Efficient Blind Source Separation Method for fMRI Using Autoencoder and Spatiotemporal Sparsity Constraints

Efficient Blind Source Separation Method for fMRI Using Autoencoder and Spatiotemporal Sparsity Constraints

Diversity measures exploited by blind source separation (BSS) methods are usually based on either statistical attributes/geometrical structures or sparse/overcomplete (underdetermined) representations of the signals. This leads to some inefficient BSS methods that are derived from either a mixing ma...

Full description

Bibliographic Details
Main Authors: Muhammad Usman Khalid, Bilal A. Khawaja, Malik Muhammad Nauman
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Sparse representation
autoencoder
BSS
fMRI
activation maps
PCA
Online Access:https://ieeexplore.ieee.org/document/10128979/

Internet

https://ieeexplore.ieee.org/document/10128979/

Similar Items