Anchored-STFT and GNAA: An extension of STFT in conjunction with an adversarial data augmentation technique for the decoding of neural signals

TL;DR

This paper introduces anchored-STFT for improved EEG feature extraction, combined with GNAA for data augmentation, and a new CNN architecture, Skip-Net, achieving state-of-the-art classification accuracy in BCI tasks.

Contribution

It presents a novel feature extraction method, GNAA augmentation technique, and a new CNN architecture, significantly enhancing EEG signal classification performance.

Findings

Achieved 90.7% accuracy on BCI II dataset III.

Achieved 89.54% accuracy on BCI IV dataset 2b.

Outperformed existing state-of-the-art methods.

Abstract

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.