Museums are increasingly adopting Extended Reality (XR) technologies to enhance access to cultural material; nevertheless, many applications still emphasize individual experiences, overlooking social interaction and inclusivity. This research aims to explore how a collaborative, inclusive XR experience can enhance communal exploration of cultural heritage while accommodating diverse user needs. An inclusive and collaborative XR experience was developed for the Antiquarium di Boscoreale, located within the Parco Archeologico di Pompei. The proposed approach integrates immersive visualization, inclusive interface design, and an adaptive suggestion layer to facilitate widespread access to a digital replica of the selected element. The recommendation system facilitates attention direction and content modification without establishing rigid pathways. A user study involving 28 people examined the experience regarding presence, social presence, usability, inclusivity, and the perceived effectiveness of adaptive recommendations. The findings indicate a high level of satisfaction. This suggests that collaborative and adaptive XR could enhance museum experiences.

The metaverse is emerging as a new space for digital engagement, revolutionising access and the cultural experience. Virtual museums overcome the physical limitations of traditional museums, offering immersive and dynamic experiences. This study aims to examine the opportunities and challenges offered by the metaverse by exploring spatial iterations and the impact of access devices on the user experience in museums. Virtual spaces can replicate or reinvent physical environments, removing geographical barriers and harnessing digital potential to create distinctive interactions, such as artwork animations and interactive narratives. The devices used significantly influence the experience: PCs, with VR viewers and advanced peripherals, offer immersion and precision; smartphones, although limited by small screens, excel in accessibility; tablets balance portability and performance, but remain inferior to PCs in terms of precision. Internet connection quality is crucial: mobile connections can cause latency, compromising fluidity and collaborative interactions. User involvement ranges from passive exploration to active collaboration, such as artefact reconstruction. More advanced technologies support complex interactions, while portable ones favour simpler, more intuitive activities. Furthermore, social dynamics in the metaverse depend on non-verbal signals and the ergonomics of interfaces, highlighting the importance of designing inclusive and adaptive digital environments. In conclusion, the metaverse offers a unique opportunity to democratise access to culture, overcoming conventional barriers and promoting global engagement. Customising design and infrastructure can make these experiences more accessible and meaningful for all.

Parkinson’s disease quietly affects fine motor control long before obvious symptoms appear, creating a need for accessible screening tools that can catch it early. This paper explores whether the way people type, specifically the timing patterns in their keystrokes, could serve as a simple and noninvasive digital marker for Parkinson’s-related motor impairment. Two complementary datasets are used: Tappy with 181 subjects and 177,000 typing windows from home environments, and NeuroQWERTY MIT-CS1/CS2 with 85 subjects and 3,117 windows from clinical settings. From this data, 26 timing features are extracted, including the duration of keypresses, the gaps between keystrokes, and patterns in typing pauses. Five different approaches are tested, from a basic baseline to Logistic Regression, SVM, Random Forest, and a 1D CNN. Random Forest gave the best overall results with an AUC of 0.748 when balancing the pooled data. When specifically looking at early-stage cases (those with UPDRS scores of 20 or lower), a meaningful signal remained, with an AUC of 0.737. However, when testing models across different datasets, performance dropped significantly, in some cases by over 27 AUC points. This indicates that domain shift. The difference between how people type at home versus in clinical settings, is a major challenge that needs to be addressed. A working FastAPI prototype is built that captures keystrokes in the browser and generates risk scores without storing what people type. This work shows that keystroke-based screening is promising and privacy-preserving, but an honest assessment indicates it requires further validation before clinical use.

Cultural heritage institutions implement E-business information systems to integrate enjoyment, economic sustainability, and public purpose. This study presents a comprehensive framework that systematically connects cultural data (shared models and vocabularies, digitally described content) with operational processes (bookings, online sales, membership, and public relations) through integration utilising documented interfaces and event exchange. This approach produces a distinctive information model that connects objects, individuals, locations, and events, while also quantifying the impact of architectural decisions on measurable outcomes: data quality and alignment, service response times, booking completion rates, membership renewal rates, and decreased absenteeism. The methodological component establishes reproducible protocols for collecting and analysing evidence, considering seasonality and contextual factors, while incorporating data protection and accessibility standards throughout the design process. We examine the anticipated outcomes and ramifications for sustainability, experiential quality, and system governance.

