Mental arithmetic detection

Name: mental arithmetic

Category: mental state classification

Dataset: Zyma2018

Objective: Multiclass classification

Split: Leave-subjects-out

Usage

neuralbench eeg mental_arithmetic

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: Zyma2019Electroencephalograms
    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: Eeg
    event_field: task
    return_one_hot: true
    aggregation: trigger
  trigger_event_type: Eeg
  start: 0.0
  duration: 5.0
  stride: 5.0
  summary_columns: [task]
compute_class_weights: true
brain_model_output_size: &brain_model_output_size 2
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

This task involves classifying EEG signals to detect whether the participants were performing a mental arithmetic task or not [Zyma2018].

Dataset Notes

• Previous work (CBraMod, EEG-FM-Bench) framed this binary classification problem as a “mental stress” detection problem. However, as the non-arithmetic condition did not control for the cognitive workload induced by the task, we posit that the most obvious signal models can rely on for the classification task will be related to the correlates of mental arithmetic.

Additional Datasets

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

• Shin2017B – 29 subjects, 2 classes (serial subtraction vs resting baseline)

To run with an alternate dataset:

neuralbench eeg mental_arithmetic --datasets shin2017b

References

[Zyma2018]

Zyma, Igor, et al. “Electroencephalograms during mental arithmetic task performance.” Data 4.1 (2019): 14.