A Review on Oxygen Consumption and Heart Rate Monitoring Methods & Applications

This study presents a systematic review on the methods used to acquire Oxygen uptake (VO2) and heart rate (HR) for monitoring cardiovascular fitness during daily activities. VO2 and HR play a significant role especially during daily activities such as walking, exercise, or housekeeping. Several studies have been undertaken in recent years to evaluate VO2 and HR in a variety of target populations, mainly in two divisions; Direct Measurements and Estimations. Direct measurements are considered as the gold standard for VO2 and HR measurements. However, despite its high level of accuracy, there are practical limitations associated with direct measurement systems. Direct measurements are expensive and sophisticated laboratory equipment is needed to measure VO2 and HR. On the other hand, estimations via wearable devices using mathematical equations or machine learning are more efficient and low-cost. Utilizing various sets of predictor variables and a variety of machine learning and statistical approaches, several types of measurement models have been formed, including the Support Vector Machine (SVM), Generalized Regression Neural Networks (GRNN), Radial Basis Function Networks (RBFN), multilayer perceptron regressor (MLR) and Decision Tree Forest (DTF). Several studies proves that machine learning is the future direction for estimating VO2 and HR for monitoring cardiovascular fitness during daily activities.