MPOWIT is also highly scalable and could realistically solve group-level PCA of fMRI on thousands of subjects, or more, using standard hardware, limited only by time, not memory. Together, these developments enable efficient estimation of accurate principal components, as we illustrate by solving a 1600-subject group-level PCA of fMRI with standard acquisition parameters, on a regular desktop computer with only 4 GB RAM, in just a few hours. Highly efficient subsampled eigenvalue decomposition techniques are also introduced, furnishing excellent PCA subspace approximations that can be used for intelligent initialization of randomized methods such as MPOWIT. More importantly, in the proposed implementation of MPOWIT, the memory required for successful recovery of the group principal components becomes independent of the number of subjects analyzed. The number of iterations is reduced considerably (as well as the number of dataloads), accelerating convergence without loss of accuracy. The key idea behind MPOWIT is to estimate a subspace larger than the desired one, while checking for convergence of only the smaller subset of interest. This method is coined multi power iteration (MPOWIT). Since the number of dataloads is not typically optimized, we extend one of these methods to compute PCA of very large datasets with a minimal number of dataloads. Existing randomized PCA methods can determine the PCA subspace with minimal memory requirements and, thus, are ideal for solving large PCA problems. This work focuses on reducing very high dimensional temporally concatenated datasets into its group PCA space. Commonly, group-level PCA of temporally concatenated datasets is computed prior to ICA of the group principal components. Principal component analysis (PCA) is widely used for data reduction in group independent component analysis (ICA) of fMRI data. 3Department of Computer Science, The University of New Mexico, Albuquerque, NM, USA.2Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM, USA.1The Mind Research Network and Lovelace Biomedical and Environmental Research Institute, Albuquerque, NM, USA.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |