用微调Transformer模型精准定位脑电图中的啁啾信号，填补自动化分析空白。
Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study
- 用ViT模型加LoRA微调，从合成脑电信号谱图中回归啁啾参数
- 对起始时间和频率的预测相关性高达0.9841，误差分布稳定无偏
- 适合神经科学与癫痫研究者用于自动化检测脑电异常信号
谱图在时频信号分析中至关重要，广泛应用于音频处理和计算神经科学。脑电图（EEG）谱图中的啁啾型模式（表现为线性或指数频率扫频）是癫痫动态的关键生物标志物，但缺乏自动检测、定位和特征提取工具。本研究通过在合成谱图上微调视觉变换器（ViT）模型，弥补这一空白，采用低秩适应（LoRA）提升模型适应性。我们生成了10万张含啁啾参数的合成谱图，构建首个大规模啁啾定位基准数据集。这些谱图模拟神经啁啾，包含线性/指数频率扫频、高斯噪声与平滑处理。使用适配回归任务的ViT模型，以均方误差（MSE）损失和AdamW优化器训练，结合学习率调度与早停机制防止过拟合。仅预测三个特征：啁啾起始时间（Onset Time）、起始频率（Onset Frequency）与结束频率（Offset Frequency）。通过预测值与真实标签间的皮尔逊相关系数评估性能，结果显示：啁啾起始时间相关性达0.9841，推理时间稳定在137至140秒之间，误差分布无显著偏差。该方法为脑电信号时频表示中的啁啾分析提供了有效工具，填补了关键方法学空白。
原文摘要 · Abstract (English)
Spectrograms are pivotal in time-frequency signal analysis, widely used in audio processing and computational neuroscience. Chirp-like patterns in electroencephalogram (EEG) spectrograms (marked by linear or exponential frequency sweep) are key biomarkers for seizure dynamics, but automated tools for their detection, localization, and feature extraction are lacking. This study bridges this gap by fine-tuning a Vision Transformer (ViT) model on synthetic spectrograms, augmented with Low-Rank Adaptation (LoRA) to boost adaptability. We generated 100000 synthetic spectrograms with chirp parameters, creating the first large-scale benchmark for chirp localization. These spectrograms mimic neural chirps using linear or exponential frequency sweep, Gaussian noise, and smoothing. A ViT model, adapted for regression, predicted chirp parameters. LoRA fine-tuned the attention layers, enabling efficient updates to the pre-trained backbone. Training used MSE loss and the AdamW optimizer, with a learning rate scheduler and early stopping to curb overfitting. Only three features were targeted: Chirp Start Time (Onset Time), Chirp Start Frequency (Onset Frequency), and Chirp End Frequency (Offset Frequency). Performance was evaluated via Pearson correlation between predicted and actual labels. Results showed strong alignment: 0.9841 correlation for chirp start time, with stable inference times (137 to 140s) and minimal bias in error distributions. This approach offers a tool for chirp analysis in EEG time-frequency representation, filling a critical methodological void.
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。