Vallis, Lori Ann
Loading...
2 results
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Machine Learning Approaches to Predicting Energy Expenditure in Preschool Children: Insights from Accelerometry, Gyroscope Data, and Cross-National Validation(2025-07-16); ; ; As highlighted by the World Health Organization, physical inactivity has been recognized as a public health crisis affecting not only adults, but also children and adolescents. To address this alarming trend, it is essential to establish a reliable and robust measure of physical activity (PA) to better understand its underlying determinants. For this purpose, wearable sensors are often used, offering an indirect measure to predict/estimate the energy expenditure (EE) of PA. With the adoption of wearable sensors, numerous researchers are implementing more sophisticated machine learning approaches in their analyses that are better equipped to model complex relationships. The overarching aim of this doctoral research was to develop and refine machine learning models to predict the EE of preschool children. Across four studies, key aspects of the modeling process were explored, including model selection, preprocessing strategies, feature selection, sensor integration, the influence of metabolic equivalent (METs) definitions, and external validation. Two calibration datasets, one consisting of Canadian preschool children and the other of German preschool children, were used to develop and evaluate models using accelerometers, gyroscopes, and portable metabolic units during semi-structured activity protocols. The findings indicated that while deep learning models achieved the lowest error on the training datasets, feature-based models demonstrated superior performance in external validation. Furthermore, preprocessing techniques, specifically frequency-based filtering, and the inclusion of frequency-domain features and participant characteristics (age, sex, height, and weight) contributed to reduced prediction error. When comparing models built using gyroscope data, accelerometer data, and a combination of both, the dual-sensor models consistently outperformed single-sensor models, yielding lower error rates. Finally, after identifying the optimal feature set, the models were applied to a large cohort of Canadian children to generate and compare PA estimates based on different METs definitions. Notably, it was found that measuring the resting period, rather than estimating it using predictive approaches, resulted in higher estimates of sedentary time and lower estimates of overall PA. Collectively, this thesis advances the field of movement behavior research by contributing validated machine learning models for estimating EE in preschool children and addressing key methodological questions relevant to this domain.doctoral thesis30 35 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Accelerometers in Young Children: Methodological Considerations and Cross-sectional and Longitudinal Associations with Motor Abilities, Physical Fitness, and Cognitive Function(2021-08-26); ; ; ; Physical activity plays an important role during early childhood and has favourable associations with numerous health outcomes. It is thought that lifestyle and physical activity behaviours may develop within the first five years of life, making the early years an optimal time for targeted intervention and observation. Accelerometers are valid and reliable devices that allow researchers to quantify large amounts of free-living data in young child populations. However, use of these devices are accompanied by many methodological decisions which can create inconsistencies and limit comparability within the literature. The focus of this thesis was to extensively review current methods being used to analyse accelerometer data from young children, examine how certain methodologies affect interpretation of accelerometer outputs, and observe subsequent cross-sectional and longitudinal associations between physical activity and health. An extensive review revealed that hundreds of published studies use accelerometers with a wide variety of data collection and analysis methods to track movement in young children. Applying different thresholds or cutpoints to quantify movement behaviours into specific intensities of movement demonstrated that choice of cutpoint significantly impacts amounts of time spent in each intensity as well as the number of children categorized as meeting physical activity guidelines. A cross-sectional analysis showed that preschool-aged children who met physical activity guidelines did not have greater levels of individual motor abilities compared to children not meeting guidelines, however sports club membership may influence motor ability development. In a longitudinal analysis, children who met physical activity guidelines during early childhood were more likely to meet guidelines during later childhood/adolescence. Additionally, performance on certain physical fitness tests at baseline also predicted greater amounts of time in physical activity and meeting physical activity guidelines at follow-up. Interestingly, meeting physical activity guidelines showed no associations with cognitive function, and some physical fitness tests showed statistically significant associations, but models did not show a substantial goodness of fit. In summary, future work should continue to investigate associations between meeting physical activity guidelines and health outcomes in young children. Given the importance of this work, we strongly encourage researchers to adapt and apply our recommended, standardized accelerometry reporting practice.doctoral thesis188 130