FUNDED PROJECTS
Enabling Product Safety and Sustainability Monitoring with Multimodal Knowledge Graphs (February 2026 – May 2026)
Team: Anelia Kurteva (PI), University of Birmingham, Boriana Rukanova, TU Delft (collaborator), Research Associate
Funded by the Ramsay Fund
Over the past decade, we have seen a drastic shift towards buying and selling products online (i.e. e-commerce), with supply and demand reaching unprecedented levels. This has put a significant burden on government agencies, such as Customs, who are responsible for ensuring the safety of thousands of products by examining their contents, origin, and value. There is a pressing need for more scalable digital solutions that help Customs monitor products’ safety and sustainability, especially considering the recently enforced Ecodesign for Sustainable Products Regulation (ESPR). This regulation mandates the provision of Digital Product Passports (DPPs) (i.e. a digital identity card for products, components, and materials), which is a step towards a solution. However, providing such DPPs, especially to Customs at scale to ease product safety and sustainability monitoring, necessitates a foundational digital infrastructure that can handle the sharing, integration and interpretation of large volumes of multimodal data (e.g. customs reports, images, metadata about products) as input and output of DPPs at scale.
Motivated by these challenges and based on past research of the PI on findable, accessible, interoperable, reusable (FAIR) DPPs, this project aims to investigate whether multimodal knowledge graphs (a more advanced types of graphs that can integrate multimodal data) can provide the necessary digital data infrastructure that enables product safety and sustainability monitoring.
Trustworthy Advisor for Future Flight (November 2025 – March 2026)
Confidential.
In collaboration with the British Standards Institute.
Investigating Multimodal Knowledge Graphs as Digital Twin Infrastructures for Financial Operations Risks (September – December 2025)
The team: Anelia Kurteva (PI), Nizar Al Ahmad (Research Associate), Industry collaborator (IRMAI)
Funder by UKFin+ Agile stream. Online info.
Financial operational risks cost the financial sector billions annually due to fragmented systems, operations, data and knowledge silos. As financial institutions face increasing complexity, cyber threats, and regulatory scrutiny, the need for dynamic, real-time risk modelling has never been more urgent.
IRMAI is a visionary start-up for AI-driven risk management, which is actively working on tackling these challenges via proactive risk automation, contextual intelligence, and compliance oversight. To realise its vision at scale, IRMAI is currently building an innovative AI-driven digital twin of financial operations to support risk management in dynamic financial ecosystems. However, a significant bottleneck actively slowing down IRMAI’s progress is the lack of a robust and trustworthy digital data infrastructure that their AI can rely on.In a reply to this urgency and informed by scientific literature, this project will investigate the utilisation of a multimodal knowledge graph (MMKG) as digital infrastructure to enable greater interoperability and efficient integration of financial operations data. The results of this will not only boost IRMAI’s developments but will also help to better understand the advantages and disadvantages of utilising a MMKG as a digital twin infrastructure for contextualising and operationalising financial operations risks.
Results:
Ontology for Financial Operations Risks
FAIR Data Hackathon (June 2026)
Funded by the Birmingham-Leiden Collaboration Fund
What motivated this event?
Preparing and using data for AI is complex and faces several socio-technical challenges related to data quality (ensuring data is clean, accurate, and free from errors or inconsistencies), dealing with bias, privacy and security (protecting sensitive information and complying with data privacy regulations) and the ethical implications of these. Enabling FAIR data through the utilisation of semantic technologies (e.g. ontologies and knowledge graphs) in research contributes to more responsible and sustainable data science and AI. Data becomes easily findable by machines and humans, accessiblethrough standardised protocols, its meaning in different contexts is easily interoperable and reusable across machines and humans. The provenance of the data and its quality can be more easily monitored, which takes us a step closer to more transparent AI. In high-risk AI application domains such as medicine and healthcare, such information becomes invaluable for supporting safer and more responsible AI development.
Who is this event for?
This high-impact interdisciplinary training hackathon is tailored for early and mid-stage researchers in computer science and domain experts in the social sciences interested in learning about the role of FAIR data in facilitating responsible technology development.
Beyond learning about the meaning and value of FAIR data, during the training sessions, we will discuss what FAIR means for data practices in AI, recent ideas on data visiting and data decentralisation, and how to effectively embed FAIR data in research proposals.
Venue Information
Date: 8th – 10th June 2026
Location: University of Leiden, The Netherlands (in person)
Organisers: Dr. Anelia Kurteva (University of Birmingham), Prof. Mirjam van Reisen (University of Leiