基于自组织神经网络的建筑市场执业资格人员信用分类研究  

Research on the credit classification of practicing qualification personnel in construction market based on self-organizing neural network

作　　者：范志清[1] 王雪青[2] 李宝龙[2] 

机构地区：[1]国家开发银行天津市分行,天津300072 [2]天津大学管理学院,天津300072

出　　处：《中国工程科学》2011年第9期105-108,共4页Strategic Study of CAE

基　　金：国家自然科学基金资助项目(70772057)

摘　　要：利用自组织神经网络技术,结合建筑市场执业资格人员信用的相关特点,研究了网络中神经元个数的确定、训练步数、网络维数、获胜神经元的领域等对网络结构和执业资格人员信用划分类别的影响,给出了执业资格人员信用分类的网络构造思想和神经网络结构,并以被调查的执业资格人员为例进行了实证研究。研究结果表明,该方法简便、易行,适用于执业资格人员信用分类研究,为开展执业资格人员信用管理奠定了良好的理论方法基础。Combining with the characters of the practicing qualification personnel in construction market,evaluation method based on the self-organizing nerural network is brought out to analyze the credit classification of the practicing qualification personnel.And the impact factors on the credit classification of the practicing qualification personnel,such as the number of neurons,the training steps,the dimension of neurons and the field of winning neurons are studied.Then a self-organizing competitive neural network is built.At last,a case study is conducted by taking practicing qualification personnel as an example.The research result reveals that the method can efficiently evaluate the credit of the practicing qualification personnel;thus,it could provide scientific advice to the construction enterprise to prevent relevant discreditable behaviors of practicing qualification personnel.

关 键 词：执业资格人员 信用 聚类分析 自组织神经网络 

分 类 号：F062.3[经济管理—政治经济学]