Hybrid time-reassigned multisynchrosqueezing transform-Picard-based automated electroencephalography artifact correction methodology for brain-computer interface applications

The electroencephalographic activity is often contaminated with non-cerebral origins resulting in erroneous classification in brain-computer interface (BCI) applications. In the present work, a novel automated Electroencephalogram artifact correction methodology is proposed. Preconditional independent component analysis (ICA) is utilized for de-mixing the electroencephalographic activity into original components. The sparse entropy-based thresholding criterion is developed to automatically identify the artifactual components and the time-reassigned multisynchrosqueezing transform coefficients are estimated. The transform coefficients are processed to retain leaked cerebral activity into artifactual components. Finally, inverse transformation and inverse ICA are performed to attain artifact-free electroencephalographic activity. The efficiency of the proposed methodology is validated on simulated and real electroencephalographic activity. The results illustrate the efficacy of the proposed methodology on both simulated and real electroencephalography activities in retaining useful cerebral information and rejecting artifactual origins, with a potential to be used in various BCI applications.