MATLAB: How to predict with a classifier inside a MATLAB function block

simulinkStatistics and Machine Learning Toolbox

I have sucessfully created a classification object (e.g. ClassificationSVM). Now I want to use it inside Simulink, i.e.

in a MATLAB function block to predict given specific inputs. How can I achieve this?

Best Answer

This is possible employing saveCompactModel, loadCompactModel and a separate .m file.

In the attachments, there is a dummy example.

Note that some restrictions apply when it comes to generating code from such models:

https://www.mathworks.com/help/releases/R2016b/stats/code-generation-support.html

Related Solutions

MATLAB: How to get the predicted probabilities from “AdaBoostM1” score

The "score" given by "predict" function is a matrix of classification scores indicating the likelihood that a label comes from a particular class, using any of the input arguments in the previous syntaxes.

You could refer to Compact Classification Ensemble "predict" function documentation for more details: https://www.mathworks.com/help/releases/R2020a/stats/compactclassificationensemble.predict.html

As for "AdaBoostM1", you can convert scores into probabilities by assigning string "doublelogit" to the ScoreTransform property of the ensemble object.

That translates to the following code snippet:

>> mdl = fitcensemble(X,Y, "Method", "AdaBoostM1", "ScoreTransform", "doublelogit")
>> [label, problikescore] = predict(mdl,x)

MATLAB: SVM predict

http://www.csie.ntu.edu.tw/~cjlin/libsvm/

Best Answer

Related Solutions

MATLAB: How to get the predicted probabilities from “AdaBoostM1” score

MATLAB: SVM predict

Related Question