Search Results (19)

Federated Learning (FL) is a privacy-focused technique for training models; however, most existing unlearning techniques in FL fall significantly short of the efficiency and situational awareness required by the GDPR. The paper introduces two new unlearning methods: EG-FedUnlearn, a gradient-based technique that eliminates the effect of specific target clients without retraining, and OFU-Ontology, an ontology-based approach that ranks data importance to facilitate forgetting contextually. EG-FedUnlearn directly eliminates the contributions of specific target data by reversing the gradient, whereas OFU-Ontology utilizes semantic relevance to prioritize forgetting data of the least importance, thereby minimizing the unlearning-induced degradation of models. The results of experiments on seven benchmark datasets demonstrate the good performance of both algorithms. OFU-Ontology yields 98% accuracy of unlearning while maintaining high model utility with very limited accuracy loss under class-based deletion on MNIST (e.g., 95%), surpassing FedEraser and VeriFi on the multiple metrics of residual influence, communication overhead, and computational cost. These results indicate that the cooperation of efficient unlearning algorithms with semantic reasoning, minimized unlearning costs, and operational performance in a distributed environment. This paper becomes the first to incorporate ontological knowledge into federated unlearning, thereby opening new avenues for scalable and intelligent private machine learning systems. Full article

The digital transformation of the Architecture, Engineering and Construction sector is accelerating the adoption of digital platforms as critical enablers of data integration, stakeholder collaboration and process optimization. This paper presents a systematic review of 125 peer-reviewed journal articles (2015–2025), selected through a PRISMA-guided search using the Scopus database, with inclusion criteria focused on English-language academic literature on platform-enabled digitalization in the built environment. Studies were grouped into six thematic domains, i.e., artificial intelligence in construction, digital twin integration, lifecycle cost management, BIM-GIS for underground utilities, energy systems and public administration, based on a combination of literature precedent and domain relevance. Unlike existing reviews focused on single technologies or sectors, this work offers a cross-sectoral synthesis, highlighting shared challenges and opportunities across disciplines and lifecycle stages. It identifies the functional roles, enabling technologies and systemic barriers affecting digital platform adoption, such as fragmented data sources, limited interoperability between systems and siloed organizational processes. These barriers hinder the development of integrated and adaptive digital ecosystems capable of supporting real-time decision-making, participatory planning and sustainable infrastructure management. The study advocates for modular, human-centered platforms underpinned by standardized ontologies, explainable AI and participatory governance models. It also highlights the importance of emerging technologies, including large language models and federated learning, as well as context-specific platform strategies, especially for applications in the Global South. Full article

Data integration (DI) and semantic interoperability (SI) are critical in healthcare, enabling seamless, patient-centric data sharing across systems to meet the demand for instant, unambiguous access to health information. Federated information systems (FIS) highlight auspicious issues for seamless DI and SI stemming from diverse data sources or models. We present a hybrid ontology-based design science research engineering (ODSRE) methodology that combines design science activities with ontology engineering principles to address the above-mentioned issues. The ODSRE constructs a systematic mechanism leveraging the Ontop virtual paradigm to establish a state-of-the-art federated virtual knowledge graph framework (FVKG) embedded virtualized knowledge graph approach to mitigate the aforementioned challenges effectively. The proposed FVKG helps construct a virtualized data federation leveraging the Ontop semantic query engine that effectively resolves data bottlenecks. Using a virtualized technique, the FVKG helps to reduce data migration, ensures low latency and dynamic freshness, and facilitates real-time access while upholding integrity and coherence throughout the federation system. As a result, we suggest a customized framework for constructing ontological monolithic semantic artifacts, especially in FIS. The proposed FVKG incorporates ontology-based data access (OBDA) to build a monolithic virtualized repository that integrates various ontological-driven artifacts and ensures semantic alignments using schema mapping techniques. Full article

