITZ J E.A model of smployment outcomes illustrating the effect of the structure of information on the level and distribution of income[J].Economic Letter,1982,10:231-236.[8] TAKAGI T,SUGENO M.Fuzzy identification of systems and application to modeling and Contro[J].IEEE Trans,1985,SMC-1(1):116-132.[9] DURBIN R,RUMEIHART D.Product unit:a computationally powerful and biologically plausible extension to back propagation networks[J].Neural Computation,1989,1 (1):133-142.
点击查看大图
计量
- 文章访问数: 1343
- HTML全文浏览量: 63
- PDF下载量: 293
- 被引次数: 0