Demir, Andac, Khalil, Iya and Kiziltan, Bulent (2023) EEG-NEXT: A MODERNIZED CONVNET FOR THE CLASSIFICATION OF COGNITIVE ACTIVITY FROM EEG. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing.

Abstract

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 learn- ing 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 mod- ernized 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 cog- nitive activity classification along with better generalizability across cohorts.

Item Type:	Article
Keywords:	EEG, brain-computer interfaces, transfer learn- ing, Euclidean-space alignment, convolutional neural networks, continuous wavelet transformation
Date Deposited:	31 Jan 2023 00:45
Last Modified:	31 Jan 2023 00:45
URI:	https://oak.novartis.com/id/eprint/49089