Giovanna Castellano

Verified

Giovanna verified their affiliation via an institutional email.

Learn more

Verified

Giovanna verified their affiliation via an institutional email.

Learn more

• Associate Professor, PhD
• Professor (Associate) at University of Bari Aldo Moro

https://sites.google.com/view/explimed-2025/home-page **** IMPORTANT DATES **** Abstract submission deadline: May 10, 2025 Paper submission deadline: May 21, 2025 Notification of acceptance: July 21 2025 Final paper submission: September 12, 2025 Early registration deadline: TBA Workshop date: 25-26 October, 2025

With this Special Issue, we aim to advance research on Human-Centered Explainable AI (HC-XAI) as a crucial interdisciplinary approach to enhancing the transparency, effectiveness, and user alignment of AI explanations. By bridging the gap between technical XAI solutions and human cognitive needs, HC-XAI can foster greater trust, ensure regulatory c...

This special session aims to create an international forum specifically focusing on eXplainable Artificial Intelligence methods in healthcare. In recent years, Artificial Intelligence algorithms have become integral to our daily lives and applied in diverse contexts, including healthcare, economics, and law. The adoption of these systems conceals s...

Inpainting focuses on filling missing or corrupted regions of an image to blend seamlessly with its surrounding content and style. While conditional diffusion models have proven effective for text-guided inpainting, we introduce the novel task of multi-mask inpainting, where multiple regions are simultaneously inpainted using distinct prompts. Furt...

Contactless methods are widely used to measure vital signs from recorded or live videos using remote photoplethysmography (rPPG), which takes advantage of the slight skin color variation that occurs periodically on specific body regions with each blood pulse. However, existing rPPG-based solutions are typically expensive and not suitable for daily...

This research introduces a novel dataset developed for streaming learning analytics, derived from the Open University Learning Analytics Dataset (OULAD). The dataset incorporates essential temporal information that captures the timing of student interactions with the Virtual Learning Environment (VLE). By integrating these time-based interactions,...

The 2024 First Workshop on Explainable Artificial Intelligence for the Medical Domain (EXPLIMED) marks its inaugural edition in conjunction with the 27th European Conference on Artificial Intelligence (ECAI 2024) in Santiago de Compostela. This workshop brought together experts in Artificial Intelligence to deepen the latest innovations and best pr...

The proliferation of AI-generated media, especially in art, has sparked interest in creating models that differentiate between original and AI-generated artworks. However, understanding why these models make certain decisions remains a significant challenge. This paper enhances the explainability of Vision Transformer-based classification models by...

In the rapidly evolving field of human-computer interaction, the need for inclusive and accessible communication methods has become increasingly vital. This paper introduces an early exploration of Text-to-LIS, a new model designed to generate contextually accurate Italian Sign Language (LIS) gestures for digital humans. Our approach addresses the...

Survey questionnaires capture employee insights and guide strategic decision-making in Human Capital Management. This study explores the application of the GPT-3.5-Turbo and GPT-4-Turbo models for the automated generation of HR-related questionnaires, addressing a significant gap in the literature. We developed a novel dataset of HR survey question...

We present GraphCLIP, a novel contrastive learning framework for multimodal artwork classification that integrates visual and contextual information to improve predictive accuracy and interpretability. Traditional computer vision methods often fall short in visual arts, where context is crucial. GraphCLIP leverages image data and a Knowledge Graph...

Inpainting focuses on filling missing or corrupted regions of an image to blend seamlessly with its surrounding content and style. While conditional diffusion models have proven effective for text-guided inpainting, we introduce the novel task of multi-mask inpainting, where multiple regions are simultaneously inpainted using distinct prompts. Furt...

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm and forearm torques remains challenging. We present two approaches for estimating angular velocities, a...

Hypertension is a disease that stresses the arteries and can cause damage to vital organs. It is often asymptomatic, and timely diagnosis and management are crucial to prevent complications and mitigate the risks associated with the disease. Photoplethysmography has proven to be effective in capturing variations in blood volume within vessels and h...

We propose a novel methodology that combines Graph Neural Networks (GNNs) with Fuzzy Logic to enhance the interpretability of deep learning models. GNNs handle structured data, while Fuzzy Logic provides a framework that excels in handling uncertainty and imprecision. To solve the challenge of interpretability in GNNs, we present a novel approach t...

