Technological advancements in Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) have enabled innovative applications in education and cultural heritage. This study presents the development and implementation of a MR experience at the Zoological Museum “Francesco Cambria” of the University of Messina, aimed at enhancing visitor engagement and learning. The MR system integrates 3D models, interactive assets, and gesture-based controls through Microsoft HoloLens 2, providing users with an immersive, multisensory experience. The system offers two visit modes: an Autonomous Mode, where visitors interact with 3D reconstructions and contextual information, and a Guided Mode, which delivers audio-narrated content based on spatial triggers. Usability and user experience were evaluated based on the System Usability Scale (SUS) and the Simulator Sickness Questionnaire (SSQ).

This work compares univariate and multivariate Long Short-Term Memory (LSTM) models for predicting delays in public transportation. Only historical delay data was used to train the univariate model, which is effective for last-minute predictions but limited in capturing wider temporal correlations because it is optimized for real-time inference with minimal data requirements. To better capture intricate patterns in transportation delays, the multivariate model incorporates extra contextual factors like time of day and topographical coordinates. Multiple multivariate models were trained on different time intervals (e.g., daily, weekly, and monthly) to evaluate the impact of training data selection on predictive accuracy. The findings show that multivariate models provide better long-term accuracy, especially when trained on properly segmented data, whereas univariate models are computationally efficient and excellent for short-term updates. These results suggest how to best adapt LSTM-based forecasting models for dynamic, practical transportation applications.

The growing diversity of data sources in modern organizations has made efficient querying and integration crucial for actionable insights. With data distributed across structured relational databases like MySQL and semistructured NoSQL systems such as MongoDB, querying heterogeneous environments has become more complex. Apache Drill and PrestoDB are two prominent query engines designed to address this challenge by providing federated querying across multiple data sources. This paper examines the architecture, design, and performance of Apache Drill and PrestoDB, focusing on their integration with MySQL and MongoDB. Using a synthetic smart city dataset that simulates urban mobility, traffic, air quality sensors, and public infrastructure usage, a series of queries, spanning from basic data retrieval to complex multi-source joins and aggregations, were executed to assess each engine’s performance across various workloads. This research provides insights into the trade-offs between flexibility and performance when querying heterogeneous data environments. It also offers guidance for optimizing data retrieval and analysis across various storage systems.

The COVID-19 pandemic was first identified in Wuhan (China) in late 2019, and quickly escalated into a global crisis, emphasizing the need for rapid and accurate diagnostic methods. Since chest X-rays play a key role in diagnosing COVID-19, we applied deep learning techniques to the COVID-19 Radiography Dataset to enhance diagnostic accuracy. These models are trained with augmented data to improve generalization across different radiographic presentations of the virus. The results demonstrate the speed and reliability of COVID-19 diagnosis, helping healthcare systems to make faster treatment decisions. This also supports ongoing efforts to manage COVID-19 and creates a foundation for using Artificial Intelligence to detect future respiratory diseases.

Hospitals suffer from implementing Data Spaces due to the risks related to data security aspects. To ensure patients' data privacy, healthcare organizations can incorporate pseudonymization strategies into their data management practices, promoting collaboration and information sharing among several hospital departments and healthcare professionals. In this paper, we defined and implemented the intent-based mul-tilevel granular approach for HL7 FHIR JSON documents pseudonymization, by comparing it with non-granular encryption of the entire document. With this approach, we enhance patient confidentiality and facilitate efficient healthcare data sharing within the Intra-Hospital Data Space, facilitating enhanced flexibility and scalability in deploying and utilizing data management systems.

This paper proposes a new solution for promoting safe driving and reducing accidents caused by drunk drivers. The scientific innovation of our work lies in the strong integration between virtual and physical environments, which allows users to experience strong emotions in simulated driving scenarios with alcohol impairments. To achieve this aim, we have implemented a Metaverse environment able to interact with multiple physical input and output devices. The virtual environment reproduces alcohol-related impairments, such as blurred vision, delayed response to commands and shaking in the event of an accident, also showing the tragic consequences of accidents during the experience. We have validated the developed solution by experimental measurement of both software performance and Quality of Experience (QoE) of volunteer users.

This work proposes a content-based approach for structured document obfuscation, which is based on Secret Share techniques implemented at the Edge of a computing system. The key innovation of our work is to increase the flexibility in data sharing, keeping data at the Edge, and improving data security, reliability, and availability. The proposed solution can also suit more complex scenarios that include continuum capabilities towards the Cloud, to benefit from high computing resources. We present the details of our work and the implementation. Then, we evaluate the performance at the Edge of the proposed approach, comparing it with its traditional implementation applied to the entire document. The goal is to analyze the differences in performance and security between the two approaches.

Monitoring road pavement conditions is vital to prevent harm or accidents to vehicles and people, and it is a crucial governmental task. Some Artificial Intelligence (AI) based systems for automatically detecting and classifying road anomalies have been proposed in the literature. In particular, vision-based Deep Learning techniques process images to analyze the road pavement and detect different types of anomalies, thus offering a very flexible approach to road monitoring. This paper focuses on the comparison of two different vision-based techniques aimed at pothole detection: CNN and R-CNN. We have carried out our experiments by analyzing video streams acquired with a smartphone mounted on the windshield of a vehicle through a car mobile holder. Also, the Deep Learning classification models have been run on different computing infrastructures, such as a Microsoft Azure virtual machine (VM) and an edge device Raspberry Pi, to evaluate the usability in the Cloud and on-road infrastructures.

