将训练集与测试集数据进行归一化；

建立GRNN或PNN神经网络；

利用建立好的神经网络对测试集中的26个乳腺组织样本的类型进行预测；

计算预测正确率（不必计算每类的正确率，只需计算正常或者病变两类的正确率，即只要预测结果与真实值属于同一大类，则认为是正确，否则认为预测错误）-The training set and test data set is normalized

Establish GRNN or PNN neural network

The use of well-established neural network test set 26 breast tissue samples of the type of forecast

Calculate the correct prediction rate (necessary to calculate the correct rate for each class, or simply calculate the normal two types of lesions in the correct ratio, as long as



Predictions and actual values belong to the same category, then that is correct, or that the prediction error)