A general framework for generative self-supervised learning in non-invasive estimation of physiological parameters using photoplethysmography

Zexing Zhang, Huimin Lu, Songzhe Ma, Jianzhong Peng, Chenglin Lin, Niya Li, Bingwang Dong

Abstract: Highlights•Generative-based SSRL framework TS2TC models PPG for universal parameter estimation.•Demonstrating method effectiveness through diverse, extensive experiments.•DPT strategy leverages shared and specific representations for enhanced learning.•Bilinear temporal-spectrogram fusion aligns features from different domains.•The proposed framework performs well in mainstream physiological parameter estimation tasks.