Background: Heart rate (HR) during physical activity is strongly affected by the level of physical fitness. Therefore, to assess the effects of fitness, we developed predictive equations to estimate the metabolic equivalent (MET) of daily activities, which includes low intensity activities, by % HR reserve (%HRR), resting HR, and multiple physical characteristics. Methods: Forty volunteers between the ages of 21 and 55 performed 20 types of daily activities while recording HR and sampling expired gas to evaluate METs values. Multiple regression analysis was performed to develop prediction models of METs with seven potential predictors, such as %HRR, resting HR, and sex. The contributing parameters were selected based on the brute force method. Additionally, leave-one-out method was performed to validate the prediction models. Results: %HRR, resting HR, sex, and height were selected as the independent variables. %HRR showed the highest contribution in the model, while the other variables exhibited small variances. METs were estimated within a 17.3% difference for each activity, with large differences in document arrangement while sitting (+17%), ascending stairs (−8%), and descending stairs (+8%). Conclusions: The results showed that %HRR is a strong predictor for estimating the METs of daily activities. Resting HR and other variables were mild contributors. (201 words)
BackgroundHerein, an algorithm that can be used in wearable health monitoring devices to estimate metabolic equivalents (METs) based on physical activity intensity data, particularly for certain activities in daily life that make MET estimation difficult.ResultsEnergy expenditure data were obtained from 42 volunteers using indirect calorimetry, triaxial accelerations and heart rates. The proposed algorithm used the percentage of heart rate reserve (%HRR) and the acceleration signal from the wearable device to divide the data into a middle-intensity group and a high-intensity group (HIG). The two groups were defined in terms of estimated METs. Evaluation results revealed that the classification accuracy for both groups was higher than 91%. To further facilitate MET estimation, five multiple-regression models using different features were evaluated via leave-one-out cross-validation. Using this approach, all models showed significant improvements in mean absolute percentage error (MAPE) of METs in the HIG, which included stair ascent, and the maximum reduction in MAPE for HIG was 24% compared to the previous model (HJA-750), which demonstrated a 70.7% improvement ratio. The most suitable model for our purpose that utilized heart rate and filtered synthetic acceleration was selected and its estimation error trend was confirmed.ConclusionFor HIG, the MAPE recalculated by the most suitable model was 10.5%. The improvement ratio was 71.6% as compared to the previous model (HJA-750C). This result was almost identical to that obtained from leave-one-out cross-validation. This proposed algorithm revealed an improvement in estimation accuracy for activities in daily life; in particular, the results included estimated values associated with stair ascent, which has been a difficult activity to evaluate so far.
As described in this paper, a physical activity classification algorithm is proposed for energy expenditure estimation. The proposed algorithm can improve the classification accuracy using both the triaxial acceleration and heart rate. The optimal classification also contributes to improvement of the accuracy of the energy expenditures estimation. The proposed algorithm employs three indices: the heart rate reserve (%HRreserve), the filtered triaxial acceleration, and the ratio of filtered and unfiltered acceleration. The percentage HRreserve is calculated using the heart rate at rest condition and the maximum heart rate, which is calculated using Karvonen Formula. Using these three indices, a decision tree is constructed to classify physical activities into five classes: sedentary, household, moderate (excluding locomotive), locomotive, and vigorous. Evaluation results show that the average classification accuracy for 21 activities is 91%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.