Motor execution classification¶
Srisrisawang2024Simultaneous (BNCI2025_001)Usage¶
neuralbench eeg motor_execution
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: Srisrisawang2024Simultaneous
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: 3.0
summary_columns: [code]
compute_class_weights: true
brain_model_output_size: &brain_model_output_size 16
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 motor execution classification task involves identifying different types of executed motor movements from EEG recordings. Here, we use the Srisrisawang2024 dataset [Srisrisawang2024], which contains 60-channel EEG from 20 healthy participants performing discrete reaching movements. The 16 classes encode the joint combination of movement direction (up, down, left, right), speed (slow, fast), and distance (near, far).
Additional Datasets¶
The following additional datasets from MOABB can also be used with this task:
Ofner2017– 15 subjects, 7 classes (executed upper limb movements: elbow, forearm, hand)Schirrmeister2017(HGD) – 14 subjects, 4 classes (left hand, right hand, both feet, rest)
To run with an alternate dataset:
neuralbench eeg motor_execution --dataset schirrmeister2017
References¶
Srisrisawang, Nitikorn, and Gernot R. Müller-Putz. “Simultaneous encoding of speed, distance, and direction in discrete reaching: an EEG study.” Journal of Neural Engineering 21.6 (2024): 066042.