Monitoring Physical Behavior in Rehabilitation Using a Machine Learning-Based Algorithm for Thigh-Mounted Accelerometers: Development and Validation Study.

Frederik Skovbjerg Helene Honoré Inger Mechlenburg Matthijs Lipperts Rikke Gade Erhard Trillingsgaard Næss-Schmidt

Published in: JMIR bioinformatics and biotechnology (2022)

Using a single thigh-mounted accelerometer, we obtained high classification levels within specific behaviors. The behaviors classified with high levels of performance mostly occur in populations with higher levels of functioning. Further development should aim at describing behaviors within populations with lower levels of functioning.

Keyphrases

machine learning
deep learning
physical activity
artificial intelligence
mental health
big data