人工神经网络在外来医学媒介生物输入风险评估中的应用研究  

Application of back propagation neural network on the risk assessment of exotic medical-vector

作　　者：裘炯良[1] 孙志[1] 王军[1] 郑剑宁[1] 卢岳云[1] 

机构地区：[1]宁波出入境检验检疫局,浙江宁波315012

出　　处：《中华卫生杀虫药械》2016年第5期456-460,共5页Chinese Journal of Hygienic Insecticides and Equipments

基　　金：国家质检总局科技计划项目(编号:2012B172)

摘　　要：目的探索BP人工神经网络在入境航空器外来医学媒介生物输入风险评估中的应用研究。方法采用8×1×1结构的三层BP神经网络模型,对2014年飞抵宁波空港口岸的2 760架次国际通行航空器进行抽样、数据训练和验证分析,并以建立的人工神经网络模型预测新到港的航空器外来医学媒介生物的携带风险。结果经过50余次迭代训练,训练过程的误判率为0.014,平均误差为0.066。应用该神经网络模型预测航空器携带外来媒介情况与实际结果的符合率达到90.0%,预测效果良好。结论针对高度不确定的非线性系统,应用BP人工神经网络可实现相对精确的预测功能,为国境卫生检疫风险评估及预警方面的研究提供理论基础。Objective To apply the back propagation neural network（ BPNN） on risk assessment of exotic medicalvector captured in the international navigation aircrafts. Methods The back propagation neural network with the structure of 8 × 1 × 1 was employed for the calculation. 2 760 aircrafts arrived at Ningbo airport in 2014 were sampled,data-trained and verified with the BP neural network. The messages about new arrival aircrafts were used for the prediction by the network. Results After over fifty time of iteration,misclassification rate of the training was 0. 014 with the 0. 066 average error. The predictive condition was good as the according rate attained 90. 0%. Conclusion The relatively exact prediction could be executed based on BP neural network,especially for the highly uncertain nonlinear system. So the network can provide the theoretical base for the risk analysis and alert of health quarantine.

关 键 词：航空器 神经网络 外来媒介 预测 SAS 

分 类 号：R184.3[医药卫生—流行病学]