Browsing by Author "Ucar, Zeliha"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
Article Citation Count: 1Determination gender-based hybrid artificial intelligence of body muscle percentage by photoplethysmography signal(Elsevier Ireland Ltd, 2022) Ucar, Muhammed Kuersad; Ucar, Kubra; Ucar, Zeliha; Bozkurt, Mehmet RecepBackground and objective: Muscle mass is one of the critical components that ensure muscle function. Loss of muscle mass at every stage of life can cause many adverse effects. Sarcopenia, which can occur in different age groups and is characterized by a decrease in muscle mass, is a critical syndrome that affects the quality of life of individuals. Aging, a universal process, can also cause loss of muscle mass. It is essential to monitor and measure muscle mass, which should be sufficient to maintain optimal health. Having various disadvantages with the ordinary methods used to estimate muscle mass increases the need for the new high technology methods. This study aims to develop a low-cost and trustworthy Body Muscle Percentage calculation model based on artificial intelligence algorithms and biomedical signals.Methods: For the study, 327 photoplethysmography signals of the subject were used. First, the photo-plethysmography signals were filtered, and sub-frequency bands were obtained. A quantity of 125 time -domain features, 25 from each signal, have been extracted. Additionally, it has reached 130 features in demographic features added to the model. To enhance the performance, the spearman feature selection algorithm was used. Decision trees, Support Vector Machines, Ensemble Decision Trees, and Hybrid ma-chine learning algorithms (the combination of three methods) were used as machine learning algorithms.Results: The recommended Body Muscle Percentage estimation model have the perfomance values for all individuals R = 0 . 95 , for males R = 0 . 90 and for females R = 0 . 90 in this study.Conclusion: Regarding the study results, it is thought that photoplethysmography-based models can be used to predict body muscle percentage.(c) 2022 Elsevier B.V. All rights reserved.Article Citation Count: 6Determination of body fat percentage by electrocardiography signal with gender based artificial intelligence(Elsevier Sci Ltd, 2021) Ucar, Muhammed Kursad; Ucar, Zeliha; Ucar, Kubra; Akman, Mehmet; Bozkurt, Mehmet RecepBackground 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. ConclusionArticle Citation Count: 19Estimation of body fat percentage using hybrid machine learning algorithms(Elsevier Sci Ltd, 2021) Ucar, Muhammed Kursad; Ucar, Zeliha; Koksal, Fatih; Daldal, NihatBefore obesity treatment, body fat percentage (BFP) should be determined. BFP cannot be measured by weighing. The devices developed to produce solutions to this problem are called "Body Analysis Devices". These devices are very costly. Therefore, more practical and cost-effective solutions are needed. This study aims to determine BFP using hybrid machine learning methods with high accuracy rate and minimum parameter. This study uses real data sets, which are 13 anthropometric measurements of individuals. Different feature groups were created with feature selection algorithm. In the next step, 4 different hybrid models were created by using MLFFNN, SVMs, and DT regression models. According to the results, BFP of individuals can be estimated with a correlation value of R = 0.79 with one anthropometric measurement. The results show that the developed system can be used to estimate BFP in practice. Besides, the system can calculate BFP with just one anthropometric measurement without device requirement. (C) 2020 Elsevier Ltd. All rights reserved.