论文部分内容阅读
目的应用决策树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。方法以中国第二大港、世界第五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850艘媒介生物阳性船舶和2 183艘媒介生物阴性船舶的33项指标展开调查。应用决策树模型法建模训练与验证,并以所建模型预测新到港的1 364艘次船舶外来媒介携带率。结果模型筛选出船舶总吨、净吨、船龄、到达季节、船型、船员类型、SSC证书签发天数等7个有效预测变量。训练获得的决策树共有12个有效叶节点,对应12条分类规则。训练过程的正确分类率为73.74%,验证过程的正确分类率为72.30%。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82.70%,预测效果良好。结论针对高度不确定的非线性系统,应用决策树模型法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 assess the risk of carrying imported exotic medical vectors on board an international voyage vessel using a decision tree model. Methods Taking Ningbo Port, the second largest port in China and the fifth largest port in the world as the research area, taking the international voyages to Hong Kong in 2014 as the research object, 33 of the 850 medium bio-positive vessels and 2 183 medium bio-negative vessels Indicators to investigate. The model training and verification were carried out by using the decision tree model method. The model was used to predict the carrier rate of 1 364 foreign carriers in new arrivals. Results The model selected seven effective predictors such as gross tonnage, net tonnage, age of vessel, season of arrival, type of vessel, type of crew, number of SSC certificates issued. The training decision tree has 12 valid leaf nodes, corresponding to 12 classification rules. The correct classification rate of the training process was 73.74%, and the correct classification rate of the verification process was 72.30%. According to the model, the coincidence rate of risk of carrying foreign vectors and actual quarantine results reached 82.70%, and the forecast effect is good. Conclusion For highly uncertain nonlinear systems, the application of decision tree model can achieve relatively accurate prediction function and provide a theoretical basis for the research on the assessment and early warning of the frontier health quarantine risk.