unsortedChannelIndices

unsortedChannelIndices

我的数据由16个通道x128个样本x400个试验组成。我想在此数据集中执行详尽的渠道选择。我应该在哪里申请PCA?

unsortedChannelIndices = [1:16]
sortedChannelIndices = [];

%Option 1
reducedData = PCA(data, classIndeces)

for chIdx = 1:length(unsortedChannelIndices)

   for c=1:length(unsortedChannelIndices)
      thisChannel = unsortedChannelIndices(c)
      thisChannelSet = [sortedChannelIndices, thisChannel];

      %Option 1
      thisData = reducedData(thisChannelSet,:,:);

      %Option 2
      thisData = PCA(data(thisChannelSet, classIndeces)

      thisPerformance(c) = eval_perf(thisData);%crossvalidation
    end
    [performance(chIdx),best] = max(thisPerformance);
    sortedChannelIndices = [sortedChannelIndices,unsortedChannelIndices(best)];
    unsortedChannelIndices(best) =  [];
end

最佳答案

PCA或任何降维技术应与将要分析的数据一起使用。如果我们要评估与较少通道(例如1:4)相对应的子集的性能,则应在此数据中应用任何降维技术(PCA(data([1:4),:,:)。因此,选项2是正确的选项。

关于machine-learning - 穷举 channel /功能选择中的降维,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/33113450/

10-08 22:13