Use of a Wireless Network of Accelerometers for Improved Measurement of Human Energy Expenditure

Abstract

Single, hip-mounted accelerometers can provide accurate measurements of energy expenditure (EE) in some settings, but are unable to accurately estimate the energy cost of many non-ambulatory activities. A multi-sensor network may be able to overcome the limitations of a single accelerometer. Thus, the purpose of our study was to compare the abilities of a wireless network of accelerometers and a hip-mounted accelerometer for the prediction of EE. Thirty adult participants engaged in 14 different sedentary, ambulatory, lifestyle and exercise activities for five minutes each while wearing a portable metabolic analyzer, a hip-mounted accelerometer (AG) and a wireless network of three accelerometers (WN) worn on the right wrist, thigh and ankle. Artificial neural networks (ANNs) were created separately for the AG and WN for the EE prediction. Pearson correlations (r) and the root mean square error (RMSE) were calculated to compare criterion-measured EE to predicted EE from the ANNs. Overall, correlations were higher (r = 0.95 vs. r = 0.88, p < 0.0001) and RMSE was lower (1.34 vs. 1.97 metabolic equivalents (METs), p < 0.0001) for the WN than the AG. In conclusion, the WN outperformed the AG for measuring EE, providing evidence that the WN can provide highly accurate estimates of EE in adults participating in a wide range of activities.

Keywords: ActiGraph; activity measurement; artificial neural network; machine learning; multi-sensor network; physical activity.

Figure 1

Artificial neural networks were created for predicting energy expenditure (EE) from the wireless network and the ActiGraph. (a) The artificial neural network (ANN) created for the wireless network; and (b) the ANN created for the ActiGraph accelerometer. Note that the numbers of input and output variables shown match the number used in the study, but only three hidden units are shown in the figure for simplicity. The ANNs in this study had 13 hidden units in the hidden layer.

Figure 2

Measured EE and predicted EE from the wireless network and hip accelerometer for each activity. * Indicates significant difference from the measured EE (p < 0.05). METs, metabolic equivalents.

Figure 3

Correlation coefficients and root mean square error (RMSE) values for predicted METs from the wireless system and hip-mounted ActiGraph ANNs, compared to the measured METs. An asterisk (*) indicates significant differences from the hip-mounted ActiGraph ANN (p < 0.05).