基于极限学习机的出口食品加工企业检验检疫信用评价研究  

Rating model for inspection and quarantine credit of export food processing enterprises based on extreme learning machine

作　　者：徐胜林[1] 周淑红 仵冀颖[1] 王键[3] 

机构地区：[1]国家质量监督检验检疫总局信息中心,北京100088 [2]标准与技术法规研究中心 [3]上海出入境检验检疫局

出　　处：《计算机时代》2015年第5期4-6,共3页Computer Era

基　　金：质检公益项目"检验检疫业务需求分析方法论及应用技术研究"(201310041)

摘　　要：为全面有效地掌握及整合企业信用信息,国家质检总局建立了一套进出口企业信用管理系统,制定了企业信用管理办法及评价标准。文章在分析出口食品加工企业检验检疫信用评价指标体系的基础上,建立了一种基于极限学习机的检验检疫信用评价模型。实验结果证明,该模型可有效预测企业信用等级,仅需预先确定隐含层神经元数目而无需设置其他参数,减少了人为干扰因素,可为检验检疫信用评价管理提供参考。To control the credit of enterprises comprehensively and effectively, a credit management information system for imports and exports enterprises was constructed by the General Administration of Quality Supervision, Inspection and Quarantine of the People＇s Republic of China （AQSIQ）. Meanwhile, the regularization and evaluation criterion for the credit of enterprises were built. In this paper, a rating model for the inspection and quarantine credit of export food processing enterprises is proposed based on the Extreme Learning Machine （ELM）. The experimental results prove that the model could effectively predict the credit of enterprises. Only the number of neuron in the hidden layer needs to be set manually. Therefore, the artificial factors are decreased. The model could provide a scientific reference for rating the inspection and quarantine credit.

关 键 词：极限学习机 检验检疫信用评价 出口食品加工企业 评价模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]