Saved in:
Bibliographic Details
Main Authors: Key, Matthew L, Mehtiyev, Tural, Qu, Xiaodong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.03480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909280867713024
author Key, Matthew L
Mehtiyev, Tural
Qu, Xiaodong
author_facet Key, Matthew L
Mehtiyev, Tural
Qu, Xiaodong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03480
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-Processing
Key, Matthew L
Mehtiyev, Tural
Qu, Xiaodong
Machine Learning
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.
title Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-Processing
topic Machine Learning
url https://arxiv.org/abs/2408.03480