Ucar, Muhammed KursadUcar, ZelihaUcar, KubraAkman, MehmetBozkurt, Mehmet Recep2024-05-252024-05-25202161746-80941746-810810.1016/j.bspc.2021.1026502-s2.0-85104667683https://doi.org/10.1016/j.bspc.2021.102650https://hdl.handle.net/20.500.14517/1621Bozkurt, Mehmet Recep/0000-0003-0673-4454; UCAR, Muhammed Kursad/0000-0002-0636-8645; AKMAN, MEHMET/0000-0001-9995-4426; UCAR, KUBRA/0000-0001-5970-9784Background and purpose: Body fat percentage (BFP) is a frequently used parameter in the assessment of body composition. The body is made up of fat, muscle and lean body tissues. Excess fat tissue in the body causes obesity. Obesity is a treatable disease that decreases the quality of life. Obesity can trigger ailments such as psychological disorders, cardiovascular diseases and respiratory and digestive problems. Dual energy X-ray absorptiometry gold standard method is laborious, costly and time consuming. For this reason, more practical methods are needed. The aim of this study is to develop BFP prediction models with gender-based electrocardiography (ECG) signal and machine learning methods. Methods: In the study, 25 features were extracted from seven different QRS bands and filtered and unfiltered ECG signals. In addition, age, height and weight were used as features. Spearman feature selection algorithm was used to increase the performance. Results: The BFP prediction models developed have performance values of R = 0.94 for men and R = 0.93 for women and R = 0.91 for all individuals. Feature selection algorithm helped increase performance. Conclusioneninfo:eu-repo/semantics/closedAccessElectrocardiography signalMachine learningArtificial intelligenceBody compositionBody fat percentageGender based body fat percentageArticleQ2Q168WOS:000670369200003