概率神经网络在烤烟产地分类中的应用

Application of Probabilistic Neural Network to Classification of Producing Areas of Flue-cured Tobaccos

利用基于统计思想和Bayes分类规则的概率神经网络的基本网络模型预测烤烟产地。网络以烤烟的主要化学成分测试数据作为输入,烤烟产地作为输出,对1995年贵州、湖南、山东、河南4省的烤烟进行产地预测。结果表明,概率神经网络能够准确地预测烤烟的产地。

Based on probability statistic theory and Bayes classification rule, probabilistic neural network model was proposed and was applied to classify the producing areas of the fluecured tobaccos. The inputs of PNN were the main chemical compositions of fluecured tobaccos, and the outputs were the codes of the producing areas of the fluecured tobaccos from Guizhou Province and Hunan Province, Shandong Province, Henan Province. The results show that PNN can classify the producing area exactly.