Abstract
Remote photoplethysmography (rPPG) enables non-contact monitoring of biomedical signals using a camera, making it suitable for telemedicine and remote health monitoring. This paper proposes an end-to-end convolutional neural network (CNN) model for estimating blood oxygen saturation (SpO2) from video data. The model is trained and evaluated on a publicly available dataset, showing promising results in accurately estimating SpO2 levels. The proposed approach has the potential to enhance remote health monitoring systems by providing a non-invasive method for SpO2 estimation.
Junghwan Lee
PhD Student
His research interests include machine learning and deep learning algorithms.
Cheolsoo Park
Professor
His research interests include machine learning, adaptive signal processing, computational neuroscience, and wearable technology.