BP神经网络在新城疫预测研究中的应用

Study on BP Neural Network in the Prediction of Newcastle Disease

对气象条件和新城疫发病率进行相关性分析,结合动物流行病学理论确定影响新城疫发病的关键气象因素。利用Matlab软件进行BP(Back-propagation)神经网络预测模型构建,计算预测值与实际发病率的误差绝对值和决定系数R2对所建预测模型进行检验。结果表明将6种气象因素作为预测研究的关键气象因子,BP神经网络模型其决定系数R2=0.760,证实预测效果较好。初步构建出新城疫发病的神经网络预测模型,探索性地将BP神经网络理论在动物疫病预测研究领域中运用,为进一步展开动物疫病预测的研究提供理论参考。

The purpose of this paper is to investigate the correlation between meteorological factors and Newcastle disease morbidity, and to determine the key factors that affect Newcastle disease. Having built BP neural network forecasting model by Matlab 7. 0 software, we tested the performance of the model according to the coefficient of determination （R^2） and absolute values of the difference between predictive value and practical morbidity. The results showed that 6 kinds of meteorological factors were determined, and the model＇s coefficient of determination was 0. 760, and the performance of the model was very good. Finally, we built Newcastle disease forecasting model, and applied BP neural network theory in animal disease forecasting research.