A fuzzy filtering based system for maximal oxygen uptake prediction using heart rate variability analysis

Abstract

An attempt has been made to predict the maximum oxygen uptake (VO2max) of an individual from a submaximum load test. The aim is to predict the VO2max from an analysis of the heart rate signal collected during the first 3 minutes of an incremental bicycle ergometer exercise test. The features of the heart rate signal are extracted in frequency domain using the continuous wavelet transform. The relationships between the signal features and corresponding VO2max are complicated by the uncertainties arising due to several factors (e.g. age, gender, etc.) related to individual behavior. A fuzzy filter is used for separating uncertainties from the modeling problem and then assessing the worst effect of uncertainties on the predicted VO2max. The method is studied with the experimental data of 49 subjects (24 females, 25 males, ag ed 28–56 years).