Publications by Michele Di Giovanni
Published:
2025
- DetailsDi Giovanni, M., Verde, L., Campanile, L., Romoli, M., Sabbarese, C., & Marrone, S. (2025). Assessing Safety and Sustainability of a Monitoring System for Nuclear Waste Management [Article]. IEEE Access, 13, 120486–120505. https://doi.org/10.1109/ACCESS.2025.3586735
Abstract
Nowadays, nuclear technologies are increasingly being integrated into industry, healthcare and manufacturing. As a side effect, waste materials are produced according to standard processes which are subject to international regulations. One of the most critical phases is the pre-disposal, due to the uncertainty related to the evolution of the materials and their potential impact on environmental protection. This paper introduces the architecture of a monitoring system able to accomplish safety goals and to guarantee energetic sustainability. The possibility of defining different system configurations (e. g., sensor scheduling policies, geometry of the sites, trustworthiness of the sensors) fosters a high adaptability to several monitoring scenarios, being characterised by different safety and sustainability levels. A methodology, integrating a model-based approach with data collection and processing, is proposed to quantitatively evaluate system configurations. This methodology is based on the definition of two metrics — one for safety and one for sustainability — and an assessment model. The model computes the metrics considering geometry of the place, scheduling and trustworthiness of monitoring sensors. This is a first step in the construction of a Decision Support System able to aid human operators in assessing system configurations and finding possible safety/sustainability trade-offs. A case study is used to show the feasibility of the approach: some configurations are evaluated on the real plant, placed at Řež in the Czech Republic, assessing them on the base of the defined metrics. © 2025 The Authors.
2024
- DetailsCampanile, L., De Fazio, R., Di Giovanni, M., & Marulli, F. (2024). Beyond the Hype: Toward a Concrete Adoption of the Fair and Responsible Use of AI [Conference paper]. CEUR Workshop Proceedings, 3762, 60–65. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205601768&partnerID=40&md5=99140624de79e37b370ed4cf816c24e7
Abstract
Artificial Intelligence (AI) is a fast-changing technology that is having a profound impact on our society, from education to industry. Its applications cover a wide range of areas, such as medicine, military, engineering and research. The emergence of AI and Generative AI have significant potential to transform society, but they also raise concerns about transparency, privacy, ownership, fair use, reliability, and ethical considerations. The Generative AI adds complexity to the existing problems of AI due to its ability to create machine-generated data that is barely distinguishable from human-generated data. Bringing to the forefront the issue of responsible and fair use of AI. The security, safety and privacy implications are enormous, and the risks associated with inappropriate use of these technologies are real. Although some governments, such as the European Union and the United States, have begun to address the problem with recommendations and proposed regulations, it is probably not enough. Regulatory compliance should be seen as a starting point in a continuous process of improving the ethical procedures and privacy risk assessment of AI systems. The need to have a baseline to manage the process of creating an AI system even from an ethics and privacy perspective becomes progressively more important In this study, we discuss the ethical implications of these advances and propose a conceptual framework for the responsible, fair, and safe use of AI. © 2024 Copyright for this paper by its authors.
2023
- DetailsCampanile, L., de Fazio, R., Di Giovanni, M., Marrone, S., Marulli, F., & Verde, L. (2023). Inferring Emotional Models from Human-Machine Speech Interactions [Conference paper]. Procedia Computer Science, 225, 1241–1250. https://doi.org/10.1016/j.procs.2023.10.112
Abstract
Human-Machine Interfaces (HMIs) are getting more and more important in a hyper-connected society. Traditional HMIs are built considering cognitive features while emotional ones are often neglected, bringing sometimes such interfaces to misuse. As a part of a long run research, oriented to the definition of an HMI engineering approach, this paper concretely proposes a method to build an emotional-aware explicit model of the user starting from the behaviour of the human with a virtual agent. The paper also proposes an instance of this model inference process in voice assistants in an automatic depression context, which can constitute the core phase to realize a Human Digital Twin of a patient. The case study generated a model composed of Fluid Stochastic Petri Net sub-models, achieved after the data analysis by a Support Vector Machine. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) - DetailsMarrone, S., Campanile, L., De Fazio, R., Di Giovanni, M., Gentile, U., Marulli, F., & Verde, L. (2023). A Petri net oriented approach for advanced building energy management systems [Article]. Journal of Ambient Intelligence and Smart Environments, 15(3), 211–233. https://doi.org/10.3233/AIS-230065
Abstract
Sustainability is one of the main goals to pursue in several aspects of everyday life; the recent energy shortage and the price raise worsen this problem, especially in the management of energy in buildings. As the Internet of Things (IoT) is an assessed computing paradigm able to capture meaningful data from the field and send them to cloud infrastructures, other approaches are also enabled, namely model-based approaches. These methods can be used to predict functional and non-functional properties of Building Energy Management Systems (BEMS) before setting up them. This paper aims at bridging the gap between model-based approaches and physical realizations of sensing and small computing devices. Through an integrated approach, able to exploit the power of different dialects of Petri Nets, this paper proposes a methodology for the early evaluation of BEMS properties as well as the automatic generation of IoT controllers. © 2023 - IOS Press. All rights reserved. - DetailsDi Giovanni, M., Campanile, L., D’Onofrio, A., Marrone, S., Marulli, F., Romoli, M., Sabbarese, C., & Verde, L. (2023). Supporting the Development of Digital Twins in Nuclear Waste Monitoring Systems [Conference paper]. Procedia Computer Science, 225, 3133–3142. https://doi.org/10.1016/j.procs.2023.10.307
Abstract
In a world whose attention to environmental and health problems is very high, the issue of properly managing nuclear waste is of a primary importance. Information and Communication Technologies have the due to support the definition of the next-generation plants for temporary storage of such wasting materials. This paper investigates on the adoption of one of the most cutting-edge techniques in computer science and engineering, i.e. Digital Twins, with the combination of other modern methods and technologies as Internet of Things, model-based and data-driven approaches. The result is the definition of a methodology able to support the construction of risk-aware facilities for storing nuclear waste. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) - DetailsConference Merging Model-Based and Data-Driven Approaches for Resilient Systems Digital Twins DesignCampanile, L., De Biase, M. S., De Fazio, R., Di Giovanni, M., Marulli, F., & Verde, L. (2023). Merging Model-Based and Data-Driven Approaches for Resilient Systems Digital Twins Design [Conference paper]. Proceedings of the 2023 IEEE International Conference on Cyber Security and Resilience, CSR 2023, 301–306. https://doi.org/10.1109/CSR57506.2023.10224945
Abstract
Nowadays, the problem of system robustness, es-pecially in critical infrastructures, is a challenging open question. Some systems provide crucial services continuously failing, threatening the availability of the provided services. By designing a robust architecture, this criticality could be overcome or limited, ensuring service continuity. The definition of a resilient system involves not only its architecture but also the methodology implemented for the calculation and analysis of some indices, quantifying system performance. This study provides an innovative architecture for Digital Twins implementation based on a hybrid methodology for improving the control system in realtime. The introduced approach brings together different techniques. In particular, the work combines the point of strengths of Model-based methods and Data-driven ones, aiming to improve system performances. © 2023 IEEE.