Table 2.

Application of denoising method in EEG signal.

Ref.	Signal Processing Method	Conclusion
Li [65]	EMG reference artifacts of neck and head muscles	More precise EMG separation without manual intervention
Maddirala and Veluvolu [66]	CWT and K-means	It is suitable for situations with few EEG signal channels and can accurately separate artifacts
Patel [67]	Combining EEMD and PCA	Automatic detection and suppression of human eye artifacts can be achieved
Xie [68]	PCA with an SVM-based semi-supervised classification model	It is suitable for processing signals with a low signal-to-noise ratio and only a few labels, with high recognition accuracy and less training time
Sheoran and Saini [69]	Combining CCA and NAPCT	Artifact components are removed without manual intervention
Miao [73]	CCA and MWF	Eye artifacts can be adaptively removed from multi-channel EEG data without the need for a reference signal
Zhou and Gotman [80]	Wavelet transform	The combination of wavelet transform and ICA can effectively remove EMG and ECG artifacts in EEG signals
Tibdewal [81]	Use the adaptive threshold of wavelet coefficients	Effectively reduces artifacts and noise while preserving the original brain signal
Chen [83]	EEMD and CCA techniques	It can make good use of interchannel information and has a good artifact removal effect in the case of serious signal pollution
Yang [84]	Extract spikes to the first IMF	Can alleviate splitting effects, but not suitable for separating multipoint spikes
Li and Zhang [85]	EMD	It can eliminate the effect of multipoint spikes on IMF screening and better remove EOG artifacts

ICA: Independent component analysis; PCA: Principal component analysis; CCA: Canonical correlation analysis; WT: Wavelet transform; EMD: Empirical mode decomposition; CWT: Continuous wavelet transform; EEMD: Ensemble empirical mode decomposition; NAPCT: Noise adjusted principal component transform; MWF: Multi-channel Wiener filter.