Anchored-STFT and GNAA: An extension of STFT in conjunction with an adversarial data augmentation technique for the decoding of neural signals
This work provides an incremental improvement in EEG signal classification accuracy for BCI users, potentially leading to more reliable control commands.
This paper addresses the challenge of noise in EEG signals for Brain-Computer Interfaces (BCIs) by proposing a novel feature extraction method, anchored-STFT, and a new data augmentation technique, GNAA. The proposed pipeline, including a new CNN architecture called Skip-Net, achieved an average classification accuracy of 90.7% on BCI competition II dataset III and 89.54% on BCI competition IV dataset 2b, outperforming state-of-the-art methods.
Brain-computer interfaces (BCIs) enable communication between humans and machines by translating brain activity into control commands. Electroencephalography (EEG) signals are one of the most used brain signals in non-invasive BCI applications but are often contaminated with noise. Therefore, it is possible that meaningful patterns for classifying EEG signals are deeply hidden. State-of-the-art deep-learning algorithms are successful in learning hidden, meaningful patterns. However, the quality and the quantity of the presented inputs is pivotal. Here, we propose a novel feature extraction method called anchored Short Time Fourier Transform (anchored-STFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT. In addition, we propose a novel augmentation method, called gradient norm adversarial augmentation (GNAA). GNAA is not only an augmentation method but is also used to harness adversarial inputs in EEG data, which not only improves the classification accuracy but also enhances the robustness of the classifier. In addition, we also propose a new CNN architecture, namely Skip-Net, for the classification of EEG signals. The proposed pipeline outperforms all state-of-the-art methods and yields an average classification accuracy of 90.7 % and 89.54 % on BCI competition II dataset III and BCI competition IV dataset 2b, respectively.