用脑电图关键性特征精准识别深度睡眠，助力无意识脑机接口改善睡眠。
Deep Sleep Classification via EEG Signal Criticality: A Passive BCI Approach for Sleep-Improvement Neurofeedback
- 基于去趋势波动分析提取脑电关键性特征，识别深度睡眠状态。
- 朴素贝叶斯模型达到87.17%的平衡准确率，显著优于其他模型。
- 适合开发睡眠优化神经反馈系统，尤其适用于老年人群。
自动睡眠分期是被动脑-机接口（pBCI）的核心应用，通过解码自发神经状态实现无需用户意图的闭环干预。本研究评估了从去趋势波动分析（DFA）导出的关键性特征，用于精确识别深度睡眠（N3）。我们分析了来自290名老年女性的347,232个脑电信号片段，利用UMAP流形学习可视化状态转换过程。随后通过10折交叉验证对比六种分类器，采用平衡准确率筛选最优“状态感知”引擎。朴素贝叶斯取得最高均值平衡准确率（87.17% ± 0.24%），显著优于全连接神经网络（FNN：81.58%）和随机森林（80.97%）。线性模型（LDA：57.21%；SVM：51.01%）表现较差，表明DFA衍生的关键性特征位于非线性流形上。概率解码脑电关键性为pBCI提供了高精度感知机制，该稳健分类流程支持发展状态依赖型神经反馈，如针对性听觉刺激，以促进认知恢复。
原文摘要 · Abstract (English)
Automated sleep staging is a fundamental application of passive Brain-Computer Interfaces (pBCI), decoding spontaneous neural states to enable closed-loop interventions independent of user intent. This study evaluates criticality features derived from Detrended Fluctuation Analysis (DFA) for the specific identification of deep sleep (N3). We analyzed $347,232$ EEG epochs from $290$ older women using UMAP manifold learning to visualize state transitions. Subsequently, six classifiers were benchmarked via 10-fold cross-validation, using balanced accuracy to determine the optimal "state-sensing" engine for neurofeedback.Naive Bayes achieved the highest mean balanced accuracy ($87.17\% \pm 0.24\%$), significantly outperforming a fully connected deep neural network (FNN: $81.58\%$) and Random Forest ($80.97\%$). Linear models (LDA: $57.21\%$; SVM: $51.01\%$) performed poorly, indicating that DFA-derived criticality features reside on a distinct, non-linear manifold. Probabilistic decoding of EEG criticality provides a high-accuracy sensing mechanism for pBCIs. This robust classification pipeline supports the development of state-dependent neurofeedback, such as targeted auditory stimulation, to enhance cognitive recovery.
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。