GRNN/PNN：基于GRNN、PNN两神经网络实现并比较鸢尾花种类识别正确率、各个模型运行时间对比—Jason niu

load iris_data.mat 

P_train = [];

T_train = [];

P_test = [];

T_test = [];

for i = 1:3 

    temp_input = features((i-1)*50+1:i*50,:);

    temp_output = classes((i-1)*50+1:i*50,:);

    n = randperm(50);

    P_train = [P_train temp_input(n(1:40),:)'];

    T_train = [T_train temp_output(n(1:40),:)'];

    P_test = [P_test temp_input(n(41:50),:)'];

    T_test = [T_test temp_output(n(41:50),:)'];

end

result_grnn = [];

result_pnn = [];

time_grnn = [];

time_pnn = [];

for i = 1:4

    for j = i:4

        p_train = P_train(i:j,:);

        p_test = P_test(i:j,:);

        t = cputime; 

        net_grnn = newgrnn(p_train,T_train);

        t_sim_grnn = sim(net_grnn,p_test);

        T_sim_grnn = round(t_sim_grnn); 

        t = cputime - t;

        time_grnn = [time_grnn t];

        result_grnn = [result_grnn T_sim_grnn'];

        t = cputime;

        Tc_train = ind2vec(T_train);

        net_pnn = newpnn(p_train,Tc_train);

        Tc_test = ind2vec(T_test);

        t_sim_pnn = sim(net_pnn,p_test);

        T_sim_pnn = vec2ind(t_sim_pnn);

        t = cputime - t;

        time_pnn = [time_pnn t];

        result_pnn = [result_pnn T_sim_pnn'];

    end

end

accuracy_grnn = [];

accuracy_pnn = [];

time = [];

for i = 1:10

    accuracy_1 = length(find(result_grnn(:,i) == T_test'))/length(T_test);

    accuracy_2 = length(find(result_pnn(:,i) == T_test'))/length(T_test);

    accuracy_grnn = [accuracy_grnn accuracy_1];

    accuracy_pnn = [accuracy_pnn accuracy_2];

end

result = [T_test' result_grnn result_pnn]

accuracy = [accuracy_grnn;accuracy_pnn]

time = [time_grnn;time_pnn]

相关知识

Dataset之IRIS：鸢尾花(Iris)数据集的简介、下载、使用方法之详细攻略
基于机器学习的落叶松毛虫发生面积预测模型
基于神经网络的农业病虫害损失预测
基于matlab的神经网络的农业病虫害损失预测
cnn神经网络虫害预测
【中科院1区】花朵授粉算法FPA
基于神经网络——鸢尾花识别（Iris）
BP神经网络鸢尾花红酒数据分类分析与源码实现
基于深度卷积神经网络的移动端花卉识别系统
基于机器学习的鸢尾花数据集的三分类算法的实现 C++

网址: GRNN/PNN：基于GRNN、PNN两神经网络实现并比较鸢尾花种类识别正确率、各个模型运行时间对比—Jason niu https://www.huajiangbk.com/newsview1354209.html