Code-modulated visually evoked potential (c-VEP) classification

Name: cvep
Category: brain-computer interfacing
Dataset: Castillos2023Cvep100
Objective: Binary classification
Split: Leave-subjects-out

Usage

neuralbench eeg cvep
Show config.yaml
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

data:
  study:
    source:
      name: Thielen2021From
    split:
      name: SklearnSplit
      split_by: subject
      valid_split_ratio: 0.2
      test_split_ratio: 0.2
      valid_random_state: 33
      test_random_state: 33
  target:
    =replace=: true
    name: LabelEncoder
    event_types: Stimulus
    event_field: code
    return_one_hot: true
    aggregation: trigger
  trigger_event_type: Stimulus
  start: 0.0
  duration: 4.0
  summary_columns: [code]
brain_model_output_size: &brain_model_output_size 20
trainer_config.monitor: val/bal_acc
trainer_config.mode: max
loss:
  name: CrossEntropyLoss
  kwargs:
    label_smoothing: 0.1
metrics: !!python/object/apply:neuralbench.defaults.metrics.get_classification_metric_configs
  - *brain_model_output_size

Description

The code-modulated visually evoked potential (c-VEP) classification task involves identifying different visual stimulus codes from EEG recordings. c-VEPs are brain responses elicited by visual stimuli that are modulated using pseudo-random binary sequences, rather than periodic flickering at fixed frequencies as in SSVEP.

Additional Datasets

The following additional datasets from MOABB can also be used with this task:

  • Castillos2023BurstVep100 – 12 subjects, burst-VEP at 100 Hz

  • Castillos2023BurstVep40 – 12 subjects, burst-VEP at 40 Hz

  • Castillos2023Cvep40 – 12 subjects, c-VEP at 40 Hz

  • MartinezCagigal2023Checker – 16 subjects, checkerboard m-sequence c-VEP

  • MartinezCagigal2023Pary – 15 subjects, non-binary p-ary m-sequence c-VEP

  • Thielen2015 – 12 subjects, Gold code c-VEP speller

  • Thielen2021 – 30 subjects, pseudo-random c-VEP calculator speller

To run with an alternate dataset:

neuralbench eeg cvep --datasets thielen2015

References