Fuzzy CART

Generates fuzzy rules of fuzzy inference system (FIS) using CART algorithm and ANFIS training

Description

The archive includes genfis4.m that generates Mamdani- and Sugeno-type FIS using CART algorithm to extract fuzzy rule information from data set. It is based mostly on Fuzzy Logic Toolbox but it has required to modify Toolbox's fuzzy rule building principle. As a result some original m-files was adapted for this new fuzzy rule structure. They are marked with the last 'x' symbol and included in the archive (e.g., getfisx.m, evalfisx.m etc.) Though some Toolbox's m-files still work (e.g., addvar.m, plotmf.m etc.)

 

Remarks:

- before you start you should create MEX files by commands:
mex src/evalfisxmex.c
mex src/anfisxmex.c

- you need Statistics Toolbox to implement CART algorithm;

- if you want to use your own decision tree algorithm you need to rewrite treeinfo.m;

- see example.m for fuzzy CART usage.

Known problems:

- it supports only regression tree without missing values for predictors and the response;

- it doesn't work if the resulting tree consists only one node (leaf);

- if some predictors are encountered in none of the branch nodes you can't use ANFIS training (evalfisx.m still works).

• Required Products: Fuzzy Logic Toolbox; Statistics Toolbox
• MATLAB release: MATLAB 7.8 (R2009a)

[nazar dikhil]

please Iam need the matlab code of anfismex function

[Roji]

Thank-you Konstantin.

[Roji]

 

[Konstantin Sidelnikov]

2Roji:
it would be better if you provided your data set or M-file, for which the described effect is observed.

[Roji]

Dear Konstantin,

Just one question. When running your code on the sample results are very satisfactory. The code works perfectly well. The problem comes when using c_cart and evalfisx with new data (let´s call it newdata, and it is an out of sample data). The outout obtained by "evalfisx(newdata, c_cart)" looks very weird. Why does it happen? The output sample I use to train the fis_cart and c_cart is between 1 and 5, but the out of sample output from c_cart (the new data for the inputs is never above prior up and low bonds) is a high negative number.

Thank-you.

Kindest Regards,

Roji

[Roji]

Great.

Thank-you Konstantin.

[Konstantin Sidelnikov]

Thanks for a positive assessment of my work.
As for your question, Roji, yes, here 2 corresponds to the number of FIS inputs.
Theoretically, the number of inputs can be arbitrary.

[Roji]

Dear Konstantin,

An amazing collection of functions that should be part of the Matlab;s suite for Fuzzy Logic. Thank-you very much.

Just one question. This piece of code:

for ind = 1 : 2
fis_cart = setfisx(fis_cart, 'input', ind, 'range', bounds(ind, :));
end

"1:2" stands for inputs 1 and 2? I mean, in case we want to use your code to use more inputs, for instance 5, should we change that by "1:5"?

Best Regards, and thanks again for your work.

Roji