An electronic system (100) for estimating a subject's blood pressure, comprising: a feature extraction module (10) configured for receiving a subject's photoplethysmogram signal (PPG1), detecting a plurality of signal characteristic points on said received photoplethysmogram signal (PPG1), calculating a plurality of distances in both time and amplitude between any two of said detected photoplethysmogram signal characteristic points, and providing a feature information signal (FE) comprising information about said calculated distances； and a blood pressure calculation module (20) configured for receiving said photoplethysmogram signal (PPG1), said feature information signal (FE) and anthropometric characteristics (AC) of the subject, and the blood pressure calculation module (20) comprising a first estimation module (21) configured for calculating systolic and diastolic blood pressure values (SBP, DBP) of the subject based on said received feature information signal (FE) and anthropometric characteristics (AC), and a second estimation module (25) configured for calculating continuous mean blood pressure values (CMBP) of the subject based on said calculated systolic and diastolic blood pressure values (SBP, DBP) and said photoplethysmogram signal (PPG1)； and wherein the first estimation module (21) uses a machine-learning regression model for calculating said systolic and diastolic blood pressure values (SBP, DBP) and the second estimation module (25) uses a Hilbert-Huang transform and an empirical mode decomposition process for calculating said continuous mean blood pressure values (CMBP).