The rapid evolution of connected vehicles and Internet of Things (IoT) technologies has significantly increased the complexity of modern automotive systems while simultaneously expanding their attack surface. In particular, the Controller Area Network (CAN-Bus), which enables communication among Electronic Control Units (ECUs), represents a critical component of in-vehicle networks and a potential target for cyber-attacks. The absence of built-in security mechanisms such as authentication and encryption makes CAN-based communication vulnerable to message injection and manipulation attacks. This paper proposes a context-aware intrusion detection approach based on a Multilevel Graph (MuG) representation to identify anomalous behaviors in connected vehicles. The proposed framework integrates data acquisition from the CAN-Bus, semantic context modeling and probabilistic inference mechanisms to analyze relationships between system components and detect abnormal system states. The architecture is organized into four layers—Acquisition, Knowledge, Inference Engine and Application—allowing structured management of data collection, contextual knowledge representation and anomaly detection. To evaluate the effectiveness of the proposed methodology, a case study focused on automotive cybersecurity was developed using the CARLA simulation environment, where multiple attack scenarios were simulated through the injection of malicious CAN messages. The experimental evaluation was conducted on a dataset generated during simulation runs and analyzed using precision, recall and F1-score metrics. The results demonstrate that the proposed multilevel graph-based approach significantly improves the detection of anomalous behaviors, achieving high accuracy in identifying both normal system conditions and simulated attack scenarios. The findings suggest that integrating context-aware modeling with graph-based inference represents a promising direction for enhancing intrusion detection capabilities in connected vehicle systems.

The study demonstrates a novel method of urban planning through a collaborative digital platform that promotes engagement and interaction among people, technicians, and administrators. Utilizing the suggested digital platform, the citizen acts as a catalyst for urban transformation, initiating processes of inclusion, participation, and civic engagement. The research examines the application of Building Information Modeling (BIM) as a foundational model for a desktop gaming platform, establishing a virtual three-dimensional (3D) interactive environment through a desktop application. This environment facilitates citizen training and collaboration in generating innovative design concepts and proposals for the repurposing of existing structures. Consequently, the end user assumes the role of designer, innovating interventions by contemplating spatial configurations and postulating various functionalities. This reinforces the role of active public involvement and territorial governance by the Public Administration, enabling it to manage diverse contributions aimed at co-designing and co-producing services. Moreover, the effective integration of HBIM (Heritage Building Information Modeling) and its application paves the door for novel opportunities in engagement, education, and interactive training, necessitating a detailed and realistic physical environment as a contextual framework for action.

Misinformation in e-business—discounts based on volatile prices, fictitious stock levels, erroneous certifications, and implausible delivery commitments—erodes trust, competition, and regulatory adherence. This study introduces EBFN-Detect, a neuro-symbolic framework for claim-centric verification that incorporates a domain ontology (EBFN-O), a commercial knowledge graph, and natural language processing models. The pipeline extracts claims from diverse sources, conducts entity linking for products, brands, and sellers, retrieves ontology-guided evidence (RAG on KG), and assesses truthfulness by integrating a claim-evidence aware classifier with symbolic verifications of temporal consistency, price plausibility, and regulatory compliance. The output generates calibrated probabilities and verifiable explanations derived from supported or refuted chains with provenance. The work delineates the method, introduces EBFN-O in accordance with schema.org/GoodRelations/PROV-O, presents a multi-source corpus annotated at three tiers (claim, linking, truth) with reproducible guidelines, describes a RAG + KG pipeline featuring transparent fusion and calibration, and proposes an evaluation protocol that integrates metrics of accuracy, retrieval quality, and explanatory utility. Consequently, EBFN-Detect demonstrates enhancements in macro F1 and Brier/ECE relative to pure neural baselines, exhibiting significant benefits in time-sensitive scenarios and in categories characterized by substantial variant ambiguity, thereby delineating a feasible approach to dependable, traceable, and contestable verification in digital commerce.

Over the years, technology has continued to improve and evolve, along with the virtual representation of real-world environments. These reconstructions serve various fields of research and beyond. The focus of this work is to transfer a real-world road segment into a driving simulation software, aiming to achieve a high level of graphical fidelity. The study is based on the reconstruction of a section of roadway located within the University of Salerno’s Fisciano campus. This was made possible through a methodology involving laser scanner surveying of the circuit, subsequent import into modeling software, refinement of any imperfections, and final validation of the resulting model. The last phase took place at the Virtual Reality Laboratory of the Department of Industrial Engineering, where, according to the main goal of the workflow, test drives were carried out to assess the accuracy of the modeled track compared to the real one. After several iterations aimed at ensuring correct compatibility with the driving simulation software and fixing missing points resulting from the scans, the validity of the proposed model was confirmed. Finally, some potential future developments were outlined to enable the use of the reconstructed model for additional academic and industrial purposes.