In this paper, we introduce PROPHET, an innovative approach to predictive process monitoring based on Heterogeneous Graph Neural Networks. PROPHET is designed to strike a balance between accurate predictions and interpretability, particularly focusing on the next-activity prediction task. For this purpose, we represent the event traces recorded for...

We apply an evolving granular-computing modeling approach, called evolving Optimal Granular System (eOGS), to bipolar mood disorder (BD) diagnosis based on speech data streams. The eOGS online learning algorithm reveals information granules in the flow and design the structure and parameters of a granular rule-based model with a certain degree of i...

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm and forearm torques remains challenging. We present two approaches for estimating angular velocities, a...

The goal of this workshop is to explore and exhibit research, methodologies, and case studies that focus on the integration of Explainable Artificial Intelligence (XAI) in the medical domain. It will provide a platform for researchers, practitioners, and policymakers to share their insights and advancements in XAI. The purpose is to improve transpa...

Precision agriculture relies heavily on effective weed management to ensure robust crop yields. This study presents RoWeeder, an innovative framework for unsupervised weed mapping that combines crop-row detection with a noise-resilient deep learning model. By leveraging crop-row information to create a pseudo-ground truth, our method trains a light...

Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\mathcal{A}\textit{rt...

Artificial Intelligence (AI) has significantly advanced medical imaging, yet the opacity of deep learning models remains challenging, often reducing the trust of medical professionals towards AI-driven diagnoses. This paper introduces a novel approach to enhance AI explainability in critical medical tasks by integrating state-of-the-art semantic se...

Recent advancements in large language models (LLMs) have enabled more autonomous conversational AI agents. However, challenges remain in developing effective chatbots, particularly in addressing LLMs' lack of "statefulness". This paper presents Converso, a novel chatbot framework that introduces a new conversation flow based on stateful conversatio...

This contribution briefly describes the research being carried out in the in AI-based e-health. Our research encompasses a wide array of methodologies and applications aimed at leveraging the capability of AI to empower the diagnosis, monitoring, and treatment of various health conditions. Through multifaceted research that covers neuroimaging anal...

Artificial Intelligence (AI) has become an integral part of our lives, and Explainable Artificial Intelligence (XAI) is becoming more essential to ensure trustworthiness and comply with regulations. XAI methodologies help to explain the automatic processing behind data analysis. This paper provides an overview of the use of XAI in the educational d...

We present Label Anything, an innovative neural network architecture designed for few-shot semantic segmentation (FSS) that demonstrates remarkable generalizability across multiple classes with minimal examples required per class. Diverging from traditional FSS methods that predominantly rely on masks for annotating support images, Label Anything i...

Accurate brain tumor segmentation is crucial for precise medical diagnosis and treatment planning in medical imaging. This research delves into assessing the effectiveness and transparency of Graph Neural Networks (GNNs) in brain tumor segmentation. The primary objectives include comparing various GNN architectures and improving their understandabi...

Understanding and classifying artworks represent a fundamental challenge in art analysis, requiring a fine interpretation of complex visual and thematic elements. Notably, this task has been tackled using deep neural networks, including both vision-based methods and hybrid ones. Although these approaches have proved effective in recognizing differe...

This study focuses on how artificial intelligence (AI) can be used in education while emphasizing the importance of adhering to European regulations requiring explanations of automatic methods. The study uses a prototype-based dynamic incremental classification algorithm called Dynamic Incremental Semi-Supervised Fuzzy C-Means-DISSFCM, based on Fuz...

Recent advances in deep learning and imaging technologies have revolutionized automated medical image analysis, especially in diagnosing Alzheimer’s disease through neuroimaging. Despite the availability of various imaging modalities for the same patient, the development of multi-modal models leveraging these modalities remains underexplored. This...

While AI techniques have enabled automated analysis and interpretation of visual content, generating meaningful captions for artworks presents unique challenges. These include understanding artistic intent, historical context, and complex visual elements. Despite recent developments in multi-modal techniques, there are still gaps in generating comp...

