Despite the large diffusion and use of embedding generated through Word2Vec, there are still many open questions about the reasons for its results and about its real capabilities. In particular, to our knowledge, no author seems to have analysed in detail how learning may be affected by the various choices of hyperparameters. In this work, we try to shed some light on various issues focusing on a typical dataset. It is shown that the learning rate prevents the exact mapping of the co-occurrence matrix, that Word2Vec is unable to learn syntactic relationships, and that it does not suffer from the problem of overfitting. Furthermore, through the creation of an ad-hoc network, it is also shown how it is possible to improve Word2Vec directly on the analogies, obtaining very high accuracy without damaging the pre-existing embedding. This analogy-enhanced Word2Vec may be convenient in various NLP scenarios, but it is used here as an optimal starting point to evaluate the limits of Word2Vec.

Climate change is increasing the occurrence of the so-called heatwaves with a trend that is expected to worsen in the next years due to global warming. The growing intensity and duration of these extreme weather events are leading to a significant number of power system failures, especially in urban areas. This is drastically affecting the reliability and normal operation of power distribution grids around the world, with high financial costs and huge negative impacts on people's life. Typically, the response to these failure events is approached by post-event analysis, aimed at identifying the grid areas that require resources to increase the resilience of the system and prevent future outages. Nevertheless, understanding the nature of heatwaves and forecasting their impact on power distribution systems can be useful to anticipate them and accelerate a reaction, possibly avoiding negative impacts on power systems and customers. In this study, a structured method to predict distribution grid disruptions caused by heatwaves is defined. The proposed method relies on machine learning to analyze previous failure data and forecast power grid outages using operational and meteorological information. The method is evaluated using real failure data from a large power distribution network located in southern Italy.

Accurate predictions of photovoltaic generation are essential for effectively managing power system resources, particularly in the face of high variability in solar radiation. This is especially crucial in microgrids and grids, where the proper operation of generation, load, and storage resources is necessary to avoid grid imbalance conditions. Therefore, the availability of reliable prediction models is of utmost importance. Authors address this issue investigating the potential benefits of a machine learning approach in combination with photovoltaic power forecasts generated using weather models. Several machine learning methods have been tested for the combined approach (linear model, Long Short-Term Memory, eXtreme Gradient Boosting, and the Light Gradient Boosting Machine). Among them, the linear models were demonstrated to be the most effective with at least an RMSE improvement of 3.7% in photovoltaic production forecasting, with respect to two numerical weather prediction based baseline methods. The conducted analysis shows how machine learning models can be used to refine the prediction of an already established PV generation forecast model and highlights the efficacy of linear models, even in a low-data regime as in the case of recently established plants.

In radiation oncology, the need for a modern Normal Tissue Complication Probability (NTCP) philosophy to include voxel-based evidence on organ radio-sensitivity (RS) has been acknowledged. Here a new formalism (Probabilistic Atlas for Complication Estimation, PACE) to predict radiation-induced morbidity (RIM) is presented. The adopted strategy basically consists in keeping the structure of a classical, phenomenological NTCP model, such as the Lyman-Kutcher-Burman (LKB), and replacing the dose distribution with a collection of RIM odds, including also significant non-dosimetric covariates, as input of the model framework. The theory was first demonstrated in silico on synthetic dose maps, classified according to synthetic outcomes. PACE was then applied to a clinical dataset of thoracic cancer patients classified for lung fibrosis. LKB models were trained for comparison. Overall, the obtained learning curves showed that the PACE model outperformed the LKB and predicted synthetic outcomes with an accuracy >0.8. On the real patients, PACE performance, evaluated by both discrimination and calibration, was significantly higher than LKB. This trend was confirmed by cross-validation. Furthermore, the capability to infer the spatial pattern of underlying RS map for the analyzed RIM was successfully demonstrated, thus paving the way to new perspectives of NTCP models as learning tools.

The use of estimation techniques on stochastic models to solve control problems is an emerging paradigm that falls under the rubric of Active Inference (AI) and Control as Inference (CAI). In this work, we use probability propagation on factor graphs to show that various algorithms proposed in the literature can be seen as specific composition rules in a factor graph. We show how this unified approach, presented both in probability space and in log of the probability space, provides a very general framework that includes the Sum-product, the Max-product, Dynamic programming and mixed Reward/Entropy criteria-based algorithms. The framework also expands algorithmic design options that lead to new smoother or sharper policy distributions. We propose original recursions such as: a generalized Sum/Max-product algorithm, a Smooth Dynamic programming algorithm and a modified versions of the Reward/Entropy algorithm. The discussion is carried over with reference to a path planning problem where the recursions that arise from various cost functions, although they may appear similar in scope, bear noticeable differences. We provide a comprehensive table of composition rules and a comparison through simulations, first on a synthetic small grid with a single goal with obstacles, and then on a grid extrapolated from a real-world scene with multiple goals and a semantic map.

The combination of different energy vectors like electrical energy, hydrogen, methane, and water is a crucial aspect to deal with in integrated local energy communities (ILECs). The ILEC stands for a set of active energy users that maximise benefits and minimise costs using optimisation procedures in producing and sharing energy. In particular, the proper management of different energy vectors is fundamental for achieving the best operating conditions of ILECs in terms of both energy and economic perspectives. To this end, different solutions have been developed, including advanced control and monitoring systems, distributed energy resources, and storage. Energy management planning software plays a pivotal role in developing ILECs in terms of performance evaluation and optimisation within a multi-carrier concept. In this paper, the state-of-the-art of ILECs is further enhanced by providing important details on the critical aspects related to the overall value chain for constituting an ILEC (e.g., conceptualisation, connecting technologies, barriers/limitations, control, and monitoring systems, and modelling tools for planning phases). By providing a clear understanding of the technical solutions and energy planning software, this paper can support the energy system transition towards cleaner systems by identifying the most suitable solutions and fostering the advancement of ILECs.