EEG-NeXt: A Modernized ConvNet for The Classification of Cognitive Activity from EEG
This addresses the problem of reliable EEG-based cognitive activity classification for brain-computer interface systems, but it is incremental as it builds on existing ConvNeXt and transfer learning techniques.
The paper tackled the challenge of learning subject/session invariant features for classifying cognitive activities from EEG signals in brain-computer interfaces, and the result was improved accuracy and better generalizability across cohorts, as demonstrated on public datasets like Physionet Sleep Cassette and BNCI2014001.
One of the main challenges in electroencephalogram (EEG) based brain-computer interface (BCI) systems is learning the subject/session invariant features to classify cognitive activities within an end-to-end discriminative setting. We propose a novel end-to-end machine learning pipeline, EEG-NeXt, which facilitates transfer learning by: i) aligning the EEG trials from different subjects in the Euclidean-space, ii) tailoring the techniques of deep learning for the scalograms of EEG signals to capture better frequency localization for low-frequency, longer-duration events, and iii) utilizing pretrained ConvNeXt (a modernized ResNet architecture which supersedes state-of-the-art (SOTA) image classification models) as the backbone network via adaptive finetuning. On publicly available datasets (Physionet Sleep Cassette and BNCI2014001) we benchmark our method against SOTA via cross-subject validation and demonstrate improved accuracy in cognitive activity classification along with better generalizability across cohorts.