There is accumulating evidence supporting the association between neighborhood built environments and adults’ physical activity (PA) and sedentary time (ST); however, few studies have investigated these associations in adolescents. A better understanding of the features of the built environment that encourage PA or ST is therefore of critical importance to promote health and wellbeing in adolescents. The aim of this study was to estimate the associations of GIS-determined and perceived walkability components in individual residential buffer zones with accelerometer-assessed moderate-to-vigorous physical activity (MVPA) and ST in adolescents. The Built Environment in Adolescent New Zealanders (BEANZ) study was conducted in two cities (Auckland and Wellington) during the 2013-2014 academic school years. The exposure measures were subjective and objective environmental indices of activity-friendliness using four residential buffers. Road network buffers were calculated around participant’s residential addresses using the sausage buffer approach at 250 m, 500 m, 1 km, and 2 km scales. A 25 m radius was used for the buffers. Data were analysed using Generalized Additive Mixed Models in R. Data were analysed from 524 participants (15.78 ± 1.62 years; 45% male). Participants accumulated ~114 min/day of moderate-to-vigorous PA (MVPA) and ~354 min/day of ST during accelerometer wear-time (~828 min/day). The estimated difference in MVPA between participants with the 1st and 3rd quartiles observed values on the composite subjective environmental index of activity-friendliness (perceived land use mix - diversity, street connectivity and aesthetics) was equivalent to ~8 min/day (~56 MVPA min/week) and for the objective environmental index of activity-friendliness (gross residential density and number of parks within 2 km distance from home) was ~6 min of MVPA/day (~45 MVPA min/week). When both indices were entered in a main-effect model, both indices remained significantly correlated with MVPA with sex as a moderator. The predicted difference in sedentary time between those with the minimum and maximum observed values on the subjective index of non-sedentariness was ~20 min/day. The combined assessment of the main effects of subjective and objective indices of activity-friendliness on NZ adolescents’ PA and ST showed positive relationships with MVPA for the subjective index only. The subjective index was a significant correlate of PA in both girls and boys, while the objective index was significant only in boys when sex was entered as a moderator. Further research is warranted to understand the relationships of ST with the built environment.

Background: Application of machine learning for classifying human behavior is increasingly common as access to raw accelerometer data improves. The aims of this scoping review are (1) to examine if machine-learning techniques can accurately identify human activity behaviors from raw accelerometer data and (2) to summarize the practical implications of these machine-learning techniques for future work. Methods: Keyword searches were performed in Scopus, Web of Science, and EBSCO databases in 2018. Studies that applied supervised machine-learning techniques to raw accelerometer data and estimated components of physical activity were included. Information on study characteristics, machine-learning techniques, and key study findings were extracted from included studies. Results: Of the 53 studies included in the review, 75% were published in the last 5 years. Most studies predicted postures and activity type, rather than intensity, and were conducted in controlled environments using 1 or 2 devices. The most common models were support vector machine, random forest, and artificial neural network. Overall, classification accuracy ranged from 62% to 99.8%, although nearly 80% of studies achieved an overall accuracy above 85%. Conclusions: Machine-learning algorithms demonstrate good accuracy when predicting physical activity components; however, their application to free-living settings is currently uncertain.

Introduction: Accurately monitoring 24-h movement behaviors is a vital step for progressing the time-use epidemiology field. Past accelerometer-based measurement protocols are either hindered by lack of wear time compliance, or the inability to accurately discern activities and postures. Recent work has indicated that skin-attached dual-accelerometers exhibit excellent 24-h uninterrupted wear time compliance. This study extends this work by validating this system for classifying various physical activities and sedentary behaviors in children and adults. Methods: Seventy-five participants (42 children) were equipped with two Axivity AX3 accelerometers; one attached to their thigh, and one to their lower back. Ten activity trials (e.g., sitting, standing, lying, walking, running) were performed while under direct observation in a lab setting. Various time- and frequency-domain features were computed from raw accelerometer data, which were then used to train a random forest machine learning classifier. Model performance was evaluated using leave-one-out cross-validation. The efficacy of the dual-sensor protocol (relative to single sensors) was evaluated by repeating the modeling process with each sensor individually. Results: Machine learning models were able to differentiate between six distinct activity classes with exceptionally high accuracy in both adults (99.1%) and children (97.3%). When a single thigh or back accelerometer was used, there was a pronounced drop in accuracy for nonambulatory activities (up to a 26.4% decline). When examining the features used for model training, those that took the orientation of both sensors into account concurrently were more important predictors. Conclusions: When previous wear time compliance results are taken together with our findings, it represents a promising step forward for monitoring and understanding 24-h time-use behaviors. The next step will be to examine the generalizability of these findings in a free-living setting.