A novel end-to-end 1D-ResCNN model to remove artifact from EEG signals
two stages of end-to-end manner:
- training stage:an objective function is often adopted to optimize the model parameters.
- test stage:the trained 1D-ResCNN model is used as a filter to automatically remove noise from the contaminated EEG signal.
1D-ResCNN model‘s advantages:
- achieves smaller RMSE and better signal-to-noise ratio(SNR).
- better noise suppression ability.
- the nonlinear characteristics of EEG after denosing are significantly maintained(preserved).
- the EEG denosing performance under unknown noise is further improved.