This paper presents an approach on how to adapt playgrounds using artificial neural networks (ANN). The playground consists of small tiles each capable of outputting coloured light, sensing force applied on them and communicating with neighbouring tiles. It is shown that a child's behaviour on the playground can be classified within eight categories by an ANN inputting the child's perception of the playground and the corresponding action performed; thus, enabling the playground to adapt real-time according to the classification.The playground has been developed, implemented and tested on a group of children. An ANN was trained using a subgroup of the children whose behaviour corresponds to the eight categories. Validating the ANN against the rest of the children's behaviours it was found that 96% were correctly classified. The trained ANN has been utilized in adapting the playground according to several playing strategies and validated by means of a statistical analysis of physiological signals (e.g. the heart rates of the children).

We used inspiration from modular robotics to create novel tools for dementia treatment based on activity analyses together with therapists and elderly in an Italian home care. This paper presents the technological development of such tools. In general, the tools are becoming part of a "multi-sensory room", i.e. a space augmented by innovative technologies, that can be configured for different therapeutic activities and needs and that leverages sensory stimulation. The development of the tools is inspired by modular robotics in order to allow for space re-configurability and adaptivity, which should support customized therapeutic interventions, and hopefully involve dementia affected users in the interaction with the solution

No abstract