Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by movements of the subject's arm affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial sensor. Unfortunately, most standard approaches of this kind rely on hand-tuned parameters, which impair their generalization capabilities and their applicability to real data in the field. In contrast, methods based on deep learning, despite their better generalization, are considered to be too complex to deploy on wearable devices.
In this work, we tackle these limitations, proposing a design space exploration methodology to automatically generate a rich family of deep Temporal Convolutional Networks (TCNs) for HR monitoring, all derived from a single "seed" model. Our flow involves a cascade of two Neural Architecture Search (NAS) tools and a hardware-friendly quantizer, whose combination yields both highly accurate and extremely lightweight models. When tested on the PPG-Dalia dataset, our most accurate model sets a new state-of-the-art in Mean Absolute Error. Furthermore, we deploy our TCNs on an embedded platform featuring a STM32WB55 microcontroller, demonstrating their suitability for real-time execution. Our most accurate quantized network achieves 4.41 Beats Per Minute (BPM) of Mean Absolute Error (MAE), with an energy consumption of 47.65 mJ and a memory footprint of 412 kB. At the same time, the smallest network that obtains a MAE < 8 BPM, among those generated by our flow, has a memory footprint of 1.9 kB and consumes just 1.79 mJ per inference.
End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables
Interuniversity Department of Regional and Urban Studies and Planning at Politecnico di Torino（理工学院区域与城市研究与规划联合大学部门）；Department of Control and Computer Engineering at Politecnico di Torino（理工学院控制与计算机工程系）；Department of Information Technology and Electrical Engineering at ETH Zurich（苏黎世联邦理工学院信息技术与电气工程系）；Department of Electrical, Electronic, and Information Engineering "Guglielmo Marconi" at University of Bologna（博洛尼亚大学电子、电子与信息工程系"Guglielmo Marconi"）
Cuffless Blood Pressure Estimation from Six Wearable Sensor Modalities in Multi-Motion-State Scenarios
Faculty of Frontier Sciences, Harbin Institute of Technology, Shenzhen（前沿科学学院，哈尔滨工业大学深圳校区）；University of Melbourne（墨尔本大学）；University of New South Wales（新南威尔士大学）
PPGnet: Deep Network for Device Independent Heart Rate Estimation from Photoplethysmogram
Healthcare Technology Innovation Centre (HTIC)（医疗技术创新中心）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Department of Electrical Engineering, Indian Institute of Technology Madras（印度理工学院马德拉斯分校电气工程系）
Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG
Department of Computer Science, University of California, Davis（加州大学戴维斯分校计算机科学系）；Department of Electrical and Computer Engineering, University of California, Davis（加州大学戴维斯分校电气与计算机工程系）
A Nonlinear Complexity Index for Wearable PPG Cardiovascular Stability: Multiscale Validation, Systematic Evaluation Correction, and Bayesian Parameter Optimization
Department of Computer Science, Morgan State University（莫根州立大学计算机科学系）
PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection
National Institute of Health Data Science, Peking University, China（北京大学国家健康数据科学研究院）；School of Intelligence Science and Technology, Peking University, China（北京大学智能科学与技术学院）；Data Science Institute, Imperial College London, UK（伦敦帝国理工学院数据科学研究院）；University of Chinese Academy of Sciences, China（中国科学院大学）
Self-Supervised Autoencoder Network for Robust Heart Rate Extraction from Noisy Photoplethysmogram: Applying Blind Source Separation to Biosignal Analysis
Mellowing Factory Co. Ltd.（梅洛灵工厂有限公司）；Chungnam National University Hospital（全南国立大学医院）；Department of Radiology, Seoul National University College of Medicine（首尔国立大学医学院放射科）
Smartwatch Photoplethysmography-Derived Heart Age via ECG-Guided Cross-Modal Pretraining as a Digital Biomarker of Vascular Aging
National Institute of Health Data Science, Peking University（北京大学健康医疗大数据科学国家研究院）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医药技术学院）；OPPO Health Lab（OPPO健康实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学学院）；Xidian University（西安电子科技大学）；Shenzhen Technology University（深圳职业技术大学）
Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach
Infant Research Centre（婴儿研究中心）；School of Computing（计算机学院）；Dublin City University（都柏林城市大学）；Department of Electrical Engineering（电气工程系）；KU Leuven（鲁汶大学）；Cork University Maternity Hospital（科克大学妇产医院）；Insight SFI Research Centre（Insight SFI研究中心）
Transformer-Based Heartbeat Monitoring with FMCW Radar Under Random Body Motion
Dept. of Information Engineering, University of Pisa（比萨大学信息工程系）；Radar and Surveillance Systems (RaSS) National Laboratory, CNIT（CNIT雷达与监视系统（RaSS）国家实验室）
An End-to-End and Accurate PPG-based Respiratory Rate Estimation Approach Using Cycle Generative Adversarial Networks
University of California Irvine（加州大学欧文分校）；University of California, Irvine（加州大学欧文分校）；Institute for Future Health, University of California, Irvine（加州大学欧文分校未来健康研究所）