This special session aims to explore and discuss various explainable AI methods that enhance the transparency and interpretability of machine learning models, ensuring trust and usability in healthcare applications.

We propose a method to perform regression on partially labeled data, which is based on SSFCM (Semi-Supervised Fuzzy C-Means), an algorithm for semi-supervised classification based on fuzzy clustering. The proposed method, called SSFCM-R, precedes the application of SSFCM with a relabeling module based on target discretization. After the application...

In this paper, we propose a novel predictive process monitoring approach, named JARVIS, that is designed to achieve a balance between accuracy and explainability in the task of next-activity prediction. To this aim, JARVIS represents different process executions (traces) as patches of an image and uses this patch-based representation within a multi...

Recognizing attributes of unknown artworks relies on more than visual information: prior knowledge and emotional context can play a crucial role. Building an AI system mimicking this perception requires a multi-modal model integrating computer vision and contextual factors. In this paper, we propose a new model that uses vision transformers and gra...

Generative AI, mainly through Diffusion Models, has revolutionized art creation, blurring the distinction between human and AI-generated art. This study introduces a novel dataset comprising human-made and AI-generated art and employs Deep Learning models (VGG-19, ResNet-50, ViT) to distinguish between them. We also use eXplainable AI techniques to...

This tutorial explores how AI advancements can enrich the understanding, enjoyment, and accessibility of art, offering new and intriguing ways to engage with artistic works (Tutorial website: https:// sites.google.com/view/aiarttutorial.).

In precision agriculture, non-invasive remote sensing can be used to observe crops and weeds in visible and non-visible spectra. This paper proposes a novel approach for weed mapping using lightweight Vision Transformers. The method uses a lightweight Transformer architecture to process high-resolution aerial images obtained from drones and perform...

Article available at the following link: https://www.amcs.uz.zgora.pl/?action=paper&paper=1714 ______________________________________________________ Acoustic features of speech are promising as objective markers for mental health monitoring. Specialized smartphone apps can gather such acoustic data without disrupting the daily activities of patien...

This special session aims at creating an international forum with specific focus on Computational Intelligence methods related to the use of pervasive computing for healthcare and wellbeing. Traditional healthcare environments are extremely complex and challenging to manage. Pervasive and ubiquitous technologies seek to overcome these limits by suc...

Machine learning algorithms are useful in assisting medical judgments, but the resulting models are frequently challenging for doctors to comprehend. Conversely, IF-THEN rules articulated in natural language are successful at describing interpretable models that are returned by Fuzzy Inference Systems. However, the construction of the fuzzy rule ba...

Predictive process monitoring (PPM) is a specific task under the umbrella of Process Mining that aims to predict several factors of a business process (e.g., next activity prediction) based on the knowledge learned from historical event logs. Despite recent PPM algorithms have gained predictive accuracy using deep learning, they commonly perform an...

Supervised deep learning has been widely applied in medical imaging to detect multiple sclerosis. However, it is difficult to have perfectly annotated lesions in magnetic resonance images, due to the inherent difficulties with the annotation process performed by human experts. To provide a model that can completely ignore annotations, we propose an...

Learning Analytics has been widely used to enhance the educational field employing Artificial Intelligence. However, explanations of the data processing have become mandatory. In order to do this, we suggest using Neuro-Fuzzy Systems (NFSs), which can provide both precise forecasts and descriptions of the processes that produced the outcomes. The b...

In medical imaging and magnetic resonance imaging (MRI), images generally represent the interaction between electromagnetic waves and the human body, often provided in multiple modalities, each represented in gray scale. However, the analysis and interpretation of these images mainly occur sequentially or, as in the case of automated tools, as a co...

This editorial note provides an overview of the papers accepted to the First Workshop on Online Learning from Uncertain Data Streams (OLUD 2022) and related sub-areas. The OLUD workshop was intended to facilitate interdisciplinary discussion on recent advancements of state-of-the-art online machine learning and incremental pattern recognition metho...

Technological improvements have resulted in a large-scale digitization effort in recent years, leading to the increasing availability of large digitized art collections. This provides an opportunity to develop AI systems capable of understanding art, thus supporting art historians and enjoying culture more generally. This paper briefly reviews our...

