Data augmentation (DA) can significantly strengthen the electroencephalogram (EEG)-based seizure prediction methods. However, existing DA approaches are just the linear transformations of original data and cannot explore the feature space to increase diversity effectively. Therefore, we propose a novel diffusion-based DA method called DiffEEG. DiffEEG can fully explore data distribution and generate samples with high diversity, offering extra information to classifiers. It involves two processes: the diffusion process and the denoised process. In the diffusion process, the model incrementally adds noise with different scales to EEG input and converts it into random noise. In this way, the representation of data can be learned. In the denoised process, the model utilizes learned knowledge to sample synthetic data from random noise input by gradually removing noise. The randomness of input noise and the precise representation enable the synthetic samples to possess diversity while ensuring the consistency of feature space. We compared DiffEEG with original, down-sampling, sliding windows and recombination methods, and integrated them into five representative classifiers. The experiments demonstrate the effectiveness and generality of our method. With the contribution of DiffEEG, the Multi-scale CNN achieves state-of-the-art performance, with an average sensitivity, FPR, AUC of 95.4%, 0.051/h, 0.932 on the CHB-MIT database and 93.6%, 0.121/h, 0.822 on the Kaggle database.

翻译：数据增强（DA）能够显著强化基于脑电图（EEG）的癫痫预测方法。然而，现有的数据增强方法仅是对原始数据进行线性变换，无法有效探索特征空间以增加多样性。因此，我们提出了一种新颖的基于扩散的数据增强方法，称为DiffEEG。DiffEEG能够充分探索数据分布并生成具有高度多样性的样本，为分类器提供额外信息。该方法包含两个过程：扩散过程与去噪过程。在扩散过程中，模型以不同尺度逐步向EEG输入添加噪声，并将其转化为随机噪声。通过这种方式，可以学习数据的表征。在去噪过程中，模型利用所学知识，通过逐步去除噪声，从随机噪声输入中采样生成合成数据。输入噪声的随机性与精确的表征能力使得合成样本在保持特征空间一致性的同时具备多样性。我们将DiffEEG与原始数据、下采样、滑动窗口及重组方法进行了比较，并将其集成到五种代表性分类器中。实验证明了我们方法的有效性与普适性。在DiffEEG的贡献下，多尺度CNN在CHB-MIT数据库上取得了平均灵敏度95.4%、误报率0.051次/小时、AUC 0.932的性能，在Kaggle数据库上取得了平均灵敏度93.6%、误报率0.121次/小时、AUC 0.822的性能，达到了最先进的水平。