计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (8): 223-225.

• 工程与应用 • 上一篇    下一篇

基于贝叶斯正则化神经网络虚拟企业敏捷性评价

缪 宁1,2,邓小珍3,刘文远2,王宝文2   

  1. 1.天津财经大学 珠江学院 计算机系,天津 301811
    2.燕山大学 信息科学与工程学院,河北 秦皇岛 066004
    3.赣州卫生学校,江西 赣州 341000
  • 收稿日期:2007-07-09 修回日期:2007-11-19 出版日期:2008-03-11 发布日期:2008-03-11
  • 通讯作者: 缪 宁

Agility evaluation of virtual enterprise based on BR neural network

MIAO Ning1,2,DENG Xiao-zhen3,LIU Wen-yuan2,WANG Bao-wen2   

  1. 1.Department of Computer Science,Pear River College,Tianjin University of Finance and Economics,Tianjin 301811,China
    2.Institute of Information Science and Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China
    3.Gangzhou Health School,Gangzhou,Jiangxi 341000,China
  • Received:2007-07-09 Revised:2007-11-19 Online:2008-03-11 Published:2008-03-11
  • Contact: MIAO Ning

摘要: 高敏捷性是虚拟企业适应不断变化的市场必备的素质,如何对它进行准确评价是虚拟企业运行中的重要问题,针对此问题先对虚拟企业及其盟员敏捷性之间的关系分析,然后提出在已知虚拟企业盟员敏捷性的基础上用贝叶斯正则化神经网络来计算虚拟企业的敏捷性,最后通过仿真试验测试了该方法的可行性。实验结果证明与非正则化神经网络相比,贝叶斯正则化神经网络的泛化能力强,评价数据结果稳定。该方法可用于各种规模的虚拟企业评价。

Abstract: To study how to measure Agility of Virtual Enterprise(VE),the relationship between VE and its member is analyzed first.Based on it,a new method using Bayesian Regularization Neural Network(BRNN) for Agility Evaluation of Virtual Enterprise is developed.A simulative example illustrates the usefulness of the proposed method.In contrast to the non regularization neural net work,the result shows that BRNN overcomes the over-fitting problems,it can be used to measure any size of VE.