用自监督与数据增强提升心率估计精度，误差降低12.2%。
EnhancePPG: Improving PPG-based Heart Rate Estimation with Self-Supervision and Augmentation
- 通过自监督预训练+数据增强，利用无标签数据学习通用特征
- 在PPG-DaLiA数据集上将心率误差从4.03降至3.54 BPM
- 仅微调模型，推理延迟几乎不变，适合可穿戴设备部署
基于光电容积脉搏波（PPG）的心率（HR）估计算法是现代可穿戴设备健康监测的核心功能。尽管深度学习模型展现潜力，但其性能依赖于大规模标注数据。本文提出EnhancePPG，通过结合自监督学习与数据增强（DA），提升现有先进模型的性能。该方法采用类似U-Net的自编码器架构，利用大量无标签数据进行无监督的PPG信号重建预训练，从而学习更具泛化能力的特征表示。无需额外标注数据，仅对现有模型进行微小调整，便在PPG-DaLiA数据集上将心率估计误差从4.03降低至3.54 Beats-Per-Minute（BPM），相对提升12.2%。此外，该方法不显著增加模型推理延迟，适用于实时可穿戴场景。
原文摘要 · Abstract (English)
Heart rate (HR) estimation from photoplethysmography (PPG) signals is a key feature of modern wearable devices for health and wellness monitoring. While deep learning models show promise, their performance relies on the availability of large datasets. We present EnhancePPG, a method that enhances state-of-the-art models by integrating self-supervised learning with data augmentation (DA). Our approach combines self-supervised pre-training with DA, allowing the model to learn more generalizable features, without needing more labelled data. Inspired by a U-Net-like autoencoder architecture, we utilize unsupervised PPG signal reconstruction, taking advantage of large amounts of unlabeled data during the pre-training phase combined with data augmentation, to improve state-of-the-art models' performance. Thanks to our approach and minimal modification to the state-of-the-art model, we improve the best HR estimation by 12.2%, lowering from 4.03 Beats-Per-Minute (BPM) to 3.54 BPM the error on PPG-DaLiA. Importantly, our EnhancePPG approach focuses exclusively on the training of the selected deep learning model, without significantly increasing its inference latency
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。