This paper presented at the American Speech and Haering Association Convention provides information on the accomplishments in international cooperation, education, consumers issues and collaborative research projects on cluttering
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.
This article describes the translation and cultural adaptation process of the WRITIC (Writing Readiness Inventory Tool in Context) into European Portuguese. We examined the content and convergent validity, test-retest, and interrater reliability on the norm-referenced subdomain of the Portuguese (PT) WRITIC Task Performance (TP). To establish content validity, we consulted six experts in handwriting. Internal consistency was found with 70 children, test-retest reliability with 65, inter-rater reliability with 69, and convergent validity with 87. All participants were typically developing kindergarten children. Convergent validity was examined with the Beery–Buktenica Developmental Test of Visual-Motor Integration (Beery™VMI-6) and the Nine Hole Peg-Test (9-HPT). On content validity, we found an agreement of 93%, a good internal consistency with Cronbach’s alpha of 0.72, and an excellent test-retest and inter-rater reliability with ICCs of 0.88 and 0.93. Correlations with Beery™VMI-6 and 9-HPT were moderate (r from 0.39 to 0.65). Translation and cross-cultural adaptation of WRITIC into European Portuguese was successful. WRITIC-PT-TP is stable over time and between raters; it has excellent internal consistency and moderate correlations with Beery™VMI-6 and 9-HPT. This analysis of the European Portuguese version of WRITIC gives us the confidence to start the implementation process of WRITIC-PT in Portugal.
In summer 2020, part of a quay wall in Amsterdam collapsed, and in 2010, construction for a parking lot in Amsterdam was hindered by old sewage lines. New sustainable electric systems are being built on top of the foundations of old windmills, in places where industry thrived in the 19th century. All these examples have one point in common: They involve largely unknown and invisible historic underground structures in a densely built historic city. We argue that truly circular building practices in old cities require smart interfaces that allow the circular use of data from the past when planning the future. The continuous use and reuse of the same plots of land stands in stark contrast with the discontinuity and dispersed nature of project-oriented information. Construction and data technology improves, but information about the past is incomplete. We have to break through the lack of historic continuity of data to make building practices truly circular. Future-oriented construction in Amsterdam requires historic knowledge and continuous documentation of interventions and findings over time. A web portal will bring together a range of diverse public and private, professional and citizen stakeholders, each with their own interests and needs. Two creative industry stakeholders, Yume interactive (Yume) and publisher NAI010, come together to work with a major engineering office (Witteveen+Bos), the AMS Institute, the office of Engineering of the Municipality of Amsterdam, UNESCO NL and two faculties of Delft University of Technology (Architecture and Computer Science) to inventorize historic datasets on the Amsterdam underground. The team will connect all the relevant stakeholders to develop a pilot methodology and a web portal connecting historic data sets for use in contemporary and future design. A book publication will document the process and outcomes, highlighting the need for circular practices that tie past, present and future.