Federated Learning (FL) is emerging as an encouraging paradigm for AI model training in healthcare that enables collaboration among institutions without revealing sensitive information. The lack of transparency in federated models makes their deployment in healthcare settings more difficult, as knowledge of the decision process is of primary importance. This paper introduces SemFedXAI, a new framework that combines Semantic Web technologies and federated learning to achieve better explainability of artificial intelligence models in healthcare. SemFedXAI extends traditional FL architectures with three key components: (1) Ontology-Enhanced Federated Learning that enriches models with domain knowledge, (2) a Semantic Aggregation Mechanism that uses semantic technologies to improve the consistency and interpretability of federated models, and (3) a Knowledge Graph-Based Explanation component that provides contextualized explanations of model decisions. We evaluated SemFedXAI within the context of e-health, reporting noteworthy advancements in explanation quality and predictive performance compared to conventional federated learning methods. The findings refer to the prospects of combining semantic technologies and federated learning as an avenue for building more explainable and resilient AI systems in healthcare. Full article

The rapid expansion of IoT devices has introduced major challenges in ensuring data interoperability, enabling real-time processing, and achieving scalability, especially in decentralized edge computing environments. In this paper, an advanced framework of FedProx with ontology-driven data standardization is proposed, which can meet such challenges comprehensively. On the one hand, it can guarantee semantic consistency across different kinds of IoT devices using unified ontology, so that data from multiple sources could be seamlessly integrated; on the other hand, it solves the non-IID issues of data and limited resources in edge servers by FedProx. Experimental findings indicate that FedProx outperforms FedAvg, with a remarkable accuracy level of 89.4%, having higher convergence rates, and attaining a 30% saving on communication overhead through gradient compression. In addition, the ontology alignment procedure yielded a 95% success rate, thereby ensuring uniform data preprocessing across domains, including traffic monitoring and parking management. The model demonstrates outstanding scalability and flexibility to new devices, while maintaining high performance during ontology evolution. These findings highlight its great potential for deployment in smart cities, environmental monitoring, and other IoT-based ecosystems, thereby enabling the creation of more efficient and integrated solutions in these areas. Full article

Federated learning (FL) makes it possible for users to share trained models with one another, thereby removing the necessity of publicly centralizing training data. One of the best and most cost-effective ways to connect users is through email. To steal sensitive information, spam emails might trick users into visiting malicious websites or performing other fraudulent actions. The developed semantic parser creates email metadata datasets from multiple email corpuses and populates the email domain ontology to facilitate the privacy of the information contained in email messages. There is a new idea to make FL global models more resistant to Byzantine attacks. It involves accepting updates only from strong participants whose local model shows higher validation scores using benchmark datasets. The proposed approach integrates FL, the email domain-specific ontology, the semantic parser, and a collection of benchmark datasets from heterogeneous email corpuses. By giving meaning to the metadata of an email message, the email’s domain-specific ontology made it possible to create datasets for email benchmark corpuses and participant updates in a unified format with the same features. In order to avoid fraudulently modified client updates from being applied to the global model, the experimental results approved the proposed approach to strengthen the resiliency of an FL global model by utilizing client model benchmark validation. Full article

Air Traffic Management (ATM) has become complicated mainly due to the increase and variety of input information from Communication, Navigation, and Surveillance (CNS) systems as well as the proliferation of Unmanned Aerial Vehicles (UAVs) requiring Unmanned Aerial System Traffic Management (UTM). In response to the UTM challenge, a decision support system (DSS) has been developed to help ATM personnel and aircraft pilots cope with their heavy workloads and challenging airspace situations. The DSS provides airspace situational awareness (ASA) driven by knowledge representation and reasoning from an Avionics Analytics Ontology (AAO), which is an Artificial Intelligence (AI) database that augments humans’ mental processes by means of implementing AI cognition. Ontologies for avionics have also been of interest to the Federal Aviation Administration (FAA) Next Generation Air Transportation System (NextGen) and the Single European Sky ATM Research (SESAR) project, but they have yet to be received by practitioners and industry. This paper presents a decision-making computer tool to support ATM personnel and aviators in deciding on airspace situations. It details the AAO and the analytical AI foundations that support such an ontology. An application example and experimental test results from a UAV AAO (U-AAO) framework prototype are also presented. The AAO-based DSS can provide ASA from outdoor park-testing trials based on downscaled application scenarios that replicate takeoffs where drones play the role of different aircraft, i.e., where a drone represents an airplane that takes off and other drones represent AUVs flying around during the airplane’s takeoff. The resulting ASA is the output of an AI cognitive process, the inputs of which are the aircraft localization based on Automatic Dependent Surveillance–Broadcast (ADS-B) and the classification of airplanes and UAVs (both represented by drones), the proximity between aircraft, and the knowledge of potential hazards from airspace situations involving the aircraft. The ASA outcomes are shown to augment the human ability to make decisions. Full article

Artificial Intelligence (AI) and Deep Reinforcement Learning (DRL) have revolutionised e-learning by creating personalised, adaptive, and secure environments. However, challenges such as privacy, bias, and data limitations persist. E-FedCloud aims to address these issues by providing more agile, personalised, and secure e-learning experiences. This study introduces E-FedCloud, an AI-assisted, adaptive e-learning system that automates personalised recommendations and tracking, thereby enhancing student performance. It employs federated learning-based authentication to ensure secure and private access for both course instructors and students. Intelligent Software Agents (ISAs) evaluate weekly student engagement using the Shannon Entropy method, classifying students into either engaged or not-engaged clusters. E-FedCloud utilises weekly engagement status, demographic information, and an innovative DRL-based early warning system, specifically ID2QN, to predict the performance of not-engaged students. Based on these predictions, the system categorises students into three groups: risk of dropping out, risk of scoring lower in the final exam, and risk of failing the end exam. It employs a multi-disciplinary ontology graph and an attention-based capsule network for automated, personalised recommendations. The system also integrates performance tracking to enhance student engagement. Data are securely stored on a blockchain using the LWEA encryption method. Full article

Individual model verification is a common practice that increases the quality of design on the left side of the Vee model, often before costly builds and prototypes are implemented. However, verification that spans multiple models at higher levels of abstraction (e.g., subsystem, system, mission) is a complicated endeavor due to the federated nature of the data. This paper presents a tool-agnostic approach to higher-level verification tasks that incorporates tools from Semantic Web Technologies (SWTs) and graph theory more generally to enable a three-pronged verification approach to connected data. The methods presented herein use existing SWTs to characterize a verification approach using ontology-aligned data from both an open-world and closed-world perspective. General graph-based algorithms are then introduced to further explore structural aspects of portions of the graph. This verification approach enables a robust model-based verification on the left side of the Vee model to reduce risk and increase the visibility of the design and analysis work being performed by multidisciplinary teams. Full article

The significance of Linked Open Data datasets for traffic information extends beyond just including open traffic data. It incorporates links to other relevant thematic datasets available on the web. This enables federated queries across different data platforms from various countries and sectors, such as transport, geospatial, environmental, weather, and more. Businesses, researchers, national operators, administrators, and citizens at large can benefit from having dynamic traffic open data connected to heterogeneous datasets across Member States. This paper focuses on the development of a semantic model that enhances the basic service to access open traffic data through a LOD-enhanced Traffic Information System in alignment with the ITS Directive (2010/40/EU). The objective is not limited to just viewing or downloading data but also to improve the extraction of meaningful information and enable other types of services that are only achievable through LOD. By structuring the information using the RDF format meant for machines and employing SPARQL for querying, LOD allows for comprehensive and unified access to all datasets. Considering that the European standard DATEX II is widely used in many priority areas and services mentioned in the ITS Directive, LOD DATEX II was developed as a complementary approach to DATEX II XML. This facilitates the accessibility and comprehensibility of European traffic data and services. As part of this development, an ontological model called dtx_srti, based on the DATEX II Ontology, was created to support these efforts. Full article

The Arctic zone of the Russian Federation is of strategic importance for the country. Considering the fragility of Arctic ecosystems, special attention needs to be paid to the sustainable development of transport and related infrastructure within the framework of the “blue economy” concept, which is relevant for Arctic waters. At the same time, it is necessary to identify the main factors and tasks of creating transport and port infrastructure, building a modern fleet, and organizing fisheries and tourism in an environmentally sound manner. The purpose of the study is to consider the problems of anthropogenic influence for seaport facilities and to create a conceptual model of an environmental risk management system. The existing problems of Arctic ports and infrastructure are analyzed and existing business processes are considered, taking into account the peculiarities of their functioning in Arctic conditions. To systematize environmental assessments and establish dependencies between the main indicators describing the impact of port activities on elements of the natural environment, ontological domain engineering is proposed. It systematizes the basic terminology used within different subject areas of ecology and risks and allows one to visualize the relationships between elements of the natural environment, objects, port systems, their parameters and impact factors to assess the impact of the seaport on the natural environment. The results of ontological engineering (design and development of ontologies) in the field of risk management are presented. Future research will be aimed at developing the applied aspect of applying the results of ontological engineering in terms of specific engineering studies related to the assessment of anthropogenic load on the Arctic territory using simulation modeling. Full article

In recent years, educational institutions have worked hard to automate their work using more trending technologies that prove the success in supporting decision-making processes. Most of the decisions in educational institutions rely on rating the academic research profiles of their staff. An enormous amount of scholarly data is produced continuously by online libraries that contain data about publications, citations, and research activities. This kind of data can change the accuracy of the academic decisions, if linked with the local data of universities. The linked data technique in this study is applied to generate a link between university semantic data and a scientific knowledge graph, to enrich the local data and improve academic decisions. As a proof of concept, a case study was conducted to allocate the best academic staff to teach a course regarding their profile, including research records. Further, the resulting data are available to be reused in the future for different purposes in the academic domain. Finally, we compared the results of this link with previous work, as evidence of the accuracy of leveraging this technology to improve decisions within universities. Full article

Advanced technologies in modern industry collect massive volumes of data from a plethora of sources, such as processes, machines, components, and documents. This also applies to predictive maintenance. To provide access to these data in a standard and structured way, researchers and practitioners need to design and develop a semantic model of maintenance entities to build a reference ontology for maintenance. To date, there have been numerous studies combining the domain of predictive maintenance and ontology engineering. However, such earlier works, which focused on semantic interoperability to exchange data with standardized meanings, did not fully leverage the opportunities provided by data federation to elaborate these semantic technologies further. Therefore, in this paper, we fill this research gap by addressing interoperability in smart manufacturing and the issue of federating different data formats effectively by using semantic technologies in the context of maintenance. Furthermore, we introduce a semantic model in the form of an ontology for mapping relevant data. The proposed solution is validated and verified using an industrial implementation. Full article

The 2021 sales volume in the market of service robots is attractive. Expert reports from the International Federation of Robotics confirm 27 billion USD in total market share. Moreover, the number of new startups with the denomination of service robots nowadays constitutes 29% of the total amount of robotic companies recorded in the United States. Those data, among other similar figures, remark the need for formal development in the service robots area, including knowledge transfer and literature reviews. Furthermore, the COVID-19 spread accelerated business units and some research groups to invest time and effort into the field of service robotics. Therefore, this research work intends to contribute to the formalization of service robots as an area of robotics, presenting a systematic review of scientific literature. First, a definition of service robots according to fundamental ontology is provided, followed by a detailed review covering technological applications; state-of-the-art, commercial technology; and application cases indexed on the consulted databases. Full article

The UniProt Knowledgebase UniProtKB is a comprehensive, high-quality, and freely accessible resource of protein sequences and functional annotation that covers genomes and proteomes from tens of thousands of taxa, including a broad range of plants and microorganisms producing natural products of medical, nutritional, and agronomical interest. Here we describe work that enhances the utility of UniProtKB as a support for both the study of natural products and for their discovery. The foundation of this work is an improved representation of natural product metabolism in UniProtKB using Rhea, an expert-curated knowledgebase of biochemical reactions, that is built on the ChEBI (Chemical Entities of Biological Interest) ontology of small molecules. Knowledge of natural products and precursors is captured in ChEBI, enzyme-catalyzed reactions in Rhea, and enzymes in UniProtKB/Swiss-Prot, thereby linking chemical structure data directly to protein knowledge. We provide a practical demonstration of how users can search UniProtKB for protein knowledge relevant to natural products through interactive or programmatic queries using metabolite names and synonyms, chemical identifiers, chemical classes, and chemical structures and show how to federate UniProtKB with other data and knowledge resources and tools using semantic web technologies such as RDF and SPARQL. All UniProtKB data are freely available for download in a broad range of formats for users to further mine or exploit as an annotation source, to enrich other natural product datasets and databases. Full article