The transition from fetal to extra-uterine life is characterized by a series of respiratory, cardiovascular and metabolic adaptation mechanisms. Approximately 90% of newborns breathe spontaneously without the need for interventions, the remaining 10% will need assistance at birth. Among the latter, most will start breathing after the first assistance maneuvers (drying, tactile stimulation, alignment of the airways); 5% thanks to the application of positive pressure ventilation (PPV). Estimates of intubation rates vary between 0.4% and 2%; less than 0.3% will require chest compression and approximately 0.05% will need medication [1, 4, 5, 15, 16]. Neonatal mortality in Italy, for babies born after the 22nd week of gestational age, is estimated as 1.7 deaths per 1000 births, compared to an average 2.1/1000 in Europe [11]. The inability of some infants to establish and sustain spontaneous or adequate breathing, contributes significantly to these early deaths and also to the burden of adverse neurological outcomes among survivors.

This document describes the rationale, the implementation and a preliminary evaluation of a semantic reasoning tool developed in the EU H2020 SPICE project to enhance the diversity of perspectives experienced by museum visitors. The tool, called DEGARI 2.0 for values, relies on the commonsense reasoning framework TCL, and exploits an ontological model formalizingthe Haidt's theory of moral values to associate museum items with combined values and emotions. Within a museum exhibition, this tool can suggest cultural items that are associated not only with the values of already experienced or preferred objects, but also with novel items with different value stances, opening the visit experience to more inclusive interpretations of cultural content. The system has been preliminarily tested, in the context of the SPICE project, on the collection of the Hecht Museum of Haifa.

Case-based retrieval and K-NN classification techniques are suitable for assessing hemodialysis treatment efficiency and for identifying risk situations. In this domain, cases involve time series data, that need to undergo a feature extraction phase in order to reduce dimensionality and to speed up similarity calculation. In this paper, we propose a deep learning architecture for time series feature extraction, based on the use of a convolutional autoencoder. Deep features provide a better time series representation with respect to features produced by the Discrete Cosine Transform (DCT). Indeed, in our experiments, K-NN classification based on deep features has outperformed the DCT-based one. We are also working in the direction of improving interpretability, by using case retrieval results obtained in a different feature space (defined on the basis of domain knowledge) to explain the outputs provided by the adoption of the deep learning technique.