从脑电图中提取拓扑特征，提升睡眠分期的降维效果
Two-Stage Hierarchical and Explainable Feature Selection Framework for Dimensionality Reduction in Sleep Staging
- 分两阶段筛选特征，结合拓扑分析补足传统方法丢失的结构信息
- 基于拓扑特征的降维使睡眠分期准确率达79.8%（t-SNE）
- UMAP在效率与性能间平衡最佳，适合实际应用
睡眠对人类健康至关重要，脑电图（EEG）信号在睡眠研究中扮演关键角色。由于EEG数据序列维度高，导致不同睡眠阶段的数据可视化与聚类面临挑战。为此，我们提出一种两阶段分层可解释特征选择框架，结合特征选择算法以提升降维性能。受拓扑数据分析启发，我们从EEG信号中提取拓扑特征，弥补传统时频分析中结构信息的损失。通过不同睡眠阶段数据的拓扑可视化及分类结果验证，所提特征有效补充了传统特征。最终比较了三种降维算法：主成分分析（PCA）、t分布随机邻域嵌入（t-SNE）和均匀流形近似与投影（UMAP）。其中，t-SNE达到最高准确率79.8%，但综合计算资源与指标表现，UMAP为最优选择。
原文摘要 · Abstract (English)
Sleep is crucial for human health, and EEG signals play a significant role in sleep research. Due to the high-dimensional nature of EEG signal data sequences, data visualization and clustering of different sleep stages have been challenges. To address these issues, we propose a two-stage hierarchical and explainable feature selection framework by incorporating a feature selection algorithm to improve the performance of dimensionality reduction. Inspired by topological data analysis, which can analyze the structure of high-dimensional data, we extract topological features from the EEG signals to compensate for the structural information loss that happens in traditional spectro-temporal data analysis. Supported by the topological visualization of the data from different sleep stages and the classification results, the proposed features are proven to be effective supplements to traditional features. Finally, we compare the performances of three dimensionality reduction algorithms: Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP). Among them, t-SNE achieved the highest accuracy of 79.8%, but considering the overall performance in terms of computational resources and metrics, UMAP is the optimal choice.
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。