Abstract: We reconstruct the extra-galactic gamma-ray source-count distribution, or dN/dS, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the FermiLAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the (1, 10) GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from cataloged sources, and then extends as dN/dS " S-2 in the unresolved regime, down to fluxes of 5 center dot 10-12 cm-2 s-1. The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

Abstract: Nuclear energy production is inherently tied to the management and disposal of radioactive waste. Enhancing classification and monitoring tools is therefore crucial, with significant socioeconomic implications. This paper reports on the applicability and performance of a high-efficiency, cost-effective and portable Compton camera for detecting and visualizing low-and medium-level radioactive waste from the decommissioning and regular operation of nuclear power plants. The results demonstrate the good performance of Compton imaging for this type of application, both in terms of image resolution and reduced measuring time. A technical readiness level of TRL7 has been thus achieved with this system prototype, as demonstrated with dedicated field measurements carried out at the radioactive-waste disposal plant of El Cabril (Spain) utilizing a pluarility of radioactive-waste drums from decomissioned nuclear power plants. The performance of the system has been enhanced by means of computer-vision techniques in combination with advanced Compton-image reconstruction algorithms based on Maximum-Likelihood Expectation Maximization. Finally, we also show the feasibility of 3D tomographic reconstruction from a series of relatively short measurements around the objects of interest. The potential of this imaging system to enhance nuclear waste management makes it a promising innovation for the nuclear industry.

Abstract: Palliative care is referred to a set of programs for patients that suffer life-limiting illnesses. These programs aim to maximize the quality of life (QoL) for the last stage of life. They are currently based on clinical evaluation of the risk of 1-year mortality. The main aim of this work is to develop and validate machine-learning-based models to predict the exitus of a patient within the next year using data gathered at hospital admission. Five machine-learning techniques were applied using a retrospective dataset. The evaluation was performed with five metrics computed by a resampling strategy: Accuracy, the area under the ROC curve, Specificity, Sensitivity, and the Balanced Error Rate. All models reported an AUC ROC from 0.857 to 0.91. Specifically, Gradient Boosting Classifier was the best model, producing an AUC ROC of 0.91, a sensitivity of 0.858, a specificity of 0.808, and a BER of 0.1687. Information from standard procedures at hospital admission combined with machine learning techniques produced models with competitive discriminative power. Our models reach the best results reported in the state of the art. These results demonstrate that they can be used as an accurate data-driven palliative care criteria inclusion.