What work space values do i need to save separately to test Classification
What work space values do i need to save separately to test Classification of a number of voice emotion recognition neural networks and compare a new input against several to give a result? TrainingHappyInput = NNHappyTrainingInput; TragetHappy= ones(1,1536); % set to Happy = 2 TragetHappy=TragetHappy*2; net = newff([min(TrainingHappyInput) max(TrainingHappyInput)],[14 1],{'tansig' 'purelin'},'traingd'); net.trainParam.epochs = 2900; %Maximum number of epochs to train net.trainParam.goal = 0.01; %Performance goal net.trainParam.lr = 0.01; %Learning rate net.trainParam.min_grad=1e-10; %Minimum performance gradient net.trainParam.show = 25; %Epochs between displays net.trainParam.time = inf; %Maximum time to train in seconds HappyTestset=TrainingHappyInput(400:700); NetOutputHappyTestData = sim(net,HappyTestset); subplot(2,1,1), plot(TrainingHappyInput(400:700),TragetHappy(400:700),HappyTestset,NetOutputHappyTestData,'o') title('Accuracy of classification'); HappyDiffTraining = TragetHappy (400:700)- NetOutputHappyTestData; subplot(2,1,2), plot(HappyDiffTraining); title('Difference Between Trained/Targets'); HappyClassifiedTrained = mean(NetOutputHappyTestData); if HappyClassifiedTrained > 1.8078 disp('Emotion detected is HAPPY...!'); else disp('Not Classified as Happy'); end This is the code I currently have for a Happy emotion and will have a similar network for sad etc. Having never studied Matlab or signal processing to finish this project I need to test a voice sample against the neural networks and output which emotion has been detected. Happy is Target is set to 2 as in the code, sad will be 3, neutral 1 etc. I don't know what variables i need to collect from each workspace and how to compare a test sample to all the networks and have a decision produced. I think it will be similar to the if statement at the end of the code above but can't work what I need to do.
Prashant Kumar answered .
2025-11-20
When you're testing a classification model in MATLAB, you should save the following workspace values separately to ensure you have all the necessary components:
1. Trained Model: Save the trained classification model object.
save('trainedModel.mat', 'trainedModel');
2. Test Data: Save the test features and test labels.
save('testData.mat', 'X_test', 'Y_test');
3.Preprocessing Parameters: If you performed any preprocessing (e.g., normalization), save the parameters used for preprocessing.
save('preprocessingParams.mat', 'mean_X', 'std_X');
4. Feature Selection: If you used feature selection, save the indices of the selected features.
save('selectedFeatures.mat', 'selectedFeatureIndices');
5. Performance Metrics: Optionally, save any performance metrics you calculated.
save('performanceMetrics.mat', 'accuracy', 'precision', 'recall');
By saving these key elements, you ensure that you can recreate the testing environment and validate the performance of your classification model.