Skip to main content
. Author manuscript; available in PMC: 2020 Jul 1.
Published in final edited form as: IEEE Trans Med Imaging. 2019 Jan 23;38(7):1715–1725. doi: 10.1109/TMI.2019.2893651

Fig. 1.

Fig. 1.

Given a set of observations, the IVA model is given as X[m]=A[m]S[m],m=1,…,M, where A[m] is the mixing matrix and the rows in S[m], are the latent sources that are dependent across datasets. These dependent sources are concatenated together to form an SCV.