Riccardo Crupi

Abstract The HERMES (High Energy Rapid Modular Ensemble of Satellites) Pathfinder mission aims to develop a constellation of nanosatellites to study astronomical transient sources, such as gamma-ray bursts, in the X and soft γ energy range, exploiting a novel inorganic scintillator. This study presents the results obtained describing, with an empirical model, the unusually intense and long-lasting residual emission of the GAGG: Ce scintillating crystal after irradiating it with high energy protons (70 MeV) and ultraviolet light (∼ 300 nm). From the model so derived, the consequences of this residual luminescence for the detector performance in operational conditions has been analysed. The suitability of this detector for the HERMES Pathfinder nanosatellites was demonstrated by the low contribution of the afterglow, 1–2 pA at peak, to the input current of the front-end electronics.

Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e., real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract – via supervised learning – an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same company (i.e., the same Entity).Given that the manual labelling of string pairs is a rather onerous task, we analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.The contributions of this work are: with empirical investigations on real-world industrial …

The detection of Gamma-Ray Bursts (GRBs) using spaceborne X/gamma-ray photon detectors depends on a reliable background count rate estimate. This study focuses on evaluating a data-driven background estimator based on a neural network designed to adapt to various X/gamma-ray space telescopes. Three trials were conducted to assess the effectiveness and limitations of the proposed estimator. Firstly, quantile regression was employed to obtain an estimation with a confidence range prediction. Secondly, we assessed the performance of the neural network, emphasizing that a dataset of four months is sufficient for training. We tested its adaptability across various temporal contexts, identified its limitations and recommended re-training for each specific period. Thirdly, utilizing Explainable Artificial Intelligence (XAI) techniques, we delved into the neural network output, determining distinctions between a network trained during solar maxima and one trained during solar minima. This entails conducting a thorough analysis of the neural network behavior under varying solar conditions.

We describe how a novel online change-point detection algorithm, called Poisson-FOCuS, can be used to optimally detect gamma-ray bursts within the computational constraints imposed by miniaturized satellites such as the upcoming HERMES-Pathfinder constellation. Poisson-FOCuS enables testing for gamma-ray burst onset at all intervals in a count time series, across all timescales and offsets, in real time and at a fraction of the computational cost of conventional strategies. We validate an implementation with automatic background assessment through exponential smoothing, using archival data from Fermi-GBM. Through simulations of lightcurves modeled after real short and long gamma-ray bursts, we demonstrate that the same implementation has higher detection power than algorithms designed to emulate the logic of Fermi-GBM and Compton-BATSE, reaching the performance of a brute-force benchmark …

This thesis comprises the first three chapters dedicated to providing an overview of Gamma Ray-Bursts (GRBs), their properties, the instrumentation used to detect them, and Artificial Intelligence (AI) applications in the context of GRBs, including a literature review and future prospects. Considering both the current and the next generation of high X-ray monitors, such as Fermi-GBM and HERMES Pathfinder (an in-orbit demonstration of six 3U nano-satellites), the research question revolves around the detection of long and faint high-energy transients, potentially GRBs, that might have been missed by previous detection algorithms. To address this, two chapters introduce a new data-driven framework, DeepGRB. In Chapter 4, a Neural Network (NN) is described for background count rate estimation for X/gamma-ray detectors, providing a performance evaluation in different periods, including both solar maxima, solar minima periods, and one containing an ultra-long GRB. The application of eXplainable Artificial Intelligence (XAI) is performed for global and local feature importance analysis to better understand the behavior of the NN. Chapter 5 employs FOCuS-Poisson for anomaly detection in count rate observations and estimation from the NN. DeepGRB demonstrates its capability to process Fermi-GBM data, confirming cataloged events and identifying new ones, providing further analysis with estimates for localization, duration, and classification. The chapter concludes with an automated classification method using Machine Learning techniques that incorporates XAI for eventual bias identification.

In the era of rapid growth and transformation driven by artificial intelligence across various sectors, which is catalyzing the fourth industrial revolution, this research is directed toward harnessing its potential to enhance the efficiency of decision-making processes within organizations. When constructing machine learning-based decision models, a fundamental step involves the conversion of domain knowledge into causal-effect relationships that are represented in causal graphs. This process is also notably advantageous for constructing explanation models. We present a method for generating causal graphs that integrates the strengths of Large Language Models (LLMs) with traditional causal theory algorithms. Our method seeks to bridge the gap between AI’s theoretical potential and practical applications. In contrast to recent related works that seek to exclude the involvement of domain experts, our method places them at the forefront of the process. We present a novel pipeline that streamlines and enhances domain-expert validation by providing robust causal graph proposals. These proposals are enriched with transparent reports that blend foundational causal theory reasoning with explanations from LLMs.