Crowd analysis from drones has attracted increasing attention in recent times due to the ease of use and affordable cost of these devices. However, how this technology can provide a solution to crowd flow detection is still an unexplored research question. To this end, we propose a crowd flow detection method for video sequences shot by a drone. Th...

Crowd analysis from drones has attracted increasing attention in recent times due to the ease of use and affordable cost of these devices. However, how this technology can provide a solution to crowd flow detection is still an unexplored research question. To this end, we propose a crowd flow detection method for video sequences shot by a drone. Th...

Today, drones equipped with high-resolution cameras and integrated high-performance GPUs are increasingly available, even at affordable prices. Such sensory and computational capabilities, combined with recent advances in deep learning and computer vision, now offer the possibility of implementing decision-making systems directly on board the drone...

People use various nonverbal communicative channels to convey emotions, among which facial expressions are considered the most important ones. Thus, automatic Facial Expression Recognition (FER) is a fundamental task to increase the perceptive skills of computers, especially in human-computer interaction. Like humans, state-of-art FER systems are a...

In this paper we introduce ${\sf STARDUST}$ (event STream Analysis for pRocess Discovery Using Sampling sTragies), a process discovery approach that analyses a trace stream, in order to discover a process model that may change over time. The basic idea is to adopt a sampling technique to select the most representative trace variants to be conside...

Intelligent systems for the medical domain often require processing data streams that evolve over time and are only partially labeled. At the same time, the need for explanations is of utmost importance not only due to various regulations, but also to increase trust among systems’ users. In this work, an online data-driven learning method with focu...

Call for papers

The healthcare domain has undergone a huge transformation thanks to the availability of new technologies. In particular, health monitoring systems have entered everyday life without interfering with the daily routine. Mobile phones are increasingly used as health monitoring systems by means of ad-hoc applications. In this work, we propose a mobile...

We introduce an approach called PLENARY (exPlaining bLack-box modEls in Natural lAnguage thRough fuzzY linguistic summaries), which is an explainable classifier based on a data-driven predictive model. Neural learning is exploited to derive a predictive model based on two levels of labels associated with the data. Then, model explanations are deriv...

Questo contributo riassume i principali risultati ottenuti nella nostra ricerca sull'analisi del patrimonio artistico digitalizzato mediante reti neurali. La ricerca si è concentrata su tre direzioni: visual link retrieval, artwork clustering e neuro-symbolic learning. Possibili sviluppi futuri concludono il contributo.

Clustering artworks is difficult for several reasons. On the one hand, recognizing meaningful patterns based on domain knowledge and visual perception is extremely hard. On the other hand, applying traditional clustering and feature reduction techniques to the highly dimensional pixel space can be ineffective. To address these issues, in this paper...

Recognizing the emotion an image evokes in the observer has long attracted the interest of the community for its many potential applications. However, it is a challenging task mainly due to the inherent complexity and subjectivity of human feelings. Such a difficulty is exacerbated in the domain of visual arts, mainly because of their abstract natu...

Nowadays, applications in various domains (computer science, engineering, medicine, economy, etc.) are based on sensor data or depend on data transmission in the cloud. Effective modeling approaches to address such a massive amount of dynamically-changing data in a feasible period of time are of utmost importance. Traditional modeling approaches fo...

We study the impact of fuzziness on the behavior of Fuzzy Rule-Based Classifiers (FRBCs) defined by trapezoidal fuzzy sets forming Strong Fuzzy Partitions. In particular, if an FRBC selects the class related to the rule with the highest activation (so-called Winner-Takes-All approach), then fuzziness, as quantified by the slope of the membership fu...

The 2022 IEEE Conference on Evolving and Adaptive Intelligent Systems (IEEE EAIS 2022) will be held in Larnaca (Cyprus), a picturesque sea side town. Larnaca is a small town combining old colonial architecture with modern buildings. The area has been inhabited for at least 3000 years and is framed in the east by the Larnaca Salt Lake and to the sou...

Process discovery, one of the main branches of process mining, aims to discover a process model that accurately describes the underlying process captured within the event data recorded in an event log. In general, process discovery algorithms return models describing the entire event log. However, this strategy may lead to discover complex, incompr...

