检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:曲波[1] 黄德生[1] 郭海强[1] 关鹏[1] 周宝森[1]
机构地区:[1]中国医科大学公共卫生学院流行病与卫生统计教研室,沈阳110001
出 处:《中国媒介生物学及控制杂志》2005年第6期450-452,共3页Chinese Journal of Vector Biology and Control
基 金:国家自然科学基金资助项目(30170833)
摘 要:目的探讨虫媒传染病斑疹伤寒和流行性乙型脑炎(乙脑)的发病率与气象因素的关系,建立反馈(BP)神经网络预测模型,并评价模型的效果。方法利用SPSS10.0统计软件进行气象因素与斑疹伤寒和乙脑发病率的相关分析;利用Matlab6.5软件构建乙脑和斑疹伤寒发病率的BP人工神经网络预测模型。结果相关分析结果显示乙脑的发病率与平均气压呈负相关(P<0.01),与平均蒸发量和最高温度呈正相关(P<0.05)。斑疹伤寒的发病率与平均气温和平均地面温度呈负相关(P<0.05)。斑疹伤寒的发病率还与最低温度呈负相关(P=0.062)。BP神经网络模型的回代结果显示,乙脑和斑疹伤寒发病率拟合模型平均误差率(MER)和决定系数(R2)分别为27.44%和98.09%及29.00%和65.35%,模型拟合效果较好。应用BP神经网络模型对1994年乙脑和斑疹伤寒发病率进行预测,其相对误差分别为80.00%和120.86%,模型的预测效果一般。结论平均气压、平均蒸发量、温度对虫媒传染病的发病率影响较大。应用BP神经网络模型对虫媒传染病的发病率具有一定的拟合和预测能力,值得进一步研究。Objective To investigate the relationship between meteorological factors and incidence of arbo infectious disease,including endemic encephalitis B and endemic typhus,to built the Back-Propagation artificial neural network model and evaluate it. Methods The data of incidence of cerebrospinal meningitis and meteorological factors from 1981 to 1994 were collected and analyzed by SPSS for windows version 10.0 ; The model of Back-Propagation artificial neural network was built by Matlab, version 6.5. Results The incidences of endemic encephalitis B was negative correlated to annual mean atmospheric pressure ( P (0.01), and was positive correlated to annual mean evaporation and the maximum temperature ( P (0.05). The incidences of endemic typhus was negative correlated to annual mean temperature, the groud temperature( P (0.05) and the minimum temperature (P = 0. 062). The MER and R2 of endemic encephalitis B and endemic typhus model were 27.44 %, 98.09 % and 29.00 %, 65.35 % respectively. The relative error of endemic encephalitis B and endemic typhus was 80.00 % and 120.86% respectively. Conclusion The incidence of arbo infectious disease is correlated to atmospheric pressure, evaporation, and temperature. The BP neural network model fits commonly for the study of arbo infectious diseases and needs further study.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.145