Explaining outliers occurrence and mechanism of their occurrence can be extremely important in a variety of domains. Malfunctions, frauds, threats, in addition to being correctly identified, oftentimes need a valid explanation in order to effectively perform actionable counteracts. The ever more widespread use of sophisticated Machine Learning approach to identify anomalies make such explanations more challenging. We present the Decision Tree Outlier Regressor (DTOR), a technique for producing rule-based explanations for individual data points by estimating anomaly scores generated by an anomaly detection model. This is accomplished by first applying a Decision Tree Regressor, which computes the estimation score, and then extracting the relative path associated with the data point score. Our results demonstrate the robustness of DTOR even in datasets with a large number of features. Additionally, in contrast to other rule-based approaches, the generated rules are consistently satisfied by the points to be explained. Furthermore, our evaluation metrics indicate comparable performance to Anchors in outlier explanation tasks, with reduced execution time.

Ranking is required for many real applications, such as search, personalisation, recommendation, and filtering. Recent research has focused on developing reliable ranking algorithms that maintain fairness in their outcomes. However, only a few consider multiple protected groups since this extension introduces significant challenges. While useful in the research sector, considering only one binary sensitive feature for handling fairness is inappropriate when the algorithm must be deployed responsibly in real-world applications.Our work is built on top of Multinomial FA*IR, a Fair Top-k ranking with multiple protected groups, which we extend to provide users the option to balance fairness and utility, adapting the final ranking accordingly. Our experimental results show that alternative better solutions overlooked by Multinomial FA*IR may be found through our approach without violating fairness boundaries. The code …

The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This paper advocates for the application of a specific form of Explainable AI -- namely, contrastive explanations -- as particularly well-suited for addressing ranking problems. This approach is especially potent when combined with an Evaluative AI methodology, which conscientiously evaluates both positive and negative aspects influencing a potential ranking. Therefore, the present work introduces Evaluative Item-Contrastive Explanations tailored for ranking systems and illustrates its application and characteristics through an experiment conducted on publicly available data.

HERMES Pathfinder is an in-orbit demonstration consisting of a constellation of six 3U nano-satellites hosting simple but innovative detectors for the monitoring of cosmic high-energy transients. The main objective of HERMES Pathfinder is to prove that accurate position of high-energy cosmic transients can be obtained using miniaturized hardware. The transient position is obtained by studying the delay time of arrival of the signal to different detectors hosted by nano-satellites on low-Earth orbits. In this context, we need to develop novel tools to fully exploit the future scientific data output of HERMES Pathfinder. In this paper, we introduce a new framework to assess the background count rate of a spaceborne, high energy detector; a key step towards the identification of faint astrophysical transients. We employ a neural network to estimate the background lightcurves on different timescales. Subsequently, we employ …

In this research, we propose a novel approach for the quantification of credit portfolio Value-at-Risk (VaR) sensitivity to asset correlations with the use of synthetic financial correlation matrices generated with deep learning models. In previous work Generative Adversarial Networks (GANs) were employed to demonstrate the generation of plausible correlation matrices, that capture the essential characteristics observed in empirical correlation matrices estimated on asset returns. Instead of GANs, we employ Variational Autoencoders (VAE) to achieve a more interpretable latent space representation. Through our analysis, we reveal that the VAE latent space can be a useful tool to capture the crucial factors impacting portfolio diversification, particularly in relation to credit portfolio sensitivity to asset correlations changes.

Nowadays, Machine Learning (ML) systems are widely used in various businesses and are increasingly being adopted to make decisions that can significantly impact people’s lives. However, these decision-making systems rely on data-driven learning, which poses a risk of propagating the bias embedded in the data. Despite various attempts by the algorithmic fairness community to outline different types of bias in data and algorithms, there is still a limited understanding of how these biases relate to the fairness of ML-based decision-making systems. In addition, efforts to mitigate bias and unfairness are often agnostic to the specific type(s) of bias present in the data. This paper explores the nature of fundamental types of bias, discussing their relationship to moral and technical frameworks. To prevent harmful consequences, it is essential to comprehend how and where bias is introduced throughout the entire …

Explainable Artificial Intelligence (XAI) is a set of techniques that allows the understanding of both technical and non-technical aspects of Artificial Intelligence (AI) systems. XAI is crucial to help satisfying the increasingly important demand of trustworthy Artificial Intelligence, characterized by fundamental aspects such as respect of human autonomy, prevention of harm, transparency, accountability, etc. Within XAI techniques, counterfactual explanations aim to provide to end users a set of features (and their corresponding values) that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations, and in particular, they fall short of considering the causal impact of such actions. In this paper, we present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate …

In recent years, the problem of addressing fairness in machine learning (ML) and automatic decision making has attracted a lot of attention in the scientific communities dealing with artificial intelligence. A plethora of different definitions of fairness in ML have been proposed, that consider different notions of what is a “fair decision” in situations impacting individuals in the population. The precise differences, implications and “orthogonality” between these notions have not yet been fully analyzed in the literature. In this work, we try to make some order out of this zoo of definitions.

Algorithmic bias mitigation has been one of the most difficult conundrums for the data science community and Machine Learning (ML) experts. Over several years, there have appeared enormous efforts in the field of fairness in ML. Despite the progress toward identifying biases and designing fair algorithms, translating them into the industry remains a major challenge. In this paper, we present the initial results of an industrial open innovation project in the banking sector: we propose a general roadmap for fairness in ML and the implementation of a toolkit called BeFair that helps to identify and mitigate bias. Results show that training a model without explicit constraints may lead to bias exacerbation in the predictions.