Sensor-enabled Activity Class Recognition in Preschoolers

Abstract

Machine learning algorithms such as RF and SVM are useful for predicting PA class from accelerometer data collected in preschool children. Although classifiers trained on hip or wrist data provided acceptable recognition accuracy, the combination of hip and wrist accelerometer delivered better performance.

Population-level physical activity surveillance in young people: are accelerometer-based measures ready for prime time?

“…Over the last decade, there has been a shift from count-based thresholds to machine learning activity classification and energy expenditure estimation algorithms based on features extracted from raw accelerometer signals [15]. When applied to youth, machine learning approaches have shown to provide more accurate predictions of physical activity intensity [13,16]. Moreover, in contrast to cut-point methods, which only estimate time spend in MVPA, physical activity classification models can predict time spent in specific activity types (e.g., walking, running, dancing, cycling) or broader activity classes (e.g., active games or sports) [13,16].…”

“…When applied to youth, machine learning approaches have shown to provide more accurate predictions of physical activity intensity [13,16]. Moreover, in contrast to cut-point methods, which only estimate time spend in MVPA, physical activity classification models can predict time spent in specific activity types (e.g., walking, running, dancing, cycling) or broader activity classes (e.g., active games or sports) [13,16]. This enables researchers in the public health and exercise sciences to explore a greater variety of physical activity metrics as well as examine age-related differences in movement behaviours that are not confounded by developmental differences in the relationship between accelerometer counts and energy expenditure.…”

“…Wrist mounted accelerometers are easier to wear for extended periods and allow investigators to evaluate compliance with more contemporary 24-h movement guidelines which require concurrent monitoring of physical activity, sedentary behaviour, and sleep [18]. With wrist mounted accelerometers, it is critically important that researchers compute physical activity metrics using more sophisticated accelerometer data processing methods [16,19]. Simple cut-point approaches applied to either processed activity counts or raw acceleration signal (i.e., Euclidean Norm Minus One -ENMO) provide misleading estimates of movement behaviour because they do not account for upper limb movements during sedentary or stationary light-intensity activities [20,21].…”

Evaluating and Enhancing the Generalization Performance of Machine Learning Models for Physical Activity Intensity Prediction From Raw Acceleration Data

“…The findings of accelerometry studies as well as in other fields of research can explain why the idea of merging data from multiple population groups and different wear locations is plausible. The use of multiple accelerometers (e.g., hip and wrist) has shown improvements in the prediction accuracy of classification models [40]. For instance, classifying energy-consuming activities in which the wrist motion is limited (e.g., cycling) has been shown to be challenging with wrist accelerometers while the presence of motion from other wear locations (e.g., hip) seems to help classify such activities more accurately (or vice versa for other activities) [15].…”

Recognition of Sedentary Behavior by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living for Telemedical Assessment of Cardiovascular Risk

“…However, Koster et al [ 6 ] pointed out that wrist accelerometers underestimated the sedentary time and in some scenarios sitting time may not be distinguished from standing time-based on accelerometer data. A recent study by Trost et al [ 7 ] using ActiGraph accelerometer on the right hip and nondominant wrist showed 90% accuracy for recognition of sedentary behavior among preschoolers. Authors used Radom Forest and support vector machine classifiers.…”