/T-BEAR

Detect EEG artifacts, outliers, or anomalies using supervised machine learning.

Primary LanguagePythonApache License 2.0Apache-2.0

Time-Based EEG Artifact Rejection (T-BEAR)

Automated process for detecting and rejecting EEG artifacts.

Table of Contents

Description

This ongoing process explores supervised learning methods to detect artifacts in EEG data and possibly other time series.

Challenges:

  • Current models are often task specific
  • Feature engineering & selection
  • High dimensionality
  • High variability between subjects
  • Low signal-to-noise ratio
  • Non-stationary signal

Possible Prototypes:

  • Machine Learning

    • Supervised:

      • Random Forest Classifier/Regressor
      • Support Vector Classifier/Machine

    • Unsupervised:

      • Isolation Forest

  • Deep Learning

    • Supervised:
      • Convolutional Neural Network (CNN)*
      • Recurrent Neural Network (RNN)

*CNN will be our goal for the final model.

Performance Metrics:

  • F1 Score
  • Precision
  • Recall
  • AUC-ROC Curve

Getting Started

Dependencies

  • Anaconda: within the tbear directory containing the file environment.yml perform:
    • Problems may arise with Windows users.
conda env create -f environment.yml
  • pip
pip install numpy scipy matplotlib pandas scikit-learn jupyter mne tensorflow

License

This project is licensed under the Apache License - see the LICENSE file for details

Acknowledgments

Inspiration, code snippets, etc.