The popularity of smartphones has led researchers to ask if they can replace traditional tools for assessing free-living physical activity. Our purpose was to establish proof-of-concept that a smartphone could record acceleration during physical activity, and those data could be modeled to predict activity type (walking or running), speed (km·h−1), and energy expenditure (METs).
An application to record and e-mail accelerations was developed for the Apple iPhone®/iPod Touch®. Twentyfive healthy adults performed treadmill walking (4.0 km·h−1 to 7.2 km·h−1) and running (8.1 km·h−1 to 11.3 km·h−1) wearing the device. Criterion energy expenditure measurements were collected via metabolic cart.
Activity type was classified with 99% accuracy. Speed was predicted with a bias of 0.02 km·h−1 (SEE: 0.57 km·h−1) for walking, –0.03 km·h−1 (SEE: 1.02 km·h−1) for running. Energy expenditure was predicted with a bias of 0.35 METs (SEE: 0.75 METs) for walking, –0.43 METs (SEE: 1.24 METs) for running.
Our results suggest that an iPhone/iPod Touch can predict aspects of locomotion with accuracy similar to other accelerometer-based tools. Future studies may leverage this and the additional features of smartphones to improve data collection and compliance.
Nolan and Doyle-Baker are with the Faculty of Kinesiology, University of Calgary, Calgary, Alberta, Canada. Mitchell is with the Dept of Health Sciences Research, Mayo Clinic, Scottsdale, AZ.