arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.06546eess.SPcs.LG
收藏

适配睡眠基础模型用于密集睡眠纺锤波定位

Adapting Sleep Foundation Models for Dense Sleep Spindle Localization

Idiap Research Institute(伊迪亚普研究所);Vrije Universiteit Brussel (VUB)(布鲁塞尔自由大学);Interuniversity Microelectronics Centre (IMEC)(跨大学微电子研究中心)

Alexis Bollengier, Abel Díaz Berenguer, Olivier Pallanca, André Anjos, Hichem Sahli

AI总结:

该研究针对密集睡眠纺锤波定位的挑战,适配SleepFM编码器构建模型,在MODA数据集上取得事件级F1值0.8080±0.0040的结果,表明保留预训练令牌尺度以下信息对密集适配有益。

摘要:

将睡眠基础模型适配到密集脑电图(EEG)事件定位具有挑战性,因为多秒表示可能无法保留足够的时间细节以实现精确的边界恢复。我们通过适配冻结的SleepFM编码器来解决睡眠纺锤波定位问题,该编码器配备了局部时频通路,可保留与纺锤波相关的频谱内容和令牌内位置。局部表示驱动定位,而残差交叉注意力则整合SleepFM的时间上下文。通过局部令牌到样本的重建和时间细化获得密集预测。在Massive Online Data Annotation(MODA)数据集上进行测试,所提出的模型在六个折的IoU为0.2时,事件级F1值达到0.8080±0.0040。 ablation研究表明,定位主要依赖局部频谱和子令牌时间信息,而预训练表示提供互补上下文。这些结果表明,密集适配受益于保留低于预训练令牌尺度的信息。代码将在论文接收后发布。

英文摘要:

Adapting sleep foundation models to dense electroencephalography (EEG) event localization is challenging because multi-second representations may not preserve sufficient temporal detail for precise boundary recovery. We address sleep spindle localization by adapting a frozen SleepFM encoder with a local time-frequency pathway that preserves spindle-relevant spectral content and intra-token position. The local representation drives localization, while residual cross-attention incorporates SleepFM temporal context. Dense predictions are obtained through localized token-to-sample reconstruction and temporal refinement. Tested on the Massive Online Data Annotation (MODA), the proposed model achieves an event-level $F_1$ of $0.8080 \pm 0.0040$ at IoU 0.2 across six folds. Ablations show that localization primarily depends on local spectral and sub-token temporal information, while the pretrained representation provides complementary context. These results indicate that dense adaptation benefits from preserving information below the pretrained token scale. Code will be released upon acceptance.

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。

↑