braindecode.preprocessing.exponential_moving_standardize#

braindecode.preprocessing.exponential_moving_standardize(data: ndarray[Any, dtype[_ScalarType_co]], factor_new: float = 0.001, init_block_size: int | None = None, eps: float = 0.0001)[source]#

Perform exponential moving standardization.

Compute the exponental moving mean mt at time t as mt=factornewmean(xt)+(1factornew)mt1.

Then, compute exponential moving variance vt at time t as vt=factornew(mtxt)2+(1factornew)vt1.

Finally, standardize the data point xt at time t as: xt=(xtmt)/max(>vt,eps).

Parameters:
  • data (np.ndarray (n_channels, n_times))

  • factor_new (float)

  • init_block_size (int) – Standardize data before to this index with regular standardization.

  • eps (float) – Stabilizer for division by zero variance.

Returns:

standardized – Standardized data.

Return type:

np.ndarray (n_channels, n_times)

Examples using braindecode.preprocessing.exponential_moving_standardize#

Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset

Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset

Fingers flexion decoding on BCIC IV 4 ECoG Dataset

Fingers flexion decoding on BCIC IV 4 ECoG Dataset