发表机构
University College Cork; INFANT Research Centre; Pediatrics and Child Health（科克大学学院; 婴儿研究中心; 儿科与儿童健康）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出MAEConformer自监督学习框架，结合Conformer与MAE从EEG和HRV信号学习。通过卷积与自注意力捕获模式与依赖，引入MR-STFT损失。模型预训练后用于下游任务，在EEG和HRV的HIE分类中表现出色，证明其学习鲁棒可转移表示的有效性。
AI 中文摘要
在本文中，我们提出了MAEConformer，这是一种新颖的自监督学习框架，它将Conformer架构与掩码自动编码器（MAE）范式相结合，用于从未标记的脑电图（EEG）和心率变异性（HRV）信号中进行大规模表示学习。通过将卷积操作与基于Transformer的自注意力相结合，MAEConformer有效地捕获了生理时间序列中的局部时间模式和长程上下文依赖关系。为了提高重建保真度和表示质量，在重建目标的基础上引入了多分辨率短时傅里叶变换（MR-STFT）损失，使模型能够跨多个尺度联合学习时间和频谱特征。特定模态的EEG和HRV MAEConformer模型分别在6030小时和4868小时的未标记记录上进行预训练，随后转移到专家注释的下游任务。实验结果表明，学习到的表示具有很强的可转移性和数据效率。在基于EEG的缺氧缺血性脑病（HIE）严重程度分类中，预训练的MAE-EEG模型在二分类和四分类任务中的测试AUC分别达到97.19%和96.56%，优于一系列现有的监督和自监督基线。在基于HRV的HIE严重程度分类任务中，MAE-HRV的测试AUC为82.42%，超过了基于Transformer的自监督和监督卷积基线。这些发现证明了MAEConformer在跨多种生理模态学习鲁棒和可转移表示方面的有效性。
英文摘要
In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals. By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectively captures both local temporal patterns and long-range contextual dependencies in physiological time series. To enhance reconstruction fidelity and representation quality, a multi-resolution short-time Fourier transform (MR-STFT) loss is incorporated alongside the reconstruction objective, enabling the model to jointly learn temporal and spectral characteristics across multiple scales. Modality-specific EEG and HRV MAEConformer models were pretrained on 6,030h and 4,868h of unlabelled recordings, respectively, and subsequently transferred to expert-annotated downstream tasks. Experimental results demonstrate that the learned representations provide strong transferability and data efficiency. In EEG-based hypoxic ischemic encephalopathy (HIE) severity classification, the pretrained MAE-EEG model achieved test AUCs of 97.19% and 96.56% for binary and four-class classification tasks, respectively, outperforming a range of state-of-the-art supervised and self-supervised baselines. On the HRV-based HIE severity classification task, MAE-HRV achieved a test AUC of 82.42%, surpassing both self-supervised Transformer-based and supervised convolutional baselines. These findings demonstrate the effectiveness of MAEConformer for learning robust and transferable representations across multiple physiological modalities.
CommentsPaper submits to IEEE Transactions on Neural Networks and Learning Systems
