Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Giuseppe Prencipe has a total of 101 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Transforming Public Administration Workflows with Multi-Agent AI: A Human-in-the-Loop Knowledge Orchestration Framework

    by Giuseppe Prencipe, Alessandro Tommasi, Cesare Zavattari, Giovacchino Tesi, Lorenzo Storchi, Kussai Shahin

    Public administrations face increasing pressure to manage large volumes of institutional knowledge while ensuring transparency, accountability, and timely responses to citizen and council inquiries. This paper presents CARE (Council Agents for Response and Engagement), a human-in-the-loop multi-agent artificial intelligence system designed to support knowledge-intensive workflows within the Autonomous Province of Trento. CARE orchestrates specialized AI agents through a stateful workflow architecture, integrating hybrid retrieval-augmented generation over a corpus of more than 160,000 administrative documents. Unlike conventional automation approaches, the system models existing governance processes, preserves institutional responsibility boundaries, and ensures traceable document grounding in response generation. Deployed in production for six months and used by 30 administrative staff members, CARE achieved a 70\% reduction in response preparation time while maintaining human oversight and institutional control. The study contributes a socio-technical architecture for AI-assisted public administration, demonstrating how multi-agent orchestration, human-in-the-loop design, and hybrid knowledge retrieval can enhance institutional knowledge reuse without compromising accountability. Implications for digital transformation, AI governance, and responsible adoption of generative AI in the public sector are discussed.

  • Universal Dancing by Luminous Robots Under Sequential Schedulers

    by Caterina Feletti, Paola Flocchini, Debasish Pattanayak, Giuseppe Prencipe, Nicola Santoro

  • Open Access

    Efficient machine learning models leveraging DCE‑MRI morphological and dynamic features allow accurate breast lesion classification

    by Gianluca Morcaldi, Maria Evelina Fantacci, Claudio Gasperi, Chiara Iacconi, Elena Lorenzini, Emanuele Neri, Giuseppe Prencipe, Alessandra Retico, Camilla Scapicchio, Maria Irene Tenerani, et al.

    We propose an ensemble learning approach to classify malignant versus benign breast lesions leveraging morphological and dynamic features derived from Magnetic Resonance Images (MRI). The analysis has been performed on 164 breast lesions of the publicly available “Advanced MRI Breast Lesions” dataset from The Cancer Imaging Archive, containing T2-weighted and Dynamic Contrast-Enhanced (DCE)-MRI sequences, along with the segmentation masks of suspicious lesions. After extracting radiomic features using Pyradiomics Python package, we computed dynamic features from DCE-MRI kinetic curves, which describe the contrast agent wash-in and wash-out. These features have been defined as the derivatives of image intensity measures, like mean and standard deviation, computed inside the masks on the 5 DCE-MRI time steps. We trained and evaluated an eXtreme Gradient Boosting (XGBoost) classifier, experimenting with different combinations of features and segmentation masks in a stratified 5-fold cross-validation. The best model trained on T2-weighted MRI morphological features achieved an Area Under the Curve (AUC) score of 0.83±0.04 on the independent test set consisting of 20 lesions, while the model using only dynamic features performed an AUC of 0.91±0.03. Despite being obtained on a small test sample, these results show the potential of features derived from DCE images in breast lesions classification.


  • Open Access

    Transforming Public Administration Workflows with Multi-Agent AI: A Human-in-the-Loop Knowledge Orchestration Framework

    by Giuseppe Prencipe, Alessandro Tommasi, Cesare Zavattari, Giovacchino Tesi, Lorenzo Storchi, Kussai Shahin

    Public administrations face increasing pressure to manage large volumes of institutional knowledge while ensuring transparency, accountability, and timely responses to citizen and council inquiries. This paper presents CARE (Council Agents for Response and Engagement), a human-in-the-loop multi-agent artificial intelligence system designed to support knowledge-intensive workflows within the Autonomous Province of Trento. CARE orchestrates specialized AI agents through a stateful workflow architecture, integrating hybrid retrieval-augmented generation over a corpus of more than 160,000 administrative documents.Unlike conventional automation approaches, the system models existing governance processes, preserves institutional responsibility boundaries, and ensures traceable document grounding in response generation. Deployed in production for six months and used by 30 administrative staff members, CARE achieved a 70\% reduction in response preparation time while maintaining human oversight and institutional control.The study contributes a socio-technical architecture for AI-assisted public administration, demonstrating how multi-agent orchestration, human-in-the-loop design, and hybrid knowledge retrieval can enhance institutional knowledge reuse without compromising accountability. Implications for digital transformation, AI governance, and responsible adoption of generative AI in the public sector are discussed.

