Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks

Sensors

Ina Indlekofer¹  Attila Reiss²  Philip Schmidt²  Kristof Van Laerhoven³ 

[1] Bosch Sensortec GmbH, Gerhard-Kindler-Straße 9, 72770 Reutlingen, Germany;Robert Bosch GmbH, Robert-Bosch-Campus 1, 71272 Renningen, Germany;Ubiquitous Computing, University of Siegen, Hölderlinstr. 3, 57076 Siegen, Germany;

关键词: heart rate;    PPG;    dataset;    time-frequency spectrum;    deep learning;    CNN;    evaluation methods;   

DOI  :  10.3390/s19143079

来源: DOAJ

【 摘 要 】

Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications. Recently, methods based on time-frequency spectra emerged to address the challenges of motion artefact compensation. However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets. We address this fragmentation by contributing research into the robustness and generalisation capabilities of PPG-based heart rate estimation approaches. First, we introduce a novel large-scale dataset (called PPG-DaLiA), including a wide range of activities performed under close to real-life conditions. Second, we extend a state-of-the-art algorithm, significantly improving its performance on several datasets. Third, we introduce deep learning to this domain, and investigate various convolutional neural network architectures. Our end-to-end learning approach takes the time-frequency spectra of synchronised PPG- and accelerometer-signals as input, and provides the estimated heart rate as output. Finally, we compare the novel deep learning approach to classical methods, performing evaluation on four public datasets. We show that on large datasets the deep learning model significantly outperforms other methods: The mean absolute error could be reduced by $31\%$ on the new dataset PPG-DaLiA, and by $21\%$ on the dataset WESAD.

【 授权许可】

Unknown