用少量脑电数据精准估算脑事件相关电位，突破传统平均法限制。
Estimating the Event-Related Potential from Few EEG Trials
- 基于不确定性感知的自编码器，直接从少量脑电试次生成脑电位
- 在少样本情况下显著优于传统平均法，零样本跨被试泛化能力强
- 适用于神经科学研究与脑机接口，尤其适合试次受限场景
事件相关电位（ERP）是基础与临床神经科学中广泛使用的脑活动测量方法，通常需通过大量脑电（EEG）试次的平均以降低噪声。本文提出EEG2ERP，一种新型不确定性感知的自编码器方法，可将任意数量的EEG试次映射为对应的ERP。为建模ERP估计的不确定性，采用自助采样训练目标，并引入独立方差解码器。我们在三个公开数据集上评估该方法：i) 包含40名被试、6种范式、超过5万条试次的完整ERP CORE数据集；ii) 大规模P300拼写脑机接口数据集；iii) 同时包含EEG与脑磁图（MEG）数据的人脸感知神经成像数据集。结果表明，在少试次条件下，该方法始终显著优于常用的传统及鲁棒平均方法。EEG2ERP是首个将EEG信号直接映射至相应ERP的深度学习方法，有望减少ERP研究所需的试次数量。代码已开源：https://github.com/andersxa/EEG2ERP
原文摘要 · Abstract (English)
Event-related potentials (ERP) are measurements of brain activity with wide applications in basic and clinical neuroscience, that are typically estimated using the average of many trials of electroencephalography signals (EEG) to sufficiently reduce noise and signal variability. We introduce EEG2ERP, a novel uncertainty-aware autoencoder approach that maps an arbitrary number of EEG trials to their associated ERP. To account for the ERP uncertainty we use bootstrapped training targets and introduce a separate variance decoder to model the uncertainty of the estimated ERP. We evaluate our approach in the challenging zero-shot scenario of generalizing to new subjects considering three different publicly available data sources; i) the comprehensive ERP CORE dataset that includes over 50,000 EEG trials across six ERP paradigms from 40 subjects, ii) the large P300 Speller BCI dataset, and iii) a neuroimaging dataset on face perception consisting of both EEG and magnetoencephalography (MEG) data. We consistently find that our method in the few trial regime provides substantially better ERP estimates than commonly used conventional and robust averaging procedures. EEG2ERP is the first deep learning approach to map EEG signals to their associated ERP, moving toward reducing the number of trials necessary for ERP research. Code is available at https://github.com/andersxa/EEG2ERP
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。