Enhanced EEG Artifact Removal for Epilepsy Detection: Integrating CCA, EMD, And DFA-Based Denoising Technique

In this study, artifact disapproval in electroencephalogram (EEG) might be related to sound originating from eye and muscle movements. This involves a two-step procedure which increases the signal readability through filtering out noise by CCA and EMD-DFA. Thus, the concept of IMFs in a communication may help EMD and DFA identify and minimize ocular disturbances whereas CCA may help minimize interfering associated with muscles. When the developed approach generates more signals from the input and minimizes the rate of loss of data, the goal is achieved. It also discusses the use of this combined strategy with other more traditional methods such as ICA, PCA, and the Wiener filters. Signal-noise ratio is used to get the association and the mean square error of the suggested system and it is used to measure the functionality. The effectiveness study showed the effectiveness of the suggested solution is better than other approaches in terms of the elimination of eeg signal. Based on the results they brought forward, the suggest that in future investigations of neurological and cognitive sciences, integrated EEG-based systems ought to incorporate artifact reduction as a part of the process.