Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

To achieve non-invasive, non-contact, and real-time heart rate monitoring, proposed a pulse signal acquisition system using PVDF (Polyvinylidene Fluoride) piezoelectric film. In order to address the issue of errors in heart rate extraction caused by differences in the morphology of pulse signals across individuals or in different states, the K-means clustering algorithm was innovatively used to locate the peak of pulse waveforms in different states and constructed a heart rate data set. Real-time heart rate monitoring by training a large number of pulse signal samples with the proposed CNN-LSTM network model. Experimental results demonstrated that the performance metrics of this model, including the MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and R² (Coefficient of Determination), are 0.2517, 0.3395, and 0.9863, respectively. the maximum error between the proposed system and the standard instrument within three minutes was only 1.55 beats/minute, indicating that the system exhibits high accuracy and reliability, and holds great potential for applications in heart rate detection.