Smart city environments increasingly integrate digital technologies, sensing infrastructures, and intelligent data-driven services to improve citizens’ quality of life and enhance urban experiences. Within this context, cultural heritage sites and archaeological parks represent important components of smart tourism ecosystems, where personalized and context-aware services can significantly improve visitor engagement. This paper presents a framework designed to enhance cultural experiences in archaeological parks through a Context-Aware Recommender System (CARS). The proposed framework integrates heterogeneous contextual data collected from IoT infrastructures, environmental sensors, and user devices, combining them within a layered framework composed of acquisition, knowledge management, inference, and application components. The recommendation engine is based on a Contextual Bias Matrix Factorization (CBMF) model that exploits embedded contextual information to predict user preferences and suggest relevant Points of Interest. The effectiveness of the proposed approach is evaluated through experiments conducted on three widely used context-aware datasets: DePaulMovies, LDOS-CoMoDa, and Travel-STS. The results show that the proposed method achieves competitive performance compared with state-of-the-art context-aware recommendation techniques, demonstrating its potential for improving user experiences in cultural heritage environments.

Immersive technologies support heritage interpretation and management, yet research remains divided between cultural and archaeological heritage and urban planning. This systematic review, reported according to PRISMA 2020, aimed to examine the design, application, and evaluation of augmented, virtual, and mixed reality systems in archaeological parks, historic districts, and urban-planning contexts. Peer-reviewed English-language journal articles and full conference papers published from 2010 to 15 July 2026 were eligible; museum-only, artifact-only, non-immersive, and methodologically insufficient reports were excluded. Scopus, Web of Science Core Collection, IEEE Xplore, ACM Digital Library, and SpringerLink were searched through 15 July 2026. A five-domain, study-type-adapted rubric was used for critical appraisal, and findings were synthesized narratively by spatial scale, delivery mode, technology pipeline, and evaluation. Of 10,790 records, 21 studies were included: 17 direct applications, three enabling methods, and one foundational survey. Twelve reported user or stakeholder evaluations, but only ten reported numerical sample sizes, precluding calculation of a pooled participant total. Evidence was heterogeneous, predominantly descriptive, and rarely longitudinal. The original screening, data extraction, and critical appraisal were performed by a single reviewer. Following peer review, all 21 included reports and the key coding and appraisal variables underwent retrospective independent verification and reconciliation. No supplementary hand-searching or citation searching was conducted. The urban dimension of ancient cities remains underexplored, while communication of uncertainty in city-scale reconstructions remains unresolved. The review proposes a cross-domain taxonomy, core evaluation outcomes, and an integrated research agenda. No external funding was received. The review was not registered, and no formal protocol was prepared.

Digital innovation has revolutionised the construction sector, bringing sophisticated technologies for infrastructure monitoring and predictive management. This study introduces a comprehensive methodology utilising BIM, IoT and AI to enhance the maintenance and operational efficiency of buildings via the deployment of the DT. BIM offers a comprehensive digital representation of structures, whereas IoT sensors gather real-time data on environmental and structural variables, including temperature, humidity, and soil conditions. AI employs machine learning algorithms to analyse data, detect abnormalities, forecast failures, and enhance building management. The ThingsBoard platform facilitates the collection and visualisation of IoT data, producing automatic warnings upon the surpassing of important thresholds. A case study on a single-family residence was conducted to validate the suggested methodology. IoT sensors affixed to the structure continuously monitor the building’s state, supplying data integrated into the BIM model. The analysed data enable the prediction of structural issues and the recommendation of preventive maintenance measures, thereby decreasing costs and enhancing safety. The findings illustrate that the amalgamation of BIM, IoT, and AI can transform the construction industry, enhancing the efficiency, sustainability, and safety of infrastructures. This methodology signifies progress towards more intelligent, robust, and proactively managed buildings.

