Description

Four acceleration-based artificial neural networks were developed for estimating energy expenditure in adults using one of four accelerometers- an ActiGraph worn on the right hip or thigh or a GENEActiv worn on either wrist. Adults performed simulated activities of daily living, locomotion, and other exercises and the model was cross-validated using leave-one-out cross validation.

The following models are available. Weighted kappa coefficients are also provided.

• Artificial neural network for hip-worn monitor (0.90)

• Artificial neural network for thigh-worn monitor (0.99)

• Artificial neural network for left wrist-worn monitor (0.95)

• Artificial neural network for right wrist-worn monitor (0.78)

Development/Validation

Sample: 40 (19 males) healthy adults, 18-44 years of age

Setting: Laboratory

Activities: Activities of daily living, cycling, walking and running, resistance exercise, stairs, stationary behaviors

Criterion: Direct observation of activity type and compendium

Accelerometer(s): ActiGraph on right hip or thigh, GENEActiv on either wrist

Validation approach: Leave-one-out cross-validation

Phase Designation

(What's this?)

This model is in Phase 0 and 2.

Instructions

The R code can be used to read in a csv file with the necessary features and then use the neural network to predict physical activity intensity. There is a separate file for each of the four models- hip, thigh, left wrist, and right wrist. There is an example data sheet for each of the four monitor wear locations (hip, thigh, left wrist, right wrist) with the variables described in the data dictionary that need to be present in the csv file. Further instructions are in the R code. More information about R is found here.

This code relies on R software which can be downloaded for free at https://www.r-project.org/

Attached Files

Download all files as a .zip or download individual files below.

Code

Example hip data

Example thigh data

Example left wrist data

Example right wrist data

Data dictionary

Hip model

Thigh model

Left wrist model

Right wrist model

Note: Compared to the original source, code was edited for consistency, example data and a data dictionary were added, models were unchanged

Source Information

Reference:

Montoye, A. H., Pivarnik, J. M., Mudd, L. M., Biswas, S., & Pfeiffer, K. A. (2016). Validation and comparison of accelerometers worn on the hip, thigh, and wrists for measuring physical activity and sedentary behavior. AIMS Public Health, 3(2), 298.

https://doi.org/10.3934/publichealth.2016.2.298 Link to paper

Original source for code:

https://drive.google.com/open?id=0B-BgdTzyd2OxazA1UE1zcTFEY1k

Corresponding author: Alexander H.K. Montoye, montoyeah@alma.edu

Contact

Kimberly Clevenger at accelerometerrepository@gmail.com