A Machine Learning-Based Big EEG Data Artifact Detection and Wavelet-Based Removal: An Empirical Approach

Table 2

Comparison of the recommended method with the existing method for artifact removal.

Methodology	Evaluation parameters	Signal-to-noise ratio (SNR)
		10	20	25
EEMD-CCA [6]	DSNR	18.611	21.7920	25.4018
Recommended (EEMD-CCA-SWT)		27.2775	32.8229	31.3270
EEMD-CCA [6]	Lambda	63.009	67.5610	71.9953
Recommended (EEMD-CCA-SWT)		75.6307	88.746	87.2213
EEMD-CCA [6]	Correlation improvement	0.0047	0.0060	0.0054
Recommended (EEMD-CCA-SWT)		0.0161	0.0258	0.0140
EEMD-CCA [6]	Spectral distortion (Pdis)	0.8974	0.9697	0.9487
Recommended (EEMD-CCA-SWT)		0.9640	0.9856	0.9867
EEMD-CCA [6]	RMSE	0.1285	0.1166	0.1072
Recommended (EEMD-CCA-SWT)		0.093	0.1126	0.0974
EEMD-CCA [6]	Coherence improvement () in percentage	84.86	83.10	83.29
Recommended (EEMD-CCA-SWT)		86.93	84.26	85.11