Application of Raw Accelerometer Data and Machine-Learning Techniques to Characterize Human Movement Behavior: A Systematic Scoping Review.

CONCLUSIONS: Machine-learning algorithms demonstrate good accuracy when predicting physical activity components; however, their application to free-living settings is currently uncertain.
PMID: 32035416 [PubMed - as supplied by publisher]

Source: Journal of Physical Activity and Health - February 9, 2020 Category: Sports Medicine Tags: J Phys Act Health Source Type: research