Document Detail


An artificial neural network model of energy expenditure using nonintegrated acceleration signals.
MedLine Citation:
PMID:  17641221     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
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 x 20 x 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.
Authors:
Megan P Rothney; Megan Neumann; Ashley Béziat; Kong Y Chen
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, N.I.H., Extramural; Validation Studies     Date:  2007-07-19
Journal Detail:
Title:  Journal of applied physiology (Bethesda, Md. : 1985)     Volume:  103     ISSN:  8750-7587     ISO Abbreviation:  J. Appl. Physiol.     Publication Date:  2007 Oct 
Date Detail:
Created Date:  2007-10-05     Completed Date:  2007-12-06     Revised Date:  2013-09-26    
Medline Journal Info:
Nlm Unique ID:  8502536     Medline TA:  J Appl Physiol (1985)     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1419-27     Citation Subset:  IM    
Affiliation:
Department of Biomedical Engineering, Vanderbilt University Medical Center, Nashville, Tennessee, USA. rothneym@niddk.nih.gov
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Acceleration*
Adolescent
Adult
Aged
Calorimetry, Indirect / methods
Energy Metabolism / physiology*
Exercise / physiology
Female
Hip
Humans
Image Processing, Computer-Assisted
Male
Middle Aged
Monitoring, Physiologic / instrumentation,  methods*
Motor Activity / physiology*
Neural Networks (Computer)*
Reproducibility of Results
Grant Support
ID/Acronym/Agency:
DK-02973/DK/NIDDK NIH HHS; DK-069465/DK/NIDDK NIH HHS; HL-082988/HL/NHLBI NIH HHS; RR-00095/RR/NCRR NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Acute changes in cardiovascular function during the onset period of daytime sleep: comparison to lyi...
Next Document:  Postactivation potentiation in a human muscle: effect on the load-velocity relation of tetanic and v...