Estimating Physical Activity Energy Expenditure Using an Ensemble Model-Based Patch-Type Sensor Module

Chronic diseases, such as coronary artery disease and diabetes, are caused by inadequate physical activity the leading cause of increasing mortality morbidity rates. Direct calorimetry calorie production indirect energy expenditure (EE) has been regarded best method for estimating EE. However, this is inconvenient, owing to use an oxygen respiration measurement mask. In study, we propose a model that estimates EE using ensemble combines artificial neural networks genetic algorithms data acquired from patch-type sensors. The proposed achieved accuracy more than 92% (Root Mean Squared Error (RMSE) = 0.1893, R2 0.91, (MSE) 0.014213, Absolute (MAE) 0.14020) testing various structures through repeated experiments.