Hi sweet,
You can train an SVM classifier to classify your data using the 'fitcsvm' function in MATLAB. You can organize your features 'X' as a matrix where each row corresponds to observation, and each column represents a feature. Similarly prepare labels 'Y' as a vector where each element corresponds to the class label for the respective row in 'X'. Use 'fitcsvm' function to train the SVM. For the gaussian distributed features, you may want to use an RBF kernel as follows
% X and Y as matrix of predictor data and array of class labels respectively
SVMModel = fitcsvm(X, Y, 'KernelFunction', 'rbf', 'Standardize', true, 'ClassNames', [-1, 1]);
Once the classifier is trained you can use it to classify new data as follows:
[label,score] = predict(SVMModel,newX);
Additionally you can refer to useful MathWorks documentation on Training SVM classifiers:
svm for binary classification: https://www.mathworks.com/help/stats/support-vector-machines-for-binary-classification.html#bsr5o09
Hope this helps!
