In Frontiers in psychology ; h5-index 92.0
How can researchers best measure infants' motor experiences in the home? Body position-whether infants are held, supine, prone, sitting, or upright-is an important developmental experience. However, the standard way of measuring infant body position, video recording by an experimenter in the home, can only capture short instances, may bias measurements, and conflicts with physical distancing guidelines resulting from the COVID-19 pandemic. Here, we introduce and validate an alternative method that uses machine learning algorithms to classify infants' body position from a set of wearable inertial sensors. A laboratory study of 15 infants demonstrated that the method was sufficiently accurate to measure individual differences in the time that infants spent in each body position. Two case studies showed the feasibility of applying this method to testing infants in the home using a contactless equipment drop-off procedure.
Franchak John M, Scott Vanessa, Luo Chuan
body position, human activity recognition, machine learning, motor development, posture, wearable sensors