Performance comparison of different regression methods for VO<inf>2</inf>max estimation

Abstract

The purpose of this paper is to develop maximal oxygen uptake (VO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> max) models by using different regression methods such as Multilayer Feed-Forward Artificial Neural Networks (MFANN's), Support Vector Regression (SVR), Generalized Regression Neural Networks (GRNN's) and Multiple Linear Regression (MLR). The dataset includes data of 439 subjects and the input variables of the dataset are gender, age, body mass index (BMI), percent body fat (BF), respiratory exchange ratio (RER) from treadmill test, self-reported rating of perceived exertion (RPE) from treadmill test, heart rate (HR) and time to exhaustion from treadmill test. The performance of the models is evaluated by calculating their standard error of estimates (SEE) and multiple correlation coefficients (R). The results suggest that MFANN-based VO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> max prediction models perform better than other prediction models.