Biometric Recognition System Based on Photoplethysmography Signals Recorded During Squat Movement and Rest

In parallel with technological developments, the usage areas of biometric systems are getting more attention. Photoplethysmography (PPG) based biometry applications have attracted attention in recent years with their safe and practical applicability. In this study, PPG signals were recorded from 7 volunteers not only in resting state but also during squat movement, and biometric recognition performances were compared. Total amplitude, covariance, kurtosis, skewness, quadratic integral and maximum fractal length values of the first derivative of the signals were extracted as features from the PPG signals. These have been tested with k-nearest neighborhood, naive Bayesian and decision tree classifiers. The results showed that the PPG signals recorded during the squat movement, with 99.65%, would provide higher recognition than the PPG signals of the resting state.