Determination of Body Fat Percentage by Gender Based with Photoplethysmography Signal Using Machine Learning Algorithm

Objective: Calculation of body fat percentage (BFP) is a frequently encountered problem in the literature. BFP is one of the most significant parameters which should be processed in body weight control programs. Anthropometric measurements and statistical methods are being used generally in the literature for BFP estimation. Artificial intelligence and gender-based models with a photoplethysmography signal (PPG) were proposed for BFP estimation in this study. Material and Methods: In the study, the PPG signal is divided into lower frequency bands, and 25 features are taken out from each frequency band. Artificial intelligence algorithms were created by reducing the extracted features with the help of a feature selection algorithm. Results: According to the results obtained, models with performance values of RMSE = 0.35, R =1 for men, RMSE = 0.87, R =1 for women were created. Conclusions: In the best performing models, the PPG signal's high-frequency components are used for men, whereas the low-frequency band of the PPG signal is used for women. As a result, the proposed model in this study is considered to be used for BFP measurement.