Search

The aerospace sector is one of the many sectors in which large amounts of data are generated. Thanks to the evolution of technology, these data can be exploited in several ways to improve the operation and management of industrial processes. However, to achieve this goal, it is necessary to define architectures and data models that allow to manage and homogenise the heterogeneous data collected. In this paper, we present an Airport Digital Twin Reference Conceptualisation's and data model based on FIWARE Generic Enablers and the Next Generation Service Interfaces-Linked Data standard. Concretely, we particularise the Airport Digital Twin to improve the efficiency of flight turnaround events. The architecture proposed is validated in the Aberdeen International Airport with the aim of reducing delays in commercial flights. The implementation includes an application that shows the real state of the airport, combining two-dimensional and three-dimensional virtual reality representations of the stands, and a mobile application that helps ground operators to schedule departure and arrival flights.

Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph similar to the original one, with a different outcome grounded on the underlying predictive model. Among these GCE techniques, those rooted in generative mechanisms have received relatively limited investigation despite demonstrating impressive accomplishments in other domains, such as artistic styles and natural language modelling. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates., Comment: Accepted in AAAI'24

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.

Machine Learning (ML) systems are a building part of the modern tools which impact our daily life in several application domains. Due to their black-box nature, those systems are hardly adopted in application domains (e.g. health, finance) where understanding the decision process is of paramount importance. Explanation methods were developed to explain how the ML model has taken a specific decision for a given case/instance. Graph Counterfactual Explanations (GCE) is one of the explanation techniques adopted in the Graph Learning domain. The existing works of Graph Counterfactual Explanations diverge mostly in the problem definition, application domain, test data, and evaluation metrics, and most existing works do not compare exhaustively against other counterfactual explanation techniques present in the literature. We present GRETEL, a unified framework to develop and test GCE methods in several settings. GRETEL is a highly extensible evaluation framework which promotes the Open Science and the evaluations reproducibility by providing a set of well-defined mechanisms to integrate and manage easily: both real and synthetic datasets, ML models, state-of-the-art explanation techniques, and evaluation measures. To present GRETEL, we show the experiments conducted to integrate and test several synthetic and real datasets with several existing explanation techniques and base ML models., Comment: 12 pages, 2 figures

We present a self-consistent prediction of the interstellar radiation field (ISRF), from the extreme ultraviolet (EUV) to sub-mm range, based on two chemical evolution models of a Milky Way-like galaxy (MWG). To this end, we develop a new tool called Mixclask to include gas emission, absorption and scattering from the photoionization code Cloudy into the Monte Carlo radiative transfer code Skirt. Both algorithms are invoked iteratively, until the physical properties of the ISM converge. We have designed a first test, reminiscent of a HII region, and we find that the results of Mixclask are in good agreement with a spherically symmetric Cloudy simulation. Both MWG models based on chemical evolution codes give results broadly consistent with previous empirical models reported in the literature for the ISRF of our Galaxy, albeit they systematically underestimate the mid-infrared emission. We also find significant differences between our two models in the whole ultraviolet range, not fully explored in previous ISRF models. These results show the feasibility of our method of combining radiative transfer with chemical evolution models: there is increased predictive power and the interstellar radiation field obtained provides further constraints on the model parameters. Python source code to implement our method is publicly available at https://github.com/MarioRomeroC/Mixclask., Comment: 16 pages, 7 figures, 3 tables. Accepted for publication in MNRAS

We carry out 1D hydrodynamical simulations of the evolution of a spherically symmetric supernova remnant (SNR) subject to an external radiation field (ERF) that influences the cooling and heating rates of the gas. We consider homogeneous media with ambient hydrogen number densities $n_{\rm H,0}$ of $0.1$ and $1$ cm$^{-3}$ permeated by an average radiation field including the cosmic microwave, extragalactic, and Galactic backgrounds, attenuated by an effective column density $N_{\rm H,eff}$ from $10^{18}$ to $10^{21}$~cm$^{-2}$. Our results may be classified into two broad categories: at low $N_{\rm H,eff}$, the ERF presents little absorption in the ultraviolet (ionising) regime, and all the 'unshielded' cases feature an equilibrium temperature $T_{eq} \sim 7000$~K below which the ambient gas cannot cool further. In this scenario, the SNR develops a nearly isothermal shock profile whose shell becomes thicker over time. At higher $N_{\rm H,eff}$, the ERF is heavily absorbed in the UV range, yielding a roughly constant heating function for temperatures $\lesssim 10^4$ K. These `shielded' cases develop a thin, cold and dense shell throughout their evolution. Energy and momentum injection to the medium do not change significantly between both scenarios, albeit luminosity is higher and more uniformly distributed over the shell for unshielded SNR., Comment: 12 pages, 5 figures, 2 tables. Accepted in MNRAS

Mobile money can facilitate financial inclusion in developing countries, which usually have high mobile phone use and steady remittance activity. Many countries in Latin America meet the minimum technological requirements to use mobile money, however, the adoption in this region is relatively low. This paper investigates the different factors that lead people in Latin America to distrust and therefore not adopt mobile money. For this purpose, we analyzed 27 mobile money applications on the market and investigated the perceptions that people in Latin America have of such interfaces. From our study, we singled out the interface features that have the greatest influence in user adoption in developing countries. We identified that for the Latin America market it is crucial to create mobile applications that allow the user to visualize and understand the workflow through which their money is traveling to recipients. We examined the significance of these findings in the design of future mobile money applications that can effectively improve the use of electronic financial transactions in Latin America., Comment: 8 pages, 5 figures, CLIHC'17

This work discusses the main analogies and differences between the deterministic approach underlying most cosmological N-body simulations and the probabilistic interpretation of the problem that is often considered in mathematics and statistical mechanics. In practice, we advocate for averaging over an ensemble of $S$ independent simulations with $N$ particles each in order to study the evolution of the one-point probability density $\Psi$ of finding a particle at a given location of phase space $(\mathbf{x},\mathbf{v})$ at time $t$. The proposed approach is extremely efficient from a computational point of view, with modest CPU and memory requirements, and it provides an alternative to traditional N-body simulations when the goal is to study the average properties of N-body systems, at the cost of abandoning the notion of well-defined trajectories for each individual particle. In one spatial dimension, our results, fully consistent with those previously reported in the literature for the standard deterministic formulation of the problem, highlight the differences between the evolution of the one-point probability density $\Psi(x,v,t)$ and the predictions of the collisionless Boltzmann (Vlasov-Poisson) equation, as well as the relatively subtle dependence on the actual finite number $N$ of particles in the system. We argue that understanding this dependence with $N$ may actually shed more light on the dynamics of real astrophysical systems than the limit $N\to\infty$., Comment: 15 pages, 6 figures. Accepted for publication in MNRAS