Informed Bootstrap Augmentation Improves EEG Decoding

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jeong, Woojae, Cui, Wenhui, Avramidis, Kleanthis, Medani, Takfarinas, Narayanan, Shrikanth, Leahy, Richard
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911267742023680
author Jeong, Woojae
Cui, Wenhui
Avramidis, Kleanthis
Medani, Takfarinas
Narayanan, Shrikanth
Leahy, Richard
author_facet Jeong, Woojae
Cui, Wenhui
Avramidis, Kleanthis
Medani, Takfarinas
Narayanan, Shrikanth
Leahy, Richard
contents Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmentation is often employed to enhance feature representations, yet conventional uniform averaging overlooks differences in trial informativeness and can degrade representational quality. We introduce a weighted bootstrapping approach that prioritizes more reliable trials to generate higher-quality augmented samples. In a Sentence Evaluation paradigm, weights were computed from relative ERP differences and applied during probabilistic sampling and averaging. Across conditions, weighted bootstrapping improved decoding accuracy relative to unweighted (from 68.35% to 71.25% at best), demonstrating that emphasizing reliable trials strengthens representational quality. The results demonstrate that reliability-based augmentation yields more robust and discriminative EEG representations. The code is publicly available at https://github.com/lyricists/NeuroBootstrap.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Informed Bootstrap Augmentation Improves EEG Decoding
Jeong, Woojae
Cui, Wenhui
Avramidis, Kleanthis
Medani, Takfarinas
Narayanan, Shrikanth
Leahy, Richard
Signal Processing
Machine Learning
Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmentation is often employed to enhance feature representations, yet conventional uniform averaging overlooks differences in trial informativeness and can degrade representational quality. We introduce a weighted bootstrapping approach that prioritizes more reliable trials to generate higher-quality augmented samples. In a Sentence Evaluation paradigm, weights were computed from relative ERP differences and applied during probabilistic sampling and averaging. Across conditions, weighted bootstrapping improved decoding accuracy relative to unweighted (from 68.35% to 71.25% at best), demonstrating that emphasizing reliable trials strengthens representational quality. The results demonstrate that reliability-based augmentation yields more robust and discriminative EEG representations. The code is publicly available at https://github.com/lyricists/NeuroBootstrap.
title Informed Bootstrap Augmentation Improves EEG Decoding
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2511.12073