Digitising public administration (PA) is essential for enhancing efficiency, transparency, and traceability in public procurement management. This document presents an integrated model that amalgamates building information modelling (BIM), digital twins (DT), IoT sensors, smart contracts, and blockchain technology to automate the contract lifecycle, encompassing technical verification to performance settlement, in accordance with the National Recovery and Resilience Plan (PNRR) and the new Public Contracts Code (Legislative Decree 36/2023). The goal is to test a digital system that can work with other systems and replace manual tasks with ones that are automated, clear, and easy to track. The concept was implemented on a photovoltaic system at the University of Salerno, where a digital twin, utilising real-time data, was synced with a BIM model in the IFC format. The operational data, verified against established technical thresholds, activates smart contracts on the Ethereum blockchain, automatically authorising the execution of payments or status records. The results indicate a substantial decrease in technical intervention duration, enhanced monitoring precision, and heightened trust among the involved parties. The model shows that it can be used again and again for large and complicated public infrastructures. It also creates a foundation for unified digital management, which makes it easier to change the way government works and bring new technologies into the public sector.

In recent years, e-business ecosystems have evolved into complex and data-driven information systems, where adaptability to the context has become a critical success factor. Traditional decision-making models, however, often prove inadequate to manage the dynamism and uncertainty of today’s digital environments, creating a gap between the richness of available data and the ability of systems to exploit it proactively. This article proposes an innovative framework integrating Artificial Intelligence and Situation Awareness to develop human-centered and adaptive E-Business Information Systems (EBIS). Our approach combines the Situation Awareness (SA) paradigm, which is the ability to perceive, understand, and project future states of the context, with a multilevel software architecture. By leveraging the integration of data from the Internet of Things (IoT), the formalization of knowledge through semantic ontologies, and the predictive power of Bayesian probabilistic models, the framework enables systems to react and anticipate user needs. The validation of the framework, conducted through a use case in the domain of smart cultural tourism at the Archaeological Park of Pompeii, demonstrated the effectiveness of our approach by defining a solid methodological basis for the creation of next-generation e-business systems, capable of learning and reacting dynamically, improving the resilience of processes and placing the user at the center of an intelligent and personalized digital experience.

As immersive technologies gain prominence in cultural heritage, understanding their specific experiential qualities has emerged as a central research challenge. This study presents a rigorously controlled comparative analysis of three immersive systems: virtual reality (VR), 360° virtual tours (VR360), and augmented reality (AR), deployed at the archaeological site of Villa Regina in Boscoreale, Italy. Despite the widespread integration of immersive technologies at cultural heritage sites, direct comparisons remain challenging due to variations in content, interface design, and assessment methods. To resolve this, three experiences were developed within a unified production framework using identical digital assets. Narrative structure, informational content, and interface logic were standardized across all conditions. A between-subjects experiment with 90 participants explored differences in intrinsic motivation, perceived presence, and user engagement using validated post-experience questionnaires and semi-structured interviews. The results show that VR elicited the greatest spatial presence and engagement, AR improved perceived realism and contextual authenticity, and VR360 offered the most accessible but least immersive experience. This study proposes a reproducible methodological framework for systematic comparisons of immersive systems and provides evidence-based design recommendations for digital cultural heritage experiences.

Accurate thermal management is crucial for ensuring the safety, longevity, and performance of lithium-ion batteries, especially in compact embedded systems like USB chargers, power banks, and IoT nodes. Despite extensive research on predictive thermal models and intelligent control frameworks, their implementation in resource-constrained microcontroller-class devices has been limited. Existing strategies in the literature, such as threshold-based or PID logic, cloud-enabled analytics, machine learning models, and observer-based estimators, are often reactive, computationally intensive, or dependent on external infrastructure, making them unsuitable for low-power, standalone applications. This study introduces a novel Scalable Embedded Thermal Intelligence architecture designed for real-time battery thermal regulation in locally executable, without cloud dependency, low-cost platforms. Unlike conventional methods, the proposed system operates entirely on-device using closed-form models implemented on an ESP32 microcontroller. It combines two synergistic algorithms: a static preemptive model that calculates a safe C-rate at startup based solely on ambient and initial battery temperature, and a dynamic disturbance-aware model that monitors temperature rise per SOC step and adjusts airflow or current adaptively without requiring high memory, floating-point units, or supervisory control. The architecture achieves sub-second response times, <7% RAM, and <25% Flash usage, and does not need cloud connectivity, simulation backend, or complex thermal-management infrastructures such as liquid cooling circuits, phase-change systems, or cloud-supervised architectures. The significant contribution of this work is not the introduction of a new electrochemical–thermal formulation, but the effective integration and application of previously validated closed-form thermal predictors on low-cost microcontroller-class hardware, designed for anticipatory battery thermal regulation while adhering to strict computational limitations. Compared to traditional battery thermal management systems using PCM, liquid-cooling circuits, or cloud-based predictive estimators, the proposed approach eliminates the need for complex thermal hardware, fluidic systems, external computing infrastructure and resource-efficient edge operation. This makes the system suitable for deployment in real-world embedded applications like USB-C smart charging cables, compact IoT power banks, and portable medical devices, where form factors, energy efficiency, and cost are critical. The proposed SETI framework offers a firmware-integrated architecture and a firmware-integrated solution that provides a lightweight embedded alternative for predictive thermal regulation for distributed energy systems and miniaturized electronics.

