End-to-End Deep Transfer Learning for Calibration-free Motor Imagery Brain Computer Interfaces
This work addresses accessibility issues for general users in out-of-the-lab BCI applications by reducing calibration needs, but it is incremental as it applies existing deep learning models to a known bottleneck without achieving required performance levels.
The study tackled the problem of poor classification accuracy and high calibration data requirements in Motor Imagery Brain-Computer Interfaces by developing calibration-free subject-independent classifiers using an end-to-end deep transfer learning approach on raw EEG signals, resulting in median accuracies of 62.5% for EEGNet and 59.2% for DeepConvNet, which are similar to non-transfer learning baselines but below the 70% threshold for significant control.
A major issue in Motor Imagery Brain-Computer Interfaces (MI-BCIs) is their poor classification accuracy and the large amount of data that is required for subject-specific calibration. This makes BCIs less accessible to general users in out-of-the-lab applications. This study employed deep transfer learning for development of calibration-free subject-independent MI-BCI classifiers. Unlike earlier works that applied signal preprocessing and feature engineering steps in transfer learning, this study adopted an end-to-end deep learning approach on raw EEG signals. Three deep learning models (MIN2Net, EEGNet and DeepConvNet) were trained and compared using an openly available dataset. The dataset contained EEG signals from 55 subjects who conducted a left- vs. right-hand motor imagery task. To evaluate the performance of each model, a leave-one-subject-out cross validation was used. The results of the models differed significantly. MIN2Net was not able to differentiate right- vs. left-hand motor imagery of new users, with a median accuracy of 51.7%. The other two models performed better, with median accuracies of 62.5% for EEGNet and 59.2% for DeepConvNet. These accuracies do not reach the required threshold of 70% needed for significant control, however, they are similar to the accuracies of these models when tested on other datasets without transfer learning.