基于信息再利用的灰色系统GM(1,1)模型在梅毒流行趋势预测中的应用  被引量:1

The application on the GM(1,1)model based on re-used information to predict syphilis incidence trend

在线阅读下载全文

作  者:韩丹[1] 郭华娟 温瑞[1] 

机构地区:[1]河南开封市疾病预防控制中心,开封475000 [2]河南开封市妇幼保健院,开封475000

出  处:《中国艾滋病性病》2013年第8期596-598,共3页Chinese Journal of Aids & STD

摘  要:目的探讨基于信息再利用的灰色预测系统模型GM(1,1)在预测梅毒疫情流行趋势上的应用,为进一步制订和完善梅毒防控措施提供参考依据。方法收集开封市2005-2012年的梅毒疫情数据,将其按照灰色系统理论利用收集数据,建立基于信息再利用的GM(1,1)模型,并和传统的GM(1,1)模型比较,预测开封市梅毒疫情的流行趋势。结果 2005-2012年,开封市梅毒呈逐年上升趋势,且上升态势越来越明显,特别是2012年增幅明显,呈现出非单调增长趋势。基于信息再利用方法,得出的平均相对误差为8.559 6,与传统方法的平均相对误差12.120 5比较,精度大为提高。结论基于信息再利用的方法建立的GM(1,1)模型,保持了传统方法建立模型的计算简便的优点,又提高了模型的拟合精度和预测精度,可以更为精准地预测开封市梅毒疫情流行趋势。Objective Probing into the application on the GM(1,1)model based on re-used information to predict syphilis incidence trend,and providing evidence for further formulating and perfecting prevention and control of syphilis.Method Collecting syphilis incidence data of Kaifeng from 2005to 2012,and then recollecting the data by using the grey system theory.The trends of syphilis incidence in Kaifeng was predicted by establishing the comparison between the traditional GM(1,1)model and the GM(1,1)model based on re-used information.Results The incidence of syphilis in Kaifeng was upward from 2005-2012,and was obvious year by year,especially presented a nonmonotone increasing trend in 2012.Based on the re-used information,an average relative error of 8.559 6was concluded.Compared with the average relative error of 12.120 5in the traditional method,the accuracy was greatly improved.Conclusion The GM(1,1)model based on information re-use can not only improve the fitting and prediction accuracy,but also reserve the advantage of easy calculation of traditional model,it can be used to predict the trend of syphilis incidence in Kaifeng.

关 键 词:灰色系统 GM(1 1)模型 梅毒 流行趋势预测 

分 类 号:R181.8[医药卫生—流行病学] R759[医药卫生—公共卫生与预防医学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象