基于支持向量机模型的河南艾滋病发病率预测

发布时间：2018-04-04 03:57

  本文选题：艾滋病　切入点：支持向量机　出处：《中国现代医学杂志》2017年12期

【摘要】：目的探索适合于河南省艾滋病发病趋势的预测模型,准确、快速地预测未来发病变化趋势,为制定艾滋病预防控制的策略和措施提供参考依据。方法收集河南省2000~2014年艾滋病发病率数据,采用支持向量机模型建立其发病率预测模型。其中2000~2013年发病率数据为训练样本,2014年发病率数据为检验样本。以平均相对误差作为预测效果的评价指标。并用该模型对河南省2015~2019年艾滋病的发病率进行预测。结果建立的支持向量机模型的平均相对误差为0.5512%。经预测,河南省2015~2019年艾滋病的发病率分别为0.85/10万、1.84/10万、1.64/10万、1.30/10万、2.01/10万。结论支持向量机模型有较高的预测精度及较小的预测误差,适用于河南省艾滋病的发病率预测。
[Abstract]:Objective to explore a prediction model suitable for the trend of HIV / AIDS incidence in Henan province, and to predict the trend of future AIDS incidence accurately and quickly, so as to provide a reference for the formulation of HIV / AIDS prevention and control strategies and measures.Methods the data of HIV / AIDS incidence from 2000 to 2014 in Henan Province were collected and the prediction model of AIDS incidence was established by using support vector machine (SVM) model.The incidence data from 2000 to 2013 were training samples, and the incidence data from 2014 were test samples.The average relative error is used as the evaluation index of the prediction effect.The model was used to predict the incidence of AIDS in Henan province from 2015 to 2019.Results the average relative error of the established support vector machine model is 0.5512.It is predicted that the incidence of AIDS in Henan Province from 2015 to 2019 is 0.85 / 100,000 / 100, 000 / 100, 000 / 100, 000 / 100, 000 / 100, 000 or 130 / 100, 000 / 100, 000 or 201 / 100, 000 respectively.Conclusion the support vector machine model has higher prediction accuracy and smaller prediction error, which is suitable for predicting the incidence of AIDS in Henan Province.
【作者单位】： 河南中医药大学;河南中医药大学第二附属医院;中国科学院生物物理研究所;
【基金】：河南省软科学研究重点项目(No:102400440002) 河南省2010年科技发展计划(No:102400440002)
【分类号】：R512.91
，

本文编号：1708261