With artificial intelligence (AI) systems entering our working and leisure environments with increasing adaptation and learning capabilities, new opportunities arise for developing hybrid (human-AI) intelligence (HI) systems, comprising new ways of collaboration. However, there is not yet a structured way of specifying design solutions of collaboration for hybrid intelligence (HI) systems and there is a lack of best practices shared across application domains. We address this gap by investigating the generalization of specific design solutions into design patterns that can be shared and applied in different contexts. We present a human-centered bottom-up approach for the specification of design solutions and their abstraction into team design patterns. We apply the proposed approach for 4 concrete HI use cases and show the successful extraction of team design patterns that are generalizable, providing re-usable design components across various domains. This work advances previous research on team design patterns and designing applications of HI systems.
MULTIFILE
We used a validated agent-based model—Socio-Emotional CONcern DynamicS (SECONDS)—to model real-time playful interaction between a child diagnosed with Autism Spectrum Disorders (ASD) and its parent. SECONDS provides a real-time (second-by-second) virtual environment that could be used for clinical trials and testingprocess-orientedexplanationsofASDsymptomatology.Weconductednumerical experiments with SECONDS (1) for internal model validation comparing two parental behavioral strategies for stimulating social development in ASD (play-centered vs. initiative-centered) and (2) for empirical case-based model validation. We compared 2,000 simulated play sessions of two particular dyads with (second-by-second) time-series observations within 29 play sessions of a real parent-child dyad with ASD on six variables related to maintaining and initiating play. Overall, both simuladistributions. Given the idiosyncratic behaviors expected in ASD, the observed correspondence is non-trivial. Our results demonstrate the applicability of SECONDS to parent-child dyads in ASD. In the future, SECONDS could help design interventions for parental care in ASDted dyads provided a better fit to the observed dyad than reference null
DOCUMENT
Background: Parents influence their children’s nutrition behavior. The relationship between parental influences and children’s nutrition behavior is often studied with a focus on the dyadic interaction between the parent and the child. However, parents and children are part of a broader system: the family. We investigated the relationship between the family nutrition climate (FNC), a family-level concept, and children’s nutrition behavior. Methods: Parents of primary school-aged children (N = 229) filled in the validated family nutrition climate (FNC) scale. This scale measures the families’ view on the consumption of healthy nutrition, consisting of four di erent concepts: value, communication, cohesion, and consensus. Parents also reported their children’s nutrition behavior (i.e., fruit, vegetable, water, candy, savory snack, and soda consumption). Multivariate linear regression analyses, correcting for potential confounders, were used to assess the relationship between the FNC scale (FNC-Total; model 1) and the di erent FNC subscales (model 2) and the child’s nutrition behavior. Results: FNC-Total was positively related to fruit and vegetable intake and negatively related to soda consumption. FNC-value was a significant predictor of vegetable (positive) and candy intake (negative), and FNC-communication was a significant predictor of soda consumption (negative). FNC-communication, FNC-cohesion, and FNC-consensus were significant predictors (positive, positive, and negative, respectively) of water consumption. Conclusions: The FNC is related to children’s nutrition behavior and especially to the consumption of healthy nutrition. These results imply the importance of taking the family-level influence into account when studying the influence of parents on children’s nutrition behavior. Trial registration: Dutch Trial Register NTR6716 (registration date 27 June 2017, retrospectively registered), METC163027, NL58554.068.16, Fonds NutsOhra project number 101.253.
DOCUMENT
