Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-Processing

TL;DR

This paper introduces EEG-DCViT, a novel deep learning model combining depthwise separable CNNs and vision transformers with clustering pre-processing, significantly improving EEG-based gaze prediction accuracy.

Contribution

The study presents a new EEG-DCViT model that integrates depthwise separable convolution and clustering pre-processing, setting a new benchmark in EEG gaze prediction.

Findings

Achieved a new RMSE benchmark of 51.6 mm in EEG gaze prediction.

Demonstrated the effectiveness of combined CNN and transformer architecture.

Highlighted the importance of pre-processing in neural data interpretation.

Abstract

In the field of EEG-based gaze prediction, the application of deep learning to interpret complex neural data poses significant challenges. This study evaluates the effectiveness of pre-processing techniques and the effect of additional depthwise separable convolution on EEG vision transformers (ViTs) in a pretrained model architecture. We introduce a novel method, the EEG Deeper Clustered Vision Transformer (EEG-DCViT), which combines depthwise separable convolutional neural networks (CNNs) with vision transformers, enriched by a pre-processing strategy involving data clustering. The new approach demonstrates superior performance, establishing a new benchmark with a Root Mean Square Error (RMSE) of 51.6 mm. This achievement underscores the impact of pre-processing and model refinement in enhancing EEG-based applications.