Recently, social robots are being used in therapeutic interventions for elderly people affected by cognitive impairments. In this paper, we report the results of a study aiming at exploring the affective reactions of seniors during the cognitive stimulation therapy performed using a social robot. To this purpose an experimental study was performed...

The growing availability of large collections of digitized artworks has revealed new opportunities to develop intelligent systems for the automatic analysis of fine arts. Among other benefits, these tools can foster a deeper understanding of fine arts, ultimately supporting the spread of culture. However, most of the systems proposed in the literat...

ArtGraph is a Knowledge Graph in the art domain, based on WikiArt and DBpedia, able to represent and describe concepts related to arworks.

Learning Analytics techniques are widely used to improve students’ performance. Data collected from Virtual Learning Environments (VLEs) are helpful to predict students’ outcomes through the analysis of their interactions with the platform. In this work, we propose the use of hybrid models which are able to return accurate predictions together with...

Questo contributo descrive brevemente la ricerca in essere nel Laboratorio di Intelligenza Computazionale del Dipartimento di Informatica dell'Università degli Studi di Bari "Aldo Moro" su tecniche di Computer Vision per applicazioni di IA sostenibile mediante droni.

In this work, neuro-fuzzy systems are compared to standard machine learning algorithms to predict the hypertension risk level. Hypertension is a cardiovascular disease, which should be continuously monitored to avoid the worsening of its symptoms. Automatic techniques are useful to support the clinicians in this task, however, most of the machine l...

MHealth technologies play a fundamental role in epidemiological situations such as the ongoing outbreak of COVID-19 because they allow people to self-monitor their health status (e.g. vital parameters) at any time and place, without necessarily having to physically go to a medical clinic. Among vital parameters, special care should be given to moni...

Soluzioni basate su Intelligenza Artificiale stanno già potenziando numerosi campi del sapere e dell'attività umana, inclusa l'arte. Infatti, i recenti progressi nel campo dell'Intelligenza Artificiale, insieme con la crescente disponibilità di collezioni di opere d'arte digitalizzate, stanno offrendo nuove opportunità agli specialisti in questi se...

Today, unmanned aerial vehicles, more commonly known as drones, can be equipped with high-resolution cameras and embedded GPUs powerful enough to provide effective and efficient aid to Search-and-Rescue (SAR) operations in remote and hostile environments. Locating victims, who may be unconscious or injured, as quickly as possible is critical to imp...

Dementia is one of the most common diseases in the elderly and a leading cause of mortality and disability. In recent years, a research effort has been made to develop computer aided diagnosis tools based on machine (deep) learning models fed with neuroimaging data. However, while much work has been done on MRI imaging, very little attention has be...

Automatic art analysis has seen an ever-increasing interest from the pattern recognition and computer vision community. However, most of the current work is mainly based solely on digitized artwork images , sometimes supplemented with some metadata and textual comments. A knowledge graph that integrates a rich body of information about artworks, ar...

Smartphones enable to collect large data streams about phone calls that, once combined with Computational Intelligence techniques, bring great potential for improving the monitoring of patients with mental illnesses. However, the acoustic data streams recorded in uncontrolled environments are dynamically changing due to various sources of uncertain...

The semantic segmentation of remotely sensed images is a difficult task because the images do not represent well-defined objects. To tackle this task, fuzzy logic represents a valid alternative to convolutional neural networks-especially in the presence of very limited data-, as it allows to classify these objects with a degree of uncertainty. Unfo...

Artificial Intelligence solutions are empowering many fields of knowledge, including art. Indeed, the growing availability of large collections of digitized artworks, coupled with recent advances in Pattern Recognition and Computer Vision, offer new opportunities for researchers in these fields to help the art community with automatic and intellige...

Automatic age estimation from facial images is attracting increasing interest due to its many potential applications. Several deep learning-based methods have been proposed to tackle this task; however, they usually require prohibitive resources to run in real-time. In this work, we propose a fully automated system based on YOLOv5 and EfficientNet...

Predictive process monitoring (PPM) techniques have become a key element in both public and private organizations by enabling crucial operational support of their business processes. Thanks to the availability of large amounts of data, different solutions based on machine and deep learning have been proposed in the literature for the monitoring of...