Related Experiment Video
Updated: Jan 24, 2026

Using Fiberless, Wearable fNIRS to Monitor Brain Activity in Real-world Cognitive Tasks
Published on: December 2, 2015
Automatic Identification of Physical Activity Type and Duration by Wearable Activity Trackers: A Validation Study
Diana Dorn1, Jessica Gorzelitz1, Ronald Gangnon2
1Department of Kinesiology, University of Wisconsin-Madison, Madison, WI, United States.
Wearable activity trackers accurately identify common activities like walking and running, but duration accuracy varies. Complex activities, such as a run within walking, show poor accuracy in these devices.
Area of Science:
- Biomedical Engineering
- Health Informatics
- Sports Science
Background:
- Activity trackers are increasingly used for health promotion and chronic disease management.
- Understanding the accuracy of wearable technology is crucial for its effective use in health research.
- Previous studies validated steps and heart rate, but not automatic activity type and duration detection.
Purpose of the Study:
- To evaluate the accuracy of 4 commercial wearable activity trackers in automatically detecting physical activity type and duration.
- To compare the performance of Fitbit Flex 2, Fitbit Alta HR, Fitbit Charge 2, and Garmin Vívosmart HR in a controlled environment.
Main Methods:
- Tested 8 activity types (walking, running, elliptical, biking, swimming) with 69 healthy adults.
- Activities included treadmill and outdoor variations, and complex sequences (run within walking).
- Compared tracker data against study personnel recordings using descriptive statistics and mean absolute percent error (MAPE).
Main Results:
- Activity type recognition was high for treadmill walking (93-97%) and running (93-100%), and outdoor walking/running (97-100%).
- Accuracy varied significantly for elliptical (3-97%), biking (44-97%), and complex run-walk sequences (36-62%).
- Duration accuracy (MAPE) ranged from 4.9% (outdoor walking) to 144.8% (treadmill running).
Conclusions:
- Wearable trackers accurately recognize common physical activities in controlled settings, particularly walking and running.
- Activity duration measurement accuracy differs significantly across activity types and tracker models.
- Complex activity patterns pose challenges for current wearable activity tracker accuracy.
More Related Videos
05:51Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
Published on: February 21, 2025
07:47Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
Published on: February 14, 2018
Related Concept Videos
Co-activators and Co-repressors
Techniques of therapeutic communication I: Active Listening, Sharing Observations, Validation, and Using Touch
Therapeutic communication is not the same as social interaction. Social interaction has no goal or purpose and consists of casual information sharing, whereas therapeutic communication has a plan or purpose for the conversation. Therapeutic...
tRNA Activation
Activation Energy
Eukaryotic Transcription Activators
The binding domains are capable of recognizing and interacting with regulatory sequences on the DNA. These...
Secondary Active Transport