A Novel Identity Authentication Method by Modeling Photoplethysmograph Waveform

In order to improve the reliability of identity authentication, this study explores a novel photoplethysmograph (PPG) based method. First, a morphology modeling method is proposed to quantitatively describe the PPG waveform with 12 features. The probabilistic neural network (PNN) and random forest (RF) are used to recognize which subject the PPG waveforms belong to. Then, the measured PPG signals are engaged as the experimental data to validate the proposed method. The experimental results show that the performance of RF is better than that of PNN, the average kappa coefficient is over 93%. Therefore, the proposed method has great potential in identity authentication by wearable devices.