Yu De-xian, Lin Li-feng, Luo Lei, Zhou Wen, Gao Lu-lu, Chen Qing, Yu Shou-yi
Department of Epidemiology, School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou 510515, China.
Nan Fang Yi Ke Da Xue Xue Bao. 2010 Jul;30(7):1604-5, 1609.
To establish a model for predicting the density of Aedes albopictus based on the climate factors.
The data of Aedes albopictus density and climate changes from 1995 to 2001 in Guangzhou were collected and analyzed. The predicting model for Aedes albopictus density was established using the Artificial Neural Network Toolbox of Matlab 7.0 software package. The climate factors used to establish the model included the average monthly pressure, evaporation capacity, relative humidity, sunshine hour, temperature, wind speed, and precipitation, and the established model was tested and verified.
The BP network model was established according to data of mosquito density and climate factors. After training the neural network for 25 times, the error of performance decreased from 0.305 539 to 2.937 51x10(-14). Verification of the model with the data of mosquito density showed a concordance rate of prediction of 80%.
The neural network model based on the climate factors is effective for predicting Aedes albopictus density.
建立基于气候因素的白纹伊蚊密度预测模型。
收集并分析1995年至2001年广州白纹伊蚊密度及气候变化数据。使用Matlab 7.0软件包的人工神经网络工具箱建立白纹伊蚊密度预测模型。用于建立模型的气候因素包括月平均气压、蒸发量、相对湿度、日照时数、温度、风速和降水量，并对建立的模型进行测试和验证。
根据蚊虫密度和气候因素数据建立了BP网络模型。神经网络训练25次后，性能误差从0.305 539降至2.937 51×10(-14)。用蚊虫密度数据对模型进行验证，预测符合率为80%。
基于气候因素的神经网络模型对白纹伊蚊密度具有有效的预测作用。
