AVEDProcessedDataset

class torcheeg.datasets.AVEDProcessedDataset(root_path: str = './eeg_preproc', chunk_size: int = 128, overlap: int = 0, num_channel: int = 32, online_transform: None | Callable = None, offline_transform: None | Callable = None, label_transform: None | Callable = None, before_trial: None | Callable = None, after_trial: None | Callable = None, after_subject: None | Callable = None, io_path: None | str = None, io_size: int = 1048576, io_mode: str = 'lmdb', num_worker: int = 0, verbose: bool = True)

This dataset contains EEG recordings from 10 subjects listening to one of two competing speech audio streams under audio-video or audio-only conditions. This class generates training samples and test samples according to the given parameters, and caches the generated results in a unified input and output format (IO). The relevant information of the dataset is as follows:

• Author: Zhang et al.

• Year: 2024

• Download URL: https://iiphci.ahu.edu.cn/toAuditoryAttention

• Reference: ZHANG H, ZHANG J. Based on audio-video evoked auditory attention detection electroencephalogram dataset[J]. Journal of Tsinghua University (Science and Technology), 2024, 64(11): 1919-1926.

• Stimulus: 16 stories selected from the Chinese short story collection “Strange Tales from a Chinese Studio”, narrated by a male and a female speaker. Each trial lasts 152 seconds with the target speaker from either 90° left or right.

• Signals: Electroencephalogram recorded in a double-walled soundproof booth at the Technical University of Denmark (DTU) using a 32-channel system and digitized at a sampling rate of 1000 Hz (downsampled to 128 Hz).

• Rating: Attended speaker (1 for male, 2 for female), attended direction (1 for left, 2 for right), condition (audio-video or audio-only)

In order to use this dataset, the download folder eeg_preproc.zip is required. After unzipping, the folder should contain the following files:

eeg_preproc/
├── audio-video
│   ├── sub1.csv
│   ├── sub2.csv
│   ├── sub3.csv
│   ├── ...
│   └── sub10.csv
└── audio-only
    ├── sub1.csv
    ├── sub2.csv
    ├── sub3.csv
    ├── ...
    └── sub10.csv

In the dataset, 50 Hz power line interference is removed, and the signals are band-pass filtered (0.1-50 Hz) and downsampled to 128 Hz. Subsequently, ocular and muscle artifacts are eliminated using independent component analysis (ICA). Finally, all EEG channels were re-referenced.

An example dataset for CNN-based methods:

from torcheeg.datasets import AVEDProcessedDataset
from torcheeg import transforms

dataset = AVEDProcessedDataset(root_path='./eeg_preproc',
                               chunk_size=128,
                               overlap=0,
                               num_channel=32,
                               online_transform=transforms.ToTensor(),
                               label_transform=transforms.Compose([
                                   transforms.Select('attended_speaker'),
                                   transforms.Lambda(lambda x: int(x) - 1)
                               ]))
print(dataset[0])

Parameters:

• root_path (str) – Downloaded data files in CSV format (unzipped eeg_preproc folder) (default: './eeg_preproc')

• chunk_size (int) – Number of data points included in each EEG chunk as training or test samples. If set to -1, the EEG signal of a trial is used as a sample of a chunk. (default: 128)

• overlap (int) – The number of overlapping data points between different chunks when dividing EEG chunks. (default: 0)

• num_channel (int) – Number of channels used. (default: 32)

• online_transform (Callable, optional) – The transformation of the EEG signals. The input is a np.ndarray, and the output is used as the first value of each element in the dataset. (default: None)

• offline_transform (Callable, optional) – The usage is the same as online_transform, but executed before generating IO intermediate results. (default: None)

• label_transform (Callable, optional) – The transformation of the label. The input is an information dictionary, and the output is used as the second value of each element in the dataset. (default: None)

• before_trial (Callable, optional) – The hook performed on the trial to which the sample belongs. It is performed before the offline transformation and thus typically used to implement context-dependent sample transformations, such as moving averages, etc. The input of this hook function is a 2D EEG signal with shape (number of electrodes, number of data points), whose ideal output shape is also (number of electrodes, number of data points).

• after_trial (Callable, optional) – The hook performed on the trial to which the sample belongs. It is performed after the offline transformation and thus typically used to implement context-dependent sample transformations, such as moving averages, etc. The input and output of this hook function should be a sequence of dictionaries representing a sequence of EEG samples. Each dictionary contains two key-value pairs, indexed by eeg (the EEG signal matrix) and key (the index in the database) respectively.

• after_subject (Callable, optional) – The hook performed on the subject to which the sample belongs. It is performed after the offline transformation and thus typically used to implement context-dependent sample transformations, such as moving averages, etc. The input and output of this hook function should be a sequence of dictionaries representing a sequence of EEG samples. Each dictionary contains two key-value pairs, indexed by eeg (the EEG signal matrix) and key (the index in the database) respectively.

• io_path (str) – The path to generated unified data IO, cached as an intermediate result. If set to None, a random path will be generated. (default: None)

• io_size (int) – Maximum size database may grow to; used to size the memory mapping. If database grows larger than map_size, an exception will be raised and the user must close and reopen. (default: 1048576)

• io_mode (str) – Storage mode of EEG signal. When io_mode is set to lmdb, TorchEEG provides an efficient database (LMDB) for storing EEG signals. LMDB may not perform well on limited operating systems, where a file system based EEG signal storage is also provided. When io_mode is set to pickle, pickle-based persistence files are used. When io_mode is set to memory, memory are used. (default: lmdb)

• num_worker (int) – Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process. (default: 0)

• verbose (bool) – Whether to display logs during processing, such as progress bars, etc. (default: True)