An artificial neural network model of energy expenditure using nonintegrated acceleration signals

TLDR

Accelerometers are promising for characterizing free‑living physical activity, but their widespread use has been limited by imprecise energy‑expenditure estimates due to oversimplified time‑integrated signals and linear regression models. The study aimed to develop a relationship between raw hip acceleration and minute‑to‑minute energy expenditure in 102 healthy adults using a room calorimeter as the reference standard. Researchers extracted ten acceleration features per minute, trained a feed‑forward artificial neural network (12×20×1 nodes) to predict energy expenditure, and compared its performance with ActiGraph and IDEEA accelerometers. The ANN produced significantly lower mean absolute and squared errors and smaller total energy‑expenditure differences than the IDEEA and ActiGraph regression models, demonstrating that raw acceleration combined with ANN is a promising method for linking body movements to energy expenditure.

Abstract

Accelerometers are a promising tool for characterizing physical activity patterns in free living. The major limitation in their widespread use to date has been a lack of precision in estimating energy expenditure (EE), which may be attributed to the oversimplified time-integrated acceleration signals and subsequent use of linear regression models for EE estimation. In this study, we collected biaxial raw (32 Hz) acceleration signals at the hip to develop a relationship between acceleration and minute-to-minute EE in 102 healthy adults using EE data collected for nearly 24 h in a room calorimeter as the reference standard. From each 1 min of acceleration data, we extracted 10 signal characteristics (features) that we felt had the potential to characterize EE intensity. Using these data, we developed a feed-forward/back-propagation artificial neural network (ANN) model with one hidden layer (12 × 20 × 1 nodes). Results of the ANN were compared with estimations using the ActiGraph monitor, a uniaxial accelerometer, and the IDEEA monitor, an array of five accelerometers. After training and validation (leave-one-subject out) were completed, the ANN showed significantly reduced mean absolute errors (0.29 ± 0.10 kcal/min), mean squared errors (0.23 ± 0.14 kcal 2 /min 2 ), and difference in total EE (21 ± 115 kcal/day), compared with both the IDEEA ( P < 0.01) and a regression model for the ActiGraph accelerometer ( P < 0.001). Thus ANN combined with raw acceleration signals is a promising approach to link body accelerations to EE. Further validation is needed to understand the performance of the model for different physical activity types under free-living conditions.