蜀山小道士的blog

%加载数据data = csvread('D:\python\anaconda\kaggle\wine.csv',1);x = data(:,1:13);y = data(:,14);y = y+1;        %标签值必须为正(含有label=0需要进行此步操作)%划分数据集[m,n] = size(x);index = randsample(m,m);x_train = ...

data = csvread('D:\matlab2016a\demo\data\air.csv');%导入数据num = size(data,1);%样本数predictnum = 6;%设置预测记录数train = data(1:num-predictnum,:);%训练样本数test = data((num-predictnum+1):end,:);%测试样本数%做累加for ...

NOGM(1,1)基本思想: PSO优化初始条件, 即：  data = csvread('D:\matlab2016a\demo\data\air.csv');num = size(data,1);predictnum = 6;train = data(1:num-predictnum,:);test = data((num-predictnum+1):end,:);...

LSSVM - Regression(注意：将LSSVM工具箱添加到toolbox会造成BPNN网络无法建立])解决办法：将LSSVM路径删去load regressionData.mat;output = output';%划分数据集[value,index] = sort(rand(1,2000));x_train = input(index(1:1800),:);x_...

LSSVM-回归gamma = 100;sig2 = 13;type = 'function estimation';%训练模型[alpha,b] = trainlssvm({x_train,y_train,type,gamma,sig2,'RBF_kernel'});%模型预测predict_train = simlssvm({x_train,y_train,type,gam...

data = csvread('D:\article\demo\seasonal\stl.csv');sample = size(data,1);timespan = 6;imfindex = 3;for i = 1:(sample-timespan)    x(i,:) = data(i:i+timespan-1,imfindex)';endy = data(timespan+1:...

BP网络的特点(优点)非线性映射能力；自适应性；(缺点)梯度下降法需要多次迭代，从而修正权值和阈值，所以训练速度慢；容易陷入局部最优，无法达到全局最小；学习率选择敏感(太小收敛速度慢，太大训练过程不稳定)；极限学习机(ELM)特点在训练过程中无需调整权值和阈值，只需要调整隐含层神经元个数，可获得唯一最优解；学习速度快，泛化性能好；data = csvread...

x_train = x(1:100,:);y_train = y(1:100,:);x_test = x(101:end,:);y_test = y(101:end,:);%数据归一化[train_input,inputps] = mapminmax(x_train');[train_output,outputps] = mapminmax(y_train');%节点设置inp...

EEMD使用手册1.将eemd工具箱放置在toolbox文件夹下2.在matlab主界面，点击"设置路径" - "添加文件夹" - 将eemd路径加入 - 保存 函数调用方法imfs = eemd(ts,Nstd,NE);注: ts(要分解的时间序列)       Nstd(高斯白噪声标准差,0.01-0.4)       NE(设置添加噪声的次数,取50或100次...

load data input output%划分数据集random_num = rand(1,2000);[value,index] = sort(random_num);x_train = input(index(1:1800),:)';y_train = output(index(1:1800));x_test = input(index(1801:2000),:)';y_t...

load data input output%划分训练集random_num = rand(1,2000);[value,index] = sort(random_num);x_train = input(index(1:1800),:)';y_train = output(index(1:1800));x_test = input(index(1801:2000),:)';y_t...

                                Matlab(小波神经网络时间序列预测)时间序列数据66 64 60 58 17 49 34 17 8 53 15 15 45 57 33 42 8 52 24 29 -13 37 37 4 32 38 68 77 95 119 161 184 276 247 251 193 226 213 195 182 166 188 1...

优化GM(1,1)主要的改进手段：优化微分方程的初始条件  data = csvread('D:\matlab2016a\demo\data\air.csv');num = size(data,1);predictnum = 6;train = data(1:num-predictnum,:);test = data((num-predictnum+1):end,:);...