入境国际航行船舶外来医学媒介生物风险评估研究及应用  

Application of risk assessment of exotic medical-vector in the international navigation ships

作　　者：裘炯良[1] 孙志[1] 王军[1] 郑剑宁[1] 杨定波[1] QIU Jiong-liang SUN Zhi WANG Jun ZHENG Jian-ning YANG Ding-bo(Ningbo Entry-exit Inspection and Quarantine Bureau , Ningbo 315012, China)

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》2017年第2期123-127,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：目的应用支持向量机模型法评估研究入境国际航行船舶携带输入外来医学媒介生物的风险。方法以中国第2大港、世界第5大港的宁波港作为研究范围,以2014年到港的国际航行船舶为研究对象,对834艘媒介生物阳性船舶和2 151艘媒介生物阴性船舶的33项指标展开调查,采集数据信息。对数据进行清洗及变量筛选后应用R语言编程实现支持向量机模型法建模训练,并以所建模型预测新到港的1 333艘次船舶外来媒介携带风险。结果经过12种支持向量机模型的筛选,以预测精度为判定指标,选定分类器与核函数两个参数分别为"nu-classification"和"高斯函数"的支持向量机模型为最优模型,并构建起基于支持向量机的外来医学媒介生物携带风险与入境国际航行船舶关联因子间的非线性关系模型。模型训练过程的正确分类率为78.89%,通过该模型预测船舶携带外来媒介风险与实际检疫结果的符合率达到82.52%,预测效果良好。结论针对高度不确定的非线性系统,应用支持向量机模型法可实现更加精确的预测功能,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 support vector machines（ SVM） on the risk assessment of exotic medical-vectors in the international navigation ships based on R language. Methods The Ningbo Port as the No. 2 in China and No.5 in the global world was regarded as the researching area,and the arrival international navigation ships in 2014 were regarded as the researching objects. 33 indexes were surveyed for 834 vector-positive vessels and 2 151 vector-negative vessels. SVM model was employed for the training and calculation. 1 333 new-arrival vessels were used for the prediction by the model. Results Twelve SVM models were constructed and compared according to the index of predicting accuracy. Finally,the SVM model with the parameters of nu-classification and Gaussian function was screened out as the optimal model. Then the nonlinear relationship model was fixed between the risks of importing exotic medical vectors and the factors of international navigation ship based on the corresponding SVM. The correct rate of the training was 78. 89%. The predictive condition was good as the according rate attained 82. 52%.Conclusion The relatively exact prediction could be executed based on SVM model,especially for the highly uncertain nonlinear system. So the model can provide the theoretical basis for the risk analysis and alert of health quarantine.

关 键 词：支持向量机 外来媒介 风险预测 R语言 大数据 

分 类 号：R184.3[医药卫生—流行病学]