Skeleton avatar technology as a way to measure physical activity in healthy older adults

Abstract Background Nowadays, self-reported assessments (SA) and accelerometer-based (AC) are commonly used methods to measure daily life physical activity (PA) in older adults. SA is simple, cost-effective, can be large epidemiological studies, but its reliability validity have been questioned. Accelerometer measurement has proven valid provide accurate reliable of everyday activities regarding frequency, duration, intensity populations, expensive requires a long-time measurement. Here is, furthermore, lack well-defined accelerometer cut-off points PA among Therefore, there need develop simple method complement/replace self-assessment facilitate the future development In this study, we explore how skeleton avatar technology (SAT) Objectives 1. To association between data assessment adults, 2. SAT standardized functional (balance) test Method The correlation analysis was response variables, deep neural networks were predict variables (AC outcomes). Results results indicate that moderate (r = 0.31) significant (p = 0.029) AC PA. balance assessed with able 3.89% Mean Absolute Error (MAE), 11.07% MAE. Conclusion Overall, these one measured outcomes devices. better than within same population. More research needed ability predicting adults various abilities, developed using 2D recordings, such as mobile phone efficiently.