AI 中文总结
研究比较PCA、DyCA、DMD、AVD四种降维方法用于脑电图癫痫检测，通过自主人工智能驱动框架优化架构和超参数，结果显示基于方差的方法性能更优，最佳分类器架构因表示而异，突出输入表示重要性及自主实验的可行性。
AI 中文摘要
从多通道脑电图（EEG）中自动检测癫痫发作受益于降维以获得紧凑、有区分力的表示。我们比较了四种信号空间降维方法，主成分分析（PCA）、动态成分分析（DyCA）、动态模式分解（DMD）和平均波动率降维（AVD），用于在坦普尔大学医院癫痫发作语料库（TUSZ v2.0.3）上基于深度学习的癫痫发作检测。为了比较表示和分类器的最佳组合，一个自主人工智能驱动的研究框架为每种表示独立优化架构和超参数。通过测试ROC-AUC衡量，基于方差的方法AVD（88.28%）和PCA（85.98%）与其各自的最佳分类器配对，比基于动力学的方法DMD（74.56%）和DyCA（74.85%）性能高出10%以上，AVD的验证到测试差距也最小。最佳性能的分类器架构因表示而异，表明表示和分类器应联合优化。我们的结果突出了输入表示对脑电图癫痫检测的重要性，并表明自主人工智能驱动实验在生物医学信号处理中的可行性。
英文摘要
Automated epileptic seizure detection from multichannel electroencephalography (EEG) benefits from dimension reduction to obtain compact, discriminative representations. We compare four signal-space dimension reduction methods, Principal Component Analysis (PCA), Dynamical Component Analysis (DyCA), Dynamic Mode Decomposition (DMD), and Average Volatility Dimensioning (AVD), for deep learning-based seizure detection on the Temple University Hospital Seizure Corpus (TUSZ v2.0.3). To enable a comparison of optimal combinations of representation and classifier, an autonomous AI-driven research framework independently optimizes architecture and hyperparameters for each representation. Measured by test ROC-AUC, the variance-based methods AVD (88.28%) and PCA (85.98%) paired with their respective optimal classifiers outperform the dynamics-based methods DMD (74.56%) and DyCA (74.85%) by over 10%, with AVD also showing the smallest validation-to-test gap. The best-performing classifier architecture differs across representations, indicating that representation and classifier should be optimized jointly. Our results highlight the importance of the input representation for EEG seizure detection and indicate the viability of autonomous AI-driven experimentation in biomedical signal processing.
CommentsAccepted to BMT 2026
