Informed Bootstrap Augmentation Improves EEG Decoding

2025-11-15

AI Summary

EEG decoding is often hampered by noise and trial-to-trial variability, leading to suboptimal performance under small-sample or complex experimental paradigms; conventional uniform averaging during data augmentation ignores inter-trial differences in information content and may incorporate low-quality trials. To address this, we propose a trial-reliability-weighted bootstrap augmentation method: single-trial reliability is quantified via ERP dissimilarity, enabling a probabilistic sampling scheme that preferentially retains high-information trials and applies reliability-based weighting during bootstrapping and averaging. This approach significantly enhances neural discriminability—achieving up to 71.25% accuracy in sentence comprehension EEG decoding, a 2.9-percentage-point improvement over unweighted baselines. Our core contribution lies in explicitly modeling trial reliability as a principled driver of data augmentation, establishing a robust and interpretable augmentation paradigm for noise-sensitive EEG decoding.

Technology Category

• Machine Learning: Ensemble Methods
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• EEG decoding suffers from noise and trial variability
• Uniform data averaging overlooks trial informativeness differences
• Weighted bootstrapping prioritizes reliable trials for better augmentation

Innovation

• Weighted bootstrapping prioritizes reliable EEG trials
• Augmentation uses probabilistic sampling with ERP-based weights
• Method improves decoding accuracy by emphasizing trial reliability