Gender recognition from PPG signals of people with different blood pressure

Abstract

Photoplethysmography (PPG) is an opto-electronic technique that measures the blood volume within micro-vascular tissue. Studies based on measuring blood pressure level with PPG have been widely used. In this study, gender recognition was performed using PPG signals recorded from people with different blood pressure levels. The obtained results showed that the sum of the derivative, kurtosis, median, skewness, variance, variance of the second derivative calculated from the wavelet transform coefficients can be used in gender recognition as an attribute. By using these features, a classification accuracy of 74.77% and a polygon area metric of 0.4961 were obtained with the decision tree classifier. It is thought that gender recognition can be achieved with PPG signals, which can also be measured on touch screens (smart phones, watches and tablets) with the proposed method.