论文部分内容阅读
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。
Objective To explore a prediction model suitable for the trend of HIV / AIDS in Henan Province, predict the trend of future incidence accurately and rapidly, and provide reference for formulating strategies and measures for AIDS prevention and control. Methods The incidence of HIV / AIDS in Henan Province from 2000 to 2014 was collected. The prediction model of incidence was established by using support vector machine model. Including 2000 to 2013 incidence data for the training samples, 2014 incidence data for the test sample. The average relative error is used as the evaluation index of the prediction effect. And use this model to predict the incidence of AIDS in Henan Province from 2015 to 2019. Results The average relative error of SVM model was 0.5512%. It is estimated that the incidence of AIDS in Henan Province from 2015 to 2019 is 0.85 / 100,000, 1.84 / 100,000, 1.64 / 100,000, 1.30 / 100,000, and 2.01 / 100,000 respectively. Conclusions Support vector machine model has higher prediction accuracy and smaller prediction error, which is suitable for predicting the incidence of AIDS in Henan Province.