Steady-state visually evoked potential (SSVEP) classification¶
Wang2017Benchmark (Wang2016)Usage¶
neuralbench eeg ssvep
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: Wang2017Benchmark
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 40
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 visual steady-state evoked potential (SSVEP) classification task involves identifying different visual stimulus frequencies from EEG recordings. SSVEPs are brain responses elicited by visual stimuli flickering at specific frequencies. In this task, we use the Wang2017 benchmark dataset [Wang2017], which contains 64-channel EEG from 34 healthy participants fixating on targets in a 40-class SSVEP speller using joint frequency-phase modulation (8-15.8 Hz with 0.2 Hz spacing).
Additional Datasets¶
The following additional datasets from MOABB can also be used with this task:
Kalunga2016– 12 subjects, 4 classesLee2019Ssvep– 54 subjects, 4 classes (5.45, 6.67, 8.57 and 12 Hz at four positions)Nakanishi2015– 9 subjects, 12 classesOikonomou2016A(MAMEM1) – 11 subjects, 5 classesOikonomou2016B(MAMEM2) – 11 subjects, 5 classesOikonomou2016C(MAMEM3) – 11 subjects, 5 classes
To run with an alternate dataset:
neuralbench eeg ssvep --datasets lee2019ssvep
References¶
Wang, Yijun, Xiaogang Chen, Xiaorong Gao, and Shangkai Gao. “A Benchmark Dataset for SSVEP-Based Brain-Computer Interfaces.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 25.10 (2017): 1746-1752.