The shift towards predictive and intelligent management models in cultural asset conservation has gained significance due to the intricacies of degradation processes and the necessity for sustainable preservation solutions. This project aims to develop a methodological framework for creating a Digital Twin (DT) for architectural heritage, which can integrate geometric, historical, environmental, and predictive data into a cohesive, dynamic system. The suggested method integrates high-accuracy surveying techniques with semantic modeling using Heritage Building Information Modelling (HBIM), augmented by real-time data collection using Internet of Things (IoT) devices. Environmental and structural parameters are perpetually monitored and integrated with the digital model using visual programming procedures, facilitating real-time changes and interactions. Machine Learning (ML) techniques are employed to analyze time-series data for the identification of deterioration trends and the simulation of predictive maintenance scenarios. The technique was validated by its application to the Ponte Leproso, a Roman bridge in Benevento, Italy, noted for its intricate stratifications and susceptibility to environmental stresses. The development of a DT of the structure facilitated the dynamic integration of sensor data with historical and architectural knowledge, hence enabling the formulation of data-driven conservation plans. This integrated workflow illustrates how the collaboration of HBIM, IoT, and AI technologies may facilitate the transition of cultural heritage management from reactive intervention to proactive, intelligent, and sustainable preservation methods.

The conservation of archaeological heritage is important for understanding and preserving human history, but conventional approaches often cannot deal effectively with the magnitude and complexity of modern issues. The integration of AI (artificial intelligence) into archaeological methodologies is enhancing research, analysis, and preservation practices. This paper focuses on the changing dynamics of AI applications in archaeological research, pointing out the phases of trend detection, technological progress, and collaborative networks: using bibliometric analysis, co-authorship networks, and keyword density visualizations, we select the dominant topics affecting the discipline, such as ML (machine learning), remote sensing, and predictive modelling. The data indicates that new technologies, such as automated detection systems and neural networks, have greatly improved strategies for site discovery and preservation. However, there exist significant issues like data access, ethical concerns, and technology inequalities across research fields. This study aims to provide a thorough and up-to-date synthesis of AI’s role in archaeology, highlighting its potential to define new best practices for heritage conservation and defining a framework for future research and collaboration. Finally, this research underlines the importance of using interdisciplinary approaches to ensure that AI serves not only as an efficient tool, but also as an ethical and sustainable means of maintaining humanity’s shared cultural heritage.

Structural monitoring plays an important role in ensuring the safety and longevity of infrastructure; nevertheless, conventional methods frequently lack the capacity for continuous and predictive analysis. This study presents an advanced Structural Health Monitoring (SHM) system that integrates IoT, Digital Twin (DT), and Deep Learning (DL) to automate the recognition of issues with structure and enhance preventive maintenance. The methodology entails obtaining vibrational data from MEMS accelerometer sensors, analyzing it with a Convolutional Autoencoder (CAE), and visualizing the anomalies immediately within the digital twin of the monitored structure. The deep learning model, trained on temporal sequences of vibration signals acquired during normal operating conditions, acquires a concise description of standard structural behaviour. During the inference phase, the reconstruction error is a metric to detect substantial deviations and produce real-time alerts. The paper delineates the issue, current advancements, methodology employed, outcomes, and a comparison with conventional procedures. The findings underscore the potential of merging IoT, DT, and DL to enhance structural monitoring, facilitating more efficient infrastructure management and mitigating the risk of unforeseen failures.