A Contactless Method for Measuring Full-Day, Naturalistic Motor Behavior Using Wearable Inertial Sensors

Abstract

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.

Online testing in developmental science: A guide to design and implementation

“…An additional two infants were tested at home and served as a case study. These exploratory data demonstrated that the wearable sensors used at home were able to distinguish changes in the relative duration of positions throughout the day (see Franchak et al, 2021 for more details). However, the authors note that sensitivity varied among participants and positions, which will have to be addressed in future research.…”

“…Turning to other remote methods, a recent study explored the possibilities of analyzing data from wearable sensors (Franchak et al, 2021). In this study, the data of 15 infants was collected in the lab.…”

Quantifying States and Transitions of Emerging Postural Control for Children Not Yet Able to Sit Independently

“…Wearable sensors were selected for objective quantification of postural behavior because of their small size, ease of application, and potential for future use across a variety of locations. They are child-friendly and have potential scalability across time (minutes to hours to full days) and settings (laboratory, clinical, home, and community) [ 55 , 56 ]. Wearable sensors are used in research and as consumer products for ambulatory individuals to measure a number of physical behaviors (e.g., steps, activity level, and fall detection) [ 57 , 58 ].…”

Milestones or Millstones: How Standard Assessments Mask Cultural Variation and Misinform Policies Aimed at Early Childhood Development

“…For example, the amount of motor experience after onset of a skill has been estimated by meticulously counting steps of infants who have recently begun to walk and those who have been walking for months (Adolph et al, 2012), and documenting every plaything encountered in infants who have been grasping objects for months (Herzberg et al, 2021). Only recently have new technologies begun to capture infants’ everyday experience and practice leading up to skill onset (Franchak, 2019; Franchak et al, 2021; Rosales et al, 2021). Clever experimental designs have recently documented how enhanced practice leads to earlier expression of a skill (Adolph & Hoch, 2019 for review) and may effect changes in other developing domains such as communication (Karasik et al, 2014; Libertus et al, 2016; Walle & Campos, 2014).…”