基于改进的非线性GM(1,1)模型的职业病预测研究

摘要

为了更准确地预测职业病,在传统GM(1,1)模型的基础上,提出改进的非线性GM(1,1)模型,在传统的GM(1,1)模型中引入弱化算子,将紧邻均值与原始数据之间的线性假设改为非线性假设,提高曲线的拟合度.以2005—2014年的全国职业病例数为研究对象,进行数据拟合和预测分析,其中以2014年职业病例数作为验证数据,并利用后验差比值和小误差概率2个参数,检验该改进模型的预测精度.由应用实例的分析结果可知:在职业病发病趋势的预测方面,改进的非线性GM(1,1)模型的预测精度提高到一级,曲线拟合度较高,预测得到2015年的职业病例数为34900例.%In order to predict the occupation diseases more accurately, on the basis of the traditional GM (1,1) model, an improved nonlinear GM (1,1) model was proposed.The weakening operator was introduced into the traditional GM (1,1) model, and the linear hypothesis between the consecutive neighbors mean and the original data was changed into the nonlin-ear hypothesis, so as to improve the fitting degree of curves.Taking the case numbers of occupational diseases from 2005 to 2014 in China as the research object, the data fitting and prediction analysis were conducted, in which the case number of occupation diseases in 2014 was used as the verification data, and the posteriori error ratio and small error probability were used to test the prediction accuracy of the improved model.The results showed that in the prediction on the incidence trend of occupational diseases, the prediction accuracy of the improved nonlinear GM (1,1) model was improved to the first level, the fitting degree of curve was relatively high, and the case number of occupational diseases in 2015 was predicted to be 34900 cases.