摘要
以2003年1月至2008年7月南京市某医院的心脑血管逐日就诊人数为样本,首先根据其时间分布特征采用虚拟变量选择包含节假日等的22个非气象因子,然后通过逐步回归法筛选气象因子和非气象因子,得到最终模型的解释变量,采用支持向量机(SVM)回归方法分别构建了南京市心、脑血管疾病预测模型。将就诊人数分为5个等级,通过反查,模型针对心、脑血管疾病在同一等级和差一等级的准确率分别为87.91%和84.62%,实际预测结果较好,证明该模型具有较高的实际应用价值。
Forecast models of cardiovescular and cerebrovescular diseases in Nanjing are separately built. First we select 22 dummy variables including holidays as non-meteorological factors according to the time distributive characters of the daily hospital visit numbers from January 2003 to July 2007.Then we choose meteorological and non-meteorological factors with stepwise regression method so as to obtain the explanatory variables which are finally used to build forecast models based on the SVM regression method.The daily hospital visit numbers are divided into five grades and the results show that the precisions of grade prediction in cardiovascular and cerebrovascular diseases are 87.91%and 84.62%respectively.Therefore, the models perform satisfactorily and can be applied to actual predictions.
出处
《气象》
CSCD
北大核心
2010年第11期82-87,共6页
Meteorological Monthly
基金
江苏省气象科研开放基金项目(K200707)
关键词
心脑血管
SVM
虚拟变量
医疗气象预报
cardiovascular-cerebrovascular diseases
support vector machine（SVM）
dummy variables
medical-meteorological forecast
