# Leveraging Cross-Subject Transfer Learning and Signal Augmentation for Enhanced RGB Color Decoding from EEG Data

## TL;DR

This paper improves EEG-based decoding of RGB colors by using transfer learning and signal augmentation, achieving 83.5% accuracy across subjects.

## Contribution

The novel approach combines transfer learning and signal augmentation to enhance EEG color decoding performance.

## Key findings

- Combining transfer learning and signal augmentation achieved 83.5% RGB color classification accuracy.
- Signal augmentation techniques like frequency slice recombination improved model generalization.
- Transfer learning reduced variability and improved performance in EEG-based color decoding.

## Abstract

Objectives: Decoding neural patterns for RGB colors from electroencephalography (EEG) signals is an important step towards advancing the use of visual features as input for brain–computer interfaces (BCIs). This study aims to overcome challenges such as inter-subject variability and limited data availability by investigating whether transfer learning and signal augmentation can improve decoding performance. Methods: This research introduces an approach that combines transfer learning for cross-subject information transfer and data augmentation to increase representational diversity in order to improve RGB color classification from EEG data. Deep learning models, including CNN-based DeepConvNet (DCN) and Adaptive Temporal Convolutional Network (ATCNet) using the attention mechanism, were pre-trained on subjects with representative brain responses and fine-tuned on target subjects to parse individual differences. Signal augmentation techniques such as frequency slice recombination and Gaussian noise addition improved model generalization by enriching the training dataset. Results: The combined methodology yielded a classification accuracy of 83.5% for all subjects on the EEG dataset of 31 previously studied subjects. Conclusions: The improved accuracy and reduced variability underscore the effectiveness of transfer learning and signal augmentation in addressing data sparsity and variability, offering promising implications for EEG-based classification and BCI applications.