Archivio della ricerca - Fondazione Bruno Kessler
Not a member yet
21227 research outputs found
Sort by
Framing the Human-Centered Artificial Intelligence Concepts and Methods: Scoping Review
No full textABSTRACT Background: With the rapid expansion of Artificial Intelligence (AI) applications, researchers have begun focusing on the concept of Human-Centered Artificial Intelligence (HCAI). This field is dedicated to designing AI systems that augment and improve human abilities, rather than substituting them. Objective: The objective of the paper is to review the information on design principles, techniques, applications, methods and outcomes adopted in the field of HCAI, in order to provide some insights on the discipline, in relation with the broader concepts of Human-Centered Design and User-centered design. Methods: Following the PRISMA Checklist Extension guidelines, we conducted a systematic review in PubMed, Sciencedirect and IEEE Xplore, including all study types, excluding scoping review and editorials. Results: Out of the 1035 studies retrieved, 14 studies conducted between 2018 and 2023 met the inclusion criteria. The main fields of application were the health sector and artificial intelligence applications. Human-centred design methodologies were adopted in 3 studies, personas in 2 studies, while the remaining methodologies were adopted in individual studies. Conclusions: Human-Centered Artificial Intelligence (HCAI) emphasizes designing AI systems that prioritize human needs, satisfaction, and trustworthiness, but current principles and guidelines are often vague and difficult to implement. The review highlights the importance of involving users early in the development process to enhance trust, especially in fields like healthcare, but notes that there is a lack of standardized HCAI methodologies and limited practical applications adhering to these principles. Clinical Trial: N/
Le frontiere della speranza. Fragilità e resilienza della democrazia
No full textIl volume raccoglie tre saggi che ruotano attorno al nesso tra democrazia e speranza. Stiamo vivendo oggi una fase di crescente sfiducia nella democrazia. Questa sfiducia è motivata dalla sensazione che le democrazie contemporanee stiano degenerando: stiano cioè tradendo l’aspettativa suscitata dall’idea che gli esseri umani possano autogovernarsi, mettendo il potere al servizio di tutti e non solo di pochi. Quanto è fragile questo sogno di un progresso universale? Quanto è resiliente? Gli autori dei contributi ospitati nel libro discutono la questione da tre punti di vista diversi e complementari: la storia recente delle democrazie occidentali, l’esigenza di andare oltre le forme politiche esistenti per rianimare la fede nell'ideale dell'autogoverno democratico, le prospettive di una democrazia "sorgiva" e “risonante”. I saggi sono introdotti da una breve premessa del curatore del volume
Back-side Illuminated SiPM for VUV/NUV light detection at Fondazione Bruno Kessler: first results
No full textAdvancements in 3D interconnecting technologies have significantly contributed to the emergence of a new generation of Silicon Photomultipliers (SiPM), which we can refer to as hybrid devices. These devices integrate the functionalities of digital SiPMs with the exceptional performance characteristics of specialized custom technologies. In recent years, the Fondazione Bruno Kessler (FBK) has been working on the technological development of Backside Illuminated (BSI) SiPMs for Vacuum Ultraviolet (VUV) and Near Ultraviolet (NUV) light detection, particularly in applications in particle physics experiments, such as detection of scintillation from liquefied noble gases.
For this wavelength range, a BSI detection technology faces critical challenges due to silicon's low photon interaction depth (less than 100 nm for λ = 400 nm). This necessitates the complete removal of the substrate, a process that has already been successfully demonstrated at FBK and the creation of a thin active “entrance window”. Additionally, for VUV-sensitive devices, the glass carrier wafer must be removed from the entrance window, as it typically absorbs light for wavelengths shorter than 350 nm. We will present the latest progress in the microfabrication technology of BSI-SiPMs and the results from the first batch, produced in the framework of the INFN IBIS project
Latent Distillation for Continual Object Detection at the Edge
No full textWhile numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to new data while maintaining performance on previous data. This is particularly pertinent for edge devices, common in dynamic environments like automotive and robotics. In this work, we address the memory and computation constraints of edge devices in the Continual Learning for Object Detection (CLOD) scenario. Specifically, (i) we investigate the suitability of an open-source, lightweight, and fast detector, namely NanoDet, for CLOD on edge devices, improving upon larger architectures used in the literature. Moreover, (ii) we propose a novel CL method, called Latent Distillation~(LD), that reduces the number of operations and the memory required by state-of-the-art CL approaches without significantly compromising detection performance. Our approach is validated using the well-known VOC and COCO benchmarks, reducing the distillation parameter overhead by 74\% and the Floating Points Operations~(FLOPs) by 56\% per model update compared to other distillation methods
Conjugated Polymer Nanoparticles for Biophotonic Applications: Preparation, Characterization, and Simulation in Biohybrid Interfaces
No full textBiophotonics has gained significant interest in recent years due to its potential in medical theranostic applications, with nano-materials emerging as key enablers for advancing optical and electronic functionalities in biological environments. In this study, conjugated polymer nanoparticles (CP-NPs), namely regio-regular poly(3-hexylthiophene) (P3HT), [6,6]-phenyl C61-butyric acid methyl ester (PCBM), and their blend (P3HT:PCBM), are exploited as nano-materials for biophotonic applications. The CP-NPs, obtained via a nanoprecipitation method, showed an average size of ca. 180 nm. Their optoelectrical properties indicate visible absorbance (350–600 nm) and red/near infra-red (NIR, 650–900 nm) emission, demonstrating their suitability for biophotonic applications, in particular in biohybrid interfaces where effective light absorption and emission in biological environments are crucial. Interestingly, under light stimulation, the photocurrent response of the CP-NPs in electrolyte solution (phosphate-buffered saline, PBS) showed a stable and reproducible signal (current density ranging from 0.18 to 7 nA cm−2) thereby enhancing their potential for bio-sensing/stimulation. Simulations of CP-NPs interactions with biological fluids (i.e., PBS) under light stimulation showed distinct carrier generation and transport behaviors, with P3HT-NPs exhibiting consistent charge generation (up to 3 × 1020 nA cm−3). These findings demonstrate that CP-NPs are promising for biophotonic applications, such as photothermal therapy, due to their efficient charge transport, UV-vis absorption, NIR emission, and controlled interactions with biological environments
Mopidip: a modular real-time pipeline for machinery diagnosis and prognosis based on deep learning algorithms
No full textCondition monitoring is a crucial process for ensuring industrial assets’ reliability and operational efficiency. In the age of the digital industry, Artificial Intelligence (AI)-based data-driven condition monitoring is proving extremely effective in detecting potential issues before they escalate into major problems, thereby reducing downtime, minimizing maintenance costs, and extending the lifespan of the equipment. The availability of tools that can enable the operationalization of these data-driven solutions is, therefore, critical. In this direction, this work proposes a comprehensive, modular, and scalable pipeline covering all the steps from the data acquisition to the AI model training and inference phases. The tool integrates the data acquisition and processing steps with a configurable feature extraction phase. Moreover, the system also integrates deep learning algorithms for diagnosis and prognosis, including a domain adaptation stage to permit transfer learning and increase generalizability. In addition, it features a communication system which allows for an online data stream to enable real-time monitoring and maintenance. The overall infrastructure was deployed in actual industrial settings and tested in a real-time experiment, demonstrating the proposed approach’s validity
La corte: spazio urbano e spazio politico
No full textl contributo offre un'analisi sulla corte italiana del Rinascimento come spazio fisico e politico, andando a privilegiare le testimonianze di cultura materiale e le modalità con cui il potere cortigiano si è espresso nello spazio pubblico
Fabrication and Characterization of SiOC(N) Cellular Structures via 3D-Printed Polyurethane Templates Impregnated with Polysilazane
No full textSilicon-based Polymer Derived Ceramics (PDCs) represent a unique class of materials synthesized at relatively low temperatures compared to conventional ceramics. Using the replica method, PDCs can be integrated with Additive Manufacturing (AM) via fused filament fabrication (FFF). However, the effect of printing parameters on PDCs’ structure, chemistry, and properties remains unclear.
We investigate the fabrication of PDC scaffolds using thermoplastic polyurethane and different nozzle sizes, varying wall thickness. The resulting SiOC(N) structure is characterized using complementary techniques: X-ray diffraction, scanning electron microscopy, and secondary ion mass spectroscopy. Mechanical properties are assessed by measuring Vickers hardness and flexural strength. A potential application of the SiOC(N) cellular structures as scaffolds for bone regeneration is evaluated by studying cell adhesion and metabolic activity. This work highlights how wall thickness impacts the impregnation and pyrolysis processes and affects properties such as hardness and biological behavior, including cell adhesion and metabolic activity
Geometric Calibration of Thermal Infrared Cameras: A Comparative Analysis for Photogrammetric Data Fusion
No full textThe determination of precise and reliable interior (IO) and relative (RO) orientation parameters for thermal infrared (TIR) cameras is critical for their subsequent use in photogrammetric processes. Although 2D calibration boards have become the predominant approach for TIR geometric calibration, these targets are susceptible to projective coupling and often introduce error through manual construction methods, necessitating the development of 3D targets tailored to TIR geometric calibration. Therefore, this paper evaluates TIR geometric calibration results obtained from 2D board and 3D field calibration approaches, documenting the construction, observation, and calculation of IO and RO parameters. This includes a comparative analysis of values derived from three popular commercial software packages commonly used for geometric calibration: MathWorks’ MATLAB, Agisoft Metashape, and Photometrix’s Australis. Furthermore, to assess the validity of derived parameters, two InfraRed Thermography 3D-Data Fusion (IRT-3DDF) methods are developed to model historic building façades and medieval frescoes. The results demonstrate the success of the proposed 3D field calibration targets for the calculation of both IO and RO parameters tailored to photogrammetric data fusion. Additionally, a novel combined TIR-RGB bundle block adjustment approach demonstrates the success of applying ‘out-of-the-box’ deep-learning neural networks for multi-modal image matching and thermal modelling. Considerations for the development of TIR geometric calibration approaches and the evolution of proposed IRT-3DDF methods are provided for future work