Applying K-SVD Dictionary Learning for EEG Compressed Sensing Framework with Outlier Detection and Independent Component Analysis

摘要

This letter reports on the effectiveness of applying the Ksingular value decomposition (SVD) dictionary learning to the electroencephalogram (EEG) compressed sensing framework with outlier detection and independent component analysis. Using the K-SVD dictionary matrix with our design parameter optimization, for example, at compression ratio of four, we improved the normalized mean square error value by 31.4% compared with that of the discrete cosine transform dictionary for CHBMIT Scalp EEG Database.