moabb.paradigms.FilterBankCVEP#
- class moabb.paradigms.FilterBankCVEP(filters=((1.0, 45.0), (12.0, 45.0), (30.0, 45.0)), events=None, n_classes=None, tmin=0.0, tmax=None, baseline=None, channels=None, resample=None, scorer=None)[source]#
Filterbank c-VEP paradigm for epoch-level decoding.
c-VEP paradigm with multiple bandpass filters. Metric is ‘roc-auc’ if 2 classes and ‘accuracy’ if more. This paradigm is meant to be used for epoch-level decoding of c-VEP datasets; this means that the goal of the classifiers with this paradigm is to predict, for every stimulation one by one, the amplitude of the target code. The code value is between 0 (i.e., stimulation off) and 1 (i.e., maximal stimulation).
- Parameters:
filters (tuple of tuple | None (default ((1., 45.), (12., 45.), (30., 45.)))) – Bank of bandpass filter to apply.
Notes
Added in version 1.0.0.