This paper describes experiments with a game device that was used for early detection of delays in motor skill development in primary school children. Children play a game by bi-manual manipulation of the device which continuously collects ac- celerometer data and game state data. Features of the data are used to discriminate between normal children and children with delays. This study focused on the feature selection. Three features were compared: mean squared jerk (time domain); power spectral entropy (fourier domain) and cosine similarity measure (quality of game play). The discriminatory power of the features was tested in an experiment where 28 children played games of different levels of difficulty. The results show that jerk and cosine similarity have reasonable discriminatory power to detect fine-grained motor skill development delays especially when taking the game level into account. Duration of a game level needs to be at least 30 seconds in order to achieve good classification results.
DOCUMENT
BackgroundThe closing of schools and sports clubs during the COVID-19 lockdown raised questions about the possible impact on children’s motor skill development. Therefore, we compared motor skill development over a one-year period among four different cohorts of primary school children of which two experienced no lockdowns during the study period (control cohorts) and two cohorts experienced one or two lockdowns during the study period (lockdown cohorts).MethodsA total of 992 children from 9 primary schools in Amsterdam (the Netherlands) participated in this study (age 5 – 7; 47.5% boys, 52.5% girls). Their motor skill competence was assessed twice, first in grade 3 (T1) and thereafter in grade 4 (T2). Children in control group 1 and lockdown group 1 were assessed a third time after two years (T3). Motor skill competence was assessed using the 4-Skills Test, which includes 4 components of motor skill: jumping force (locomotion), jumping coordination (coordination), bouncing ball (object control) and standing still (stability). Mixed factorial ANOVA’s were used to analyse our data.ResultsNo significant differences in motor skill development over the study period between the lockdown groups and control groups (p > 0.05) were found, but a difference was found between the two lockdown groups: lockdown group 2 developed significantly better than lockdown group 1 (p = 0.008). While socioeconomic status was an effect modifier, sex and motor ability did not modify the effects of the lockdowns.ConclusionsThe COVID-19 lockdowns in the Netherlands did not negatively affect motor skill development of young children in our study. Due to the complexity of the factors related to the pandemic lockdowns and the dynamic systems involved in motor skill development of children, caution must be taken with drawing general conclusions. Therefore, children’s motor skill development should be closely monitored in the upcoming years and attention should be paid to individual differences.
MULTIFILE
BACKGROUND: Approximately 5%-10% of elementary school children show delayed development of fine motor skills. To address these problems, detection is required. Current assessment tools are time-consuming, require a trained supervisor, and are not motivating for children. Sensor-augmented toys and machine learning have been presented as possible solutions to address this problem.OBJECTIVE: This study examines whether sensor-augmented toys can be used to assess children's fine motor skills. The objectives were to (1) predict the outcome of the fine motor skill part of the Movement Assessment Battery for Children Second Edition (fine MABC-2) and (2) study the influence of the classification model, game, type of data, and level of difficulty of the game on the prediction.METHODS: Children in elementary school (n=95, age 7.8 [SD 0.7] years) performed the fine MABC-2 and played 2 games with a sensor-augmented toy called "Futuro Cube." The game "roadrunner" focused on speed while the game "maze" focused on precision. Each game had several levels of difficulty. While playing, both sensor and game data were collected. Four supervised machine learning classifiers were trained with these data to predict the fine MABC-2 outcome: k-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), and support vector machine (SVM). First, we compared the performances of the games and classifiers. Subsequently, we compared the levels of difficulty and types of data for the classifier and game that performed best on accuracy and F1 score. For all statistical tests, we used α=.05.RESULTS: The highest achieved mean accuracy (0.76) was achieved with the DT classifier that was trained on both sensor and game data obtained from playing the easiest and the hardest level of the roadrunner game. Significant differences in performance were found in the accuracy scores between data obtained from the roadrunner and maze games (DT, P=.03; KNN, P=.01; LR, P=.02; SVM, P=.04). No significant differences in performance were found in the accuracy scores between the best performing classifier and the other 3 classifiers for both the roadrunner game (DT vs KNN, P=.42; DT vs LR, P=.35; DT vs SVM, P=.08) and the maze game (DT vs KNN, P=.15; DT vs LR, P=.62; DT vs SVM, P=.26). The accuracy of only the best performing level of difficulty (combination of the easiest and hardest level) achieved with the DT classifier trained with sensor and game data obtained from the roadrunner game was significantly better than the combination of the easiest and middle level (P=.046).CONCLUSIONS: The results of our study show that sensor-augmented toys can efficiently predict the fine MABC-2 scores for children in elementary school. Selecting the game type (focusing on speed or precision) and data type (sensor or game data) is more important for determining the performance than selecting the machine learning classifier or level of difficulty.
DOCUMENT
