线性SVM的特征权重（Matlab中的fitcsvm）

Question

我有以下交叉验证线性SVM的实现。我想知道哪个输出变量代表特征权重，因此特征的相关性？在存储训练分类器参数的“cl”变量中，我找到变量“W”和“alpha” - 据我所知，alpha表示分类器系数 - 因此alpha是反映每个分类器重要性的变量特征？在我的情况下，“W”似乎对于每个条目几乎为零，而alpha在0和1之间，通常等于1.

%% SVM-Classification
nrFolds = 10; %number of folds of crossvalidation, 10 is standard
kernel = 'linear'; % 'linear', 'rbf' or 'polynomial'
C = 1; % C is the 'boxconstraint' parameter. Small C = Allow for more missclassif.
solver = 'L1QP';

cvFolds = crossvalind('Kfold', labels, nrFolds);


for i = 1:nrFolds                            % iteratre through each fold
    testIdx = (cvFolds == i);                % indices of test instances
    trainIdx = ~testIdx;                     % indices training instances

    % train the SVM
    cl = fitcsvm(features(trainIdx,:), labels(trainIdx),'KernelFunction',kernel,'Standardize',true,...
    'BoxConstraint',C,'ClassNames',[0,1],'Solver',solver);

    [label,scores] =  predict(cl, features(testIdx,:));
    eq = sum(label==labels(testIdx));
    accuracy(i) = eq/numel(labels(testIdx));

end

crossValAcc = mean(accuracy)