Related Experiment Video
Updated: Jun 25, 2026
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
Published on: December 11, 2015
Accurate measurement of simulated slow and altered walking activity: Apple Watch best in class wearable devices
Grant Rowe1, David Weight2,3, Alethea Rea2
1Discipline of Psychology, College of Science, Health, Engineering and Education, Murdoch University, Perth, Western Australia, Australia.
Background:
Wearable activity devices, widely used to monitor physical activity in non-injured populations, have shown potential in encouraging early ambulation and enhanced recovery in hospitalised patients. This study evaluated the accuracy of wearable devices in tracking step counts under simulated hospital conditions, seeking the optimal body location placement for individuals with altered gait.
Methods:
This method comparison study involved healthy adults walking on a treadmill while performing slow and shuffling walking patterns. Twelve wearable devices were placed on the arm, waist, and leg, and their recorded step counts were compared to manual counts from filmed sessions, following Consumer Technology Association guidelines.
Results:
The Apple Watch, particularly when worn on the waist, demonstrated the highest reliability and adaptability across walking patterns. Leg placement, which accounted for 10 of the top 20 device-position combinations, suggested that larger movement amplitudes improve step count accuracy, particularly during slow or altered gaits.
Conclusion:
This study confirmed the Apple Watch to be the most accurate wearable step count device. The study provides new understanding as to the precision of commercially available devices and their placement, when aiming to improve and, or conduct research about, patient physical activity outcomes.
