I need help about the imbalanced data

i have a data set , but i couldn't manage to get a good solution . I will be apprecite if you help me to handle imbalanced data. Thanks a lot

Answer 1

[KSSV]

Read about readtable.

After reading you can access the rspective columns using T.T1, T.T2 etc... or T.(1), T.(2) etc.

T = readtable('https://in.mathworks.com/matlabcentral/answers/uploaded_files/744984/data.xlsx')

T = 500×9 table
     T1      T2      T3      T4      T5      T6      T7      T8     RESULT
    ____    ____    ____    ____    ____    ____    ____    ____    ______

    12.5    6.25    1.05      11       3     1.3    1.75     1.6      3   
     2.7     2.7     2.2    3.35    1.75     2.8    1.55     1.8      2   
     2.5     2.9     2.2     3.2    1.75       3    1.65     1.7      3   
     2.5     2.9     2.2    3.05    1.85     2.8    1.45    1.95      3   
     2.7       3       2     3.5     1.8     2.8    1.65     1.7      2   
     2.5     3.1     2.1    3.05       2     2.8     1.3     2.3      2   
       9       4     1.2     7.5    2.35     1.6    1.85     1.5      1   
     3.4     3.3    1.65    3.75     2.2    2.15     1.5    1.85      2   
     3.2       3     1.8    3.75     1.8    2.55     1.7    1.65      3   
       8     4.3     1.2       7     2.5     1.5     1.6    1.75      3   
     5.5     3.6    1.35    5.25     2.3    1.75     1.7    1.65      3   
     2.5     3.1     2.1     3.2    1.95     2.7    1.55     1.8      3   
     2.5     2.7     2.3     3.2     1.7    3.05    1.65     1.7      3   
     5.5     4.6    1.25       5     2.6     1.6    1.55     1.8      3   
    6.25    3.75     1.3    5.25     2.4    1.65    1.55     1.8      3   
       4     3.6     1.5    4.25     2.4     1.9    1.35    2.15      3   

[aslan kaya]

it doesn't help me. I have already done this, i have tried neural network but regregerssion is very bad.. Thanks

[KSSV]

What exactly you are trying?

[aslan kaya]

I am trying to get a good workign neural network.. But i couldn't

[KSSV]

Neural network for what?

[aslan kaya]

clear all;

close all;

clc

data=xlsread('data.xlsx');

input=data(:,1:8);

output=data(:,end);

x=input';

t=output';

trainFcn='trainlm';

hiddenLayerSize=[10 8 3];

net=feedforwardnet(hiddenLayerSize, trainFcn);

net.layers(1).transferFcn='tansig';

net.layers(2).transferFcn='tansig';

net.layers(3).transferFcn='tansig';

net.input.processFcns={'removeconstantrows', 'mapminmax'};

net.output.processFcns={'removeconstantrows', 'mapminmax'};

net.divideFcn='dividerand';

net.divideMode='sample';

net.divideParam.trainRatio=70/100;

net.divideParam.valRatio=20/100;

net.divideParam.testRatio=10/100;

net.trainParam.show=25;

net.trainParam.lr=0.001;

net.trainParam.epochs=100;

net.trainParam.goal=0;

net.trainParam.max_fail=50;

net.trainParam.mc=0.9;

net.trainParam.min_grad=0;

net.performFcn='mse';

net.plotFcns={'plotform', 'plottrainstate','ploterrhist','plotregression', 'plotfit'};

[net,tr]=train(net,x,t);

y=net(x);

e=gsubtract(t,y);

performance=perform(net,t,y);

trainTargets=t.*tr.trainMask(1);

valTargets=t.*tr.valnMask(1);

testTargets=t.*tr.testMask(1);

trainPerformance=perform(net,trainTargets,y);

valPerformance=perform(net,valTargets,y);

testPerformance=perform(net,testTargets,y);

a=trainFcn;

b=hiddenLayerSize;

f1=net.layers(1).transferFcn;

f2=net.layers(2).transferFcn;

f3=net.layers(3).transferFcn;

f=trainPerformance;

g=valPerformance;

k=testPerformance;

result=[a,',',num2str(b),',',f1,',',f2,',',f3,',', num2str(f),',',num2str(g),',',num2str(k)];

disp(result)