The pervasiveness of wearable technology has opened the market for products that analyse running biomechanics and provide feedback to the user. To improve running technique feedback should target specific running biomechanical key points and promote an external focus. Aim for this study was to define and empirically test tailored feedback requirements for optimal motor learning in four consumer available running wearables. First, based on desk research and observations of coaches, a screening protocol was developed. Second, four wearables were tested according to the protocol. Third, results were reviewed, and four experts identified future requirements. Testing and reviewing the selected wearables with the protocol revealed that only two less relevant running biomechanical key points were measured. Provided feedback promotes an external focus of the user. Tailoring was absent in all wearables. These findings indicate that consumer available running wearables have a potential for optimal motor learning but need improvements as well.
Background: Motor learning is central to domains such as sports and rehabilitation; however, often terminologies are insufficiently uniform to allow effective sharing of experience or translation of knowledge. A study using a Delphi technique was conducted to ascertain level of agreement between experts from different motor learning domains (i.e., therapists, coaches, researchers) with respect to definitions and descriptions of a fundamental conceptual distinction within motor learning, namely implicit and explicit motor learning. Methods: A Delphi technique was embedded in multiple rounds of a survey designed to collect and aggregate informed opinions of 49 international respondents with expertise related to motor learning. The survey was administered via an online survey program and accompanied by feedback after each round. Consensus was considered to be reached if $70% of the experts agreed on a topic. Results: Consensus was reached with respect to definitions of implicit and explicit motor learning, and seven common primary intervention strategies were identified in the context of implicit and explicit motor learning. Consensus was not reached with respect to whether the strategies promote implicit or explicit forms of learning. Discussion: The definitions and descriptions agreed upon may aid translation and transfer of knowledge between domains in the field of motor learning. Empirical and clinical research is required to confirm the accuracy of the definitions and to explore the feasibility of the strategies that were identified in research, everyday practice and education.
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.
"RoseGuardian" is een unieke samenwerking tussen de bedrijven Compas Agro BV, Frank Coenders Kwekerijen BV en Fontys Hogeschool met haar onderzoeks- en technologiegroep GreenTechLab. Dit project heeft als doel om gezamenlijk robotica toe te passen om de onkruidverwijdering en het beheer in de open teelt van rozen te verbeteren. Het project richt zich op het onderzoeken, testen en valideren van onkruidherkenning voor het elimineren van onkruid. Het doel van het project is de efficiëntie te verhogen, de arbeidskosten te verlagen en de gewasopbrengst te verbeteren terwijl de milieueffecten tot een minimum worden beperkt. Het project brengt de expertise van de bedrijven Compas Agro en Frank Coenders Kwekerijen op het gebied van vollegrondteelt samen met de expertise van GreenTechLab op het gebied van precisietuinbouw en robotica. Er wordt gestreefd naar een resultaat waarbij het lukt: - Om de beste methode voor het verwijderen van onkruid te onderzoeken. - Om onkruid en niet-onkruid te identificeren met behulp van een vision applicatie op basis van deep learning en AI. - Om praktijktesten te doen om onkruid te verwijderen in een proefomgeving. Hier vindt de validatie van dit project plaats.
