calculating accuracy and confusion matrix

211 views (last 30 days)
saeeda saher
saeeda saher on 20 Jun 2018
I have used Classification Learner app for classifying 7 classes(happy, sad, angry, disgust, neutral, fear, surprise) I trained the model using SVM on the training set. Then used the trained model on the test set, it provided me labels as result, I want to calculate the accuracy rate and confusion matrix for the test set. Please help me to code it. I am new to MATLAB, and don't know how to code it.
  1 Comment
Mohd Syamizal Mohd Isa
Mohd Syamizal Mohd Isa on 9 Jul 2020
i have the problem like you, do you have the solution???

Sign in to comment.

Answers (1)

Stephan
Stephan on 20 Jun 2018
Edited: Stephan on 20 Jun 2018
Hi,
to compute the confusion matrix use:
confusionmat
command. Some examples are given in the confusionmat documentation.
If you have a Neural Network Toolbox™ license, you can plot the confusion matrix using
plotconfusion
which is described here.
For calculation of the accuracy you could calculate the error from your crossvalidated model using
crossval
command at first and then calculate the error in form using the
kfoldloss
command. This gives you the error from your test set for your model which should mean:
accuracy = 1 - kfoldloss
These steps are shown with examples here.
Best regards
Stephan

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!