# Enhancing EEG Decoding with Selective Augmentation Integration

## TL;DR

This paper introduces a new framework and neural architecture to improve EEG analysis using selective data augmentation and contrastive learning, achieving significant performance gains.

## Contribution

The novel contribution is an end-to-end EEG augmentation framework with adaptive contrastive learning and a new neural architecture called NeuroBrain.

## Key findings

- The proposed framework achieved a 29.42% performance gain over HappyQuokka.
- It showed a 5.45% accuracy improvement compared to EEGNet on EEG decoding tasks.

## Abstract

Deep learning holds considerable promise for electroencephalography (EEG) analysis but faces challenges due to scarce and noisy EEG data, and the limited generality of existing data augmentation techniques. To address these issues, we propose an end-to-end EEG augmentation framework with an adaptive mechanism. This approach utilizes contrastive learning to mitigate representational distortions caused by augmentation, thereby strengthening the encoder’s feature learning. A selective augmentation strategy is further incorporated to dynamically determine optimal augmentation combinations based on performance. We also introduce NeuroBrain, a novel neural architecture specifically designed for auditory EEG decoding. It effectively captures both local and global dependencies within EEG signals. Comprehensive evaluations on the SparrKULee and WithMe datasets confirm the superiority of our proposed framework and architecture, demonstrating a 29.42% performance gain over HappyQuokka and a 5.45% accuracy improvement compared to EEGNet. These results validate our method’s efficacy in tackling key challenges in EEG analysis and advancing the state of the art.