arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.30104cs.AI
收藏

脑电图基础模型中的时间特征提取器:包含预训练时间序列模型的受控比较

Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model

Ayşe Betül Yüce, Chris Joey Leffler, Sarun Varghese, Myra Spiliopoulou, Sebastian Stober

AI总结:

本文在统一脑电图基础模型框架下,受控比较了三种时间特征提取策略(线性基线、卷积编码器、冻结预训练时间序列模型MOMENT),发现预训练TSFM可作为有效的时间特征提取器,但效果因下游任务而异。

摘要:

脑电图(EEG)基础模型旨在从大规模脑记录中学习可泛化的表示。然而,时间特征提取器的作用以及预训练时间序列基础模型(TSFMs)是否能有效迁移到这一场景仍未充分探索。我们在统一的EEG基础模型内,对三种时间特征提取策略进行了受控比较,包括线性基线、卷积编码器和冻结的预训练TSFM(MOMENT)。我们使用两个下游任务(运动想象和情绪识别)评估它们对表示质量的影响。结果揭示了不同基准测试中的不同趋势。在运动想象数据集上,简单的时间表示表现具有竞争力,而情绪数据集则受益于更丰富的时间建模。尽管未专门针对EEG进行适配,预训练的TSFM作为有效的时间特征提取器,表明通用时间序列表示可以作为冻结的时间特征提取器迁移到EEG基础模型中。

英文摘要:

Electroencephalography (EEG) foundation models aim to learn generalizable representations from large-scale brain recordings. However, the role of temporal feature extractors and whether pretrained time-series foundation models (TSFMs) can be effectively transferred to this setting remains underexplored. We conduct a controlled comparison of three temporal feature extraction strategies, including a linear baseline, a convolutional encoder, and a frozen pretrained TSFM (MOMENT), within a unified EEG foundation model. We evaluate their impact on representation quality using two downstream tasks: motor imagery and emotion recognition. Results reveal different trends across the evaluated benchmarks. On the motor imagery dataset, simple temporal representations perform competitively, whereas the emotion dataset benefits from richer temporal modeling. Although not specifically adapted to EEG, the pretrained TSFM serves as an effective temporal feature extractor, suggesting that general-purpose time-series representations can be transferred as frozen temporal feature extractors within EEG foundation models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