Natural disasters are more and more often present in our daily life. Many are the cases where these events affect people and economies. In this context, there is the need for a technological intervention in support of first responders, with solutions capable of make decisions on the disaster areas. Indeed, considering these scenarios are time-sensitive, the intention is moving the computation units closer to those areas. In this paper, we propose a computing continuum architecture for offloading distributed intelligences over cloud, edge and deep edge layers. Exploiting the federated learning paradigm, enables mobile and stationary devices to independently train local models, contributing to the creation of the global common model.

Nowadays, tele-rehabilitation has emerged as an effective approach for providing assisted living, increasing clinical outcomes, positively enhancing patients' Quality of Life (QoL) and fostering the reintegration of patients into society, also pushing down clinical costs. Cloud computing in combination with Edge Computing and Artificial Intelligence (AI) are the main enablers for tele-rehabilitation. In particular, Edge rehabilitation devices can act as smart digital biomarkers sending quantifiable physiological and behavioural patients' data to the Hospital Cloud. However, due to hardware limitations, it is not clear which Machine Learning (ML) models can be executed in cheap Edge devices. In this paper, we aim at answering this question. In particular, several ML-based pose estimation models (i.e., PoseNet, MoveNet and BlazePose) have been tested and assessed on the Edge, identifying the best one and demonstrating the feasibility of such an approach.

Nowadays the process of anonymization of documents has been the subject of several studies and debates. By anonymization of documents, we mean the process of replacing sensitive data in order to preserve the confidentiality of documents without altering their content. In this work, we introduce Docflow, an open-source document anonymization engine capable of anonymizing documents based on specific filters chosen by the user. We applied Docflow to anonymize a set of legal documents and performed a processing performance analysis. By providing a Markdown input file to be anonymized, Docflow is able to redact all information according to users' choices, preserving the document content. Docflow will be integrated with NLP algorithms for the generation of the Markdown source file starting from documents already processed in different formats, but always with human supervision in the loop.

The recent advancements in miniaturized smart data collecting devices pushed the need of securing communications between people and devices. Traditional approaches based on key exchange protocol can't be performed by resource-constrained embedded devices, and a novel approach, based on a robust decentralization of the eXtended Triple Diffie-Hellman (X3DH) protocol, has been proposed, namely the BlockChain-Based X3DH (BCB-X3DH) protocol. This work progresses the analysis further to fit a generic Smart City scenario with Edge and IoT nodes, performing intensive analysis on Raspberry Pi 3 model B+ and Raspberry Pi 4 to validate that the new protocol is not only resistant from well-known distributed attacks but can also be executed by miniaturized hardware with benefits in terms of resources, energy consumption and battery life-cycle.

Internet of Things has revolutionized the way services are distributed in smart environments, approaching the computation where data are generated. However, IoT devices have limited resources and reconfiguring them can be very difficult. In these cases, Edge computing represents a challenging solution supporting IoT with flexible management of resources. We investigate how pushing computation activities from Edge to IoT, changing the behavior of IoT nodes according to application or system requirements. We adopted the Multi-Hop-Over-The-Air update technology enabling the auto-configuration of IoT devices based on MicroController Units. Considering IoT nodes connected in a mesh network, we developed a distributed and collaborative ecosystem performing on-fly injection of code in IoT nodes, thus automatically deploying new services whenever necessary. We implemented a prototype of the proposed solution over a heterogeneous Edge-IoT mesh network and performed experiments with the purpose to study the update phase of end-devices while they execute Digital Signal Processing.

Nowadays, the increasing complexity of digital applications for social and business activities has required more and more advanced mechanisms to prove the identity of subjects like those based on the Two-Factor Authentication (2FA). Such an approach improves the typical authentication paradigm but it has still some weaknesses. Specifically, it has to deal with the disadvantages of a centralized architecture causing several security threats like denial of service (DoS) and man-in-the-middle (MITM). In fact, an attacker who succeeds in violating the central authentication server could be able to impersonate an authorized user or block the whole service. This work advances the state of art of 2FA solutions by proposing a decentralized Microservices and Blockchain Based One Time Password (MBB-OTP) protocol for security-enhanced authentication able to mitigate the aforementioned threats and to fit different application scenarios. Experiments prove the goodness of our MBB-OTP protocol considering both private and public Blockchain configurations.

Every year the healthcare sector suffers from incorrect therapies and an increasing number of patients analysis, which causes congestion in the hospitals and, potentially, worsening of patient's clinical conditions. Extending the concept of the Decision Support System already investigated by the authors, this work advances the state of the art of Reinforcement Learning (RL) via Markov Decision Process formulation, considering an agent acting in his environment motivated by the achievement of the maximum individual objective by appropriate incentives. Transparency, security and privacy of the model are guaranteed by the adoption of Blockchain to enhance the perception of safety around medical operators improving access to hospital services. Experiments focused on the Smart Contract execution time and resources usage have proved the goodness of the proposed model considering both private and public Blockchain configurations.

Several cases are reported every year where the prescribed therapy results incompatible with the patient’s medical history, leading to worsening of clinical condition or death. Some technologies and processes to prevent this misbehaviour already exist, but a concrete solution is not available in hospitals yet. This paper presents a Decision Support System (DSS) that can be easily integrated into a typical health workflow at hospitals and provides feedback on the possible prescription of drugs at a patient with specific diseases. The DSS is based on a Big Data analysis algorithm able to check drugs and diseases relationships and detect possible failures in drugs prescriptions. We developed a prototype of the proposed solution, implementing the DSS system and setting up the necessary Big Data management tools for the effective adoption of the DSS system. We performed some evaluations to assess the efficacy and the response time of the DSS algorithm.