after_hook_linear_dynamical_system

class torcheeg.transforms.after_hook_linear_dynamical_system(data: List[ndarray | Tensor], V0: float = 0.01, A: float = 1, T: float = 0.0001, C: float = 1, sigma: float = 1)

A common hook function used to normalize the signal of the whole trial/session/subject after dividing it into chunks and transforming the divided chunks.

It is used as follows:

from torcheeg.datasets import DEAPDataset
from torcheeg.transforms import after_hook_linear_dynamical_system

dataset = DEAPDataset(root_path='./data_preprocessed_python',
                      offline_transform=transforms.Compose([
                          transforms.BandDifferentialEntropy(),
                          transforms.ToGrid(DEAP_CHANNEL_LOCATION_DICT)
                      ]),
                      online_transform=transforms.ToTensor(),
                      after_trial=after_hook_linear_dynamical_system,
                      label_transform=transforms.Compose([
                          transforms.Select('valence'),
                          transforms.Binary(5.0),
                      ]))

If you want to pass in parameters, use partial to generate a new function:

from functools import partial
from torcheeg.datasets import DEAPDataset
from torcheeg.transforms import after_hook_linear_dynamical_system

dataset = DEAPDataset(root_path='./data_preprocessed_python',
                      offline_transform=transforms.Compose([
                          transforms.BandDifferentialEntropy(),
                          transforms.ToGrid(DEAP_CHANNEL_LOCATION_DICT)
                      ]),
                      online_transform=transforms.ToTensor(),
                      after_trial=partial(after_hook_linear_dynamical_system, V0=0.01, A=1, T=0.0001, C=1, sigma=1),
                      label_transform=transforms.Compose([
                          transforms.Select('valence'),
                          transforms.Binary(5.0),
                      ]))

Parameters:

• data (list) – A list of np.ndarray or torch.Tensor, one of which corresponds to an EEG signal in trial.

• V0 (float) – The initial variance of the linear dynamical system (default: 0.01)

• A (float) – The coefficient of the linear dynamical system (default: 1)

• T (float) – The term added to the diagonal of the covariance matrix (default: 0.0001)

• C (float) – The coefficient of the linear dynamical system (default: 1)

• sigma (float) – The variance of the linear dynamical system (default: 1)

Returns:

The normalized results of a trial. It is a list of np.ndarray or torch.Tensor, one of which corresponds to an EEG signal in trial.

Return type:

list