  • Open Access

    Machine Learning to Identify a New Digital Biomarker to Monitor Everyday Upper Limb Use in Children with Unilateral Cerebral Palsy

    by Silvia Filogna, Giuseppe Prencipe, Alina Sîrbu, Elena Beani, Davide Marchi, Giordano Scerra, Giuseppina Sgandurra

  • Open Access

    MIEO: encoding clinical data to enhance cardiovascular event prediction

    by Davide Borghini, Davide Marchi, Angelo Nardone, Giordano Scerra, Silvia Giulia Galfrè, Alessandro Pingitore, Giuseppe Prencipe, Corrado Priami, Alina Sîrbu

    As clinical data are becoming increasingly available, machine learning methods have been employed to extract knowledge from them and predict clinical events. While promising, approaches suffer from at least two main issues: low availability of labelled data and data heterogeneity leading to missing values. This work proposes the use of self-supervised auto-encoders to efficiently address these challenges. We apply our methodology to a clinical dataset from patients with ischaemic heart disease. Patient data is embedded in a latent space, built using unlabelled data, which is then used to train a neural network classifier to predict cardiovascular death. Results show improved balanced accuracy compared to applying the classifier directly to the raw data, demonstrating that this solution is promising, especially in conditions where availability of unlabelled data could increase.

  • Open Access

    A Holistic Approach Towards Evaluating Upper Limb Function in Children with Unilateral Cerebral Palsy: A Narrative Review of Clinical Tools and Promising Technologies for Comprehensive Assessment

    by Giovanna De Luca, Alexandra Kalkantzi, Lisa Mailleux, Rocío Palomo-Carrión, Hilde Feys, Roslyn N. Boyd, Elena Beani, Matteo Cianchetti, Silvia Filogna, Giuseppe Prencipe, et al.

    Optimal upper limb (UpL) function is essential for performing daily activities; however, children with unilateral spastic cerebral palsy (USCP) often experience impairments in UpL function, which can impact their quality of life or independence. While UpL motor impairments are a primary concern, non-motor functions, such as cognition, attention, and visual function, commonly impaired in USCP, may also play a role in UpL performance. Nevertheless, these non-motor functions are often not considered in evaluation protocols that focus on the UpL. Moreover, clinical evaluation is typically conducted in structured and controlled settings and may not accurately reflect the child’s abilities in daily life. Non-invasive, novel technologies are a promising solution for filling this gap, by providing additional quantitative and ecologically valid information to clinicians. In this context, this overview aims (i) to present the most frequently used tools for a holistic evaluation in children with USCP, ensuring a thorough understanding of the UpL function, and (ii) to report the evidence of how novel, non-invasive technologies can enhance clinical evaluation in daily life, enabling a more comprehensive evaluation. This work could set a basis for multidimensional evaluation protocols for UpL function in USCP, providing a different approach to the current standards.


  • Open Access

    Universal Dancing by Luminous Robots under Sequential Schedulers

    by Caterina Feletti, Paola Flocchini, Debasish Pattanayak, Giuseppe Prencipe, Nicola Santoro

    The Dancing problem requires a swarm of $n$ autonomous mobile robots to form a sequence of patterns, aka perform a choreography. Existing work has proven that some crucial restrictions on choreographies and initial configurations (e.g., on repetitions of patterns, periodicity, symmetries, contractions/expansions) must hold so that the Dancing problem can be solved under certain robot models. Here, we prove that these necessary constraints can be dropped by considering the LUMI model (i.e., where robots are endowed with a light whose color can be chosen from a constant-size palette) under the quite unexplored sequential scheduler. We formalize the class of Universal Dancing problems which require a swarm of $n$ robots starting from any initial configuration to perform a (periodic or finite) sequence of arbitrary patterns, only provided that each pattern consists of $n$ vertices (including multiplicities). However, we prove that, to be solvable under LUMI, the length of the feasible choreographies is bounded by the compositions of $n$ into the number of colors available to the robots. We provide an algorithm solving the Universal Dancing problem by exploiting the peculiar capability of sequential robots to implement a distributed counter mechanism. Even assuming non-rigid movements, our algorithm ensures spatial homogeneity of the performed choreography.

  • Open Access

    Line formation and scattering in silent programmable matter

    by Alfredo Navarra, Francesco Piselli, Giuseppe Prencipe