遗传神经网络在温室黄瓜霜霉病预测中的应用

Application of the Combination of Genetic Algorithm and Artificial Neural Network to Prediction of Cucumber Downy Mildew

在神经网络结构的优化、连接权重的训练中采用遗传算法的方法对日光温室黄瓜霜霉病进行预测 ,并对其发生程度进行了拟合 ,计算值与实际值接近 。

Based upon the combination of genetic algorithm and BP neural network, a model to predict cucumber downy mildew was established in this paper. The hidden nodes in neural network and the weights were optimized. The result of training indicates that the prediction values approximate to the real values and the model is feasible in forecasting cucumber downy mildew because it takes the advantages of both traditional neural network and genetic algorithms, and gets rid of their defects.