Abstract
Purpose: To compare raw acceleration output of the ActiGraph™ GT3X+ and GENEA activity monitors. Methods: A GT3X+ and GENEA were oscillated in an orbital shaker at frequencies ranging from 0.7 to 4.0 Hz (ten 2-min trials/frequency) on a fixed radius of 5.08 cm. Additionally, 10 participants (age = 23.8 ± 5.4 years) wore the GT3X+ and GENEA on the dominant wrist and performed treadmill walking (2.0 and 3.5 mph) and running (5.5 and 7.5 mph) and simulated free-living activities (computer work, cleaning a room, vacuuming and throwing a ball) for 2-min each. A linear mixed model was used to compare the mean triaxial vector magnitude (VM) from the GT3X+ and GENEA at each oscillation frequency. For the human testing protocol, random forest machine-learning technique was used to develop two models using frequency domain (FD) and time domain (TD) features for each monitor. We compared activity type recognition accuracy between the GT3X+ and GENEA when the prediction model was fit using one monitor and then applied to the other. Z-statistics were used to compare the proportion of accurate predictions from the GT3X+ and GENEA for each model. Results: GENEA produced significantly higher (p < 0.05, 3.5 to 6.2%) mean VM than GT3X+ at all frequencies during shaker testing. Training the model using TD input features on the GENEA and applied to GT3X+ data yielded significantly lower (p < 0.05) prediction accuracy. Prediction accuracy was not compromised when interchangeably using FD models between monitors. Conclusions: It may be inappropriate to apply a model developed on the GENEA to predict activity type using GT3X+ data when input features are TD attributes of raw acceleration.
Highlights
In 2009, the American College of Sports Medicine and the National Institutes of Health co-sponsored the ‘Objective Measurement of Physical Activity: Best Practices and Future Directions’conference to update best practice recommendations for using wearable monitors to assess physical activity [1]
Raw acceleration vector magnitudes were significantly different between the GT3X+ and the GENEA during shaker testing at all four oscillation frequencies
We examined if vector magnitude (VM) of triaxial raw acceleration signals from the GT3X+ and GENEA were similar to each other during mechanical shaker testing and if an activity type recognition model developed using data from one activity monitor could be applied to that from the other and yield similar prediction accuracy
Summary
Conference to update best practice recommendations for using wearable monitors to assess physical activity [1]. An acceleration signal has time-domain (TD) and frequency-domain (FD) features that are used as prediction variables to estimate attributes of physical activity and sedentary behavior [2,3]. Availability of numerous signal features greatly enhances the potential of using complex machine learning techniques to accurately estimate physical activity and sedentary behavior. These techniques are becoming increasingly popular, as they provide improved estimates as compared to the traditional activity count cut-points [3,4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
