Ica choose number of components

1. How do you determine the number of components in ICA?
2. How many ICA components to remove?
3. What is kurtosis ICA?
4. Which is better PCA or ICA?

How do you determine the number of components in ICA?

U =eig(cov(D)); k= 31; sum(U( (end-k+1): end ))/sum(U); where U is the vector of eigenvalues of your sample's covariance matrix in reverse order, D is your data and k is the number of components you are using.

How many ICA components to remove?

(C) The same EEG signals corrected for artifacts by ICA by removing the six selected components, and, (D) spectral analysis of the original and artifact-corrected EEG recordings.

What is kurtosis ICA?

ICA decomposes a multivariate signal into 'independent' components through 1. orthogonal rotation and 2. maximizing statistical independence between components in some way - one method used is to maximize non-gaussianity (kurtosis).

Which is better PCA or ICA?

ICA optimizes higher-order statistics such as kurtosis. PCA optimizes the covariance matrix of the data which represents second-order statistics. ICA finds independent components. ICA can extract independent sources which are independent of the higher-order correlations.