Description

Four models were developed for classifying physical activity intensity in adults using a GENEActiv accelerometer worn on the left wrist. Models were trained using adults performing simulated activities of daily living, locomotion, and other exercises and cross-validated in an independent sample who performed similar activities.

The following models are available. Classification accuracy is also provided.

• Artificial neural network (77.7%*)

• Random forest (78.5%*)

• Decision tree (75.7%*)

• Support vector machine (70.9%*)

*which specific models are provided is not indicated so these are approximate

Development/Validation

Sample: 39 (19 males) healthy adults, 18-35 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 the MET compendium

Accelerometer(s): GENEActiv on the left wrist

Validation approach: Cross-validation in an independent sample of 24 adults

Phase Designation

(What's this?)

This model is in Phase 0, 1, and 4.

Instructions

The R code can be used to read in a csv file with the necessary features and then use the chosen model to predict energy expenditure in METs for 30-sec windows. There is a separate file for each of the four models- the artificial neural network, random forest, decision tree, and support vector machine. There is an example data sheet 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 data

Data dictionary

Artificial neural network model

Random forest model

Decision tree model

Support vector machine model

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

Source Information

Montoye, A. H., Westgate, B. S., Fonley, M. R., & Pfeiffer, K. A. (2018). Cross-validation and out-of-sample testing of physical activity intensity predictions with a wrist-worn accelerometer. Journal of Applied Physiology, 124(5), 1284-1293. https://doi.org/10.1152/japplphysiol.00760.2017 Link to article

Original source for code:

https://drive.google.com/file/d/0B-BgdTzyd2OxMGlLR1ZhTj-I0R28/view

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

Contact

Kimberly Clevenger at accelerometerrepository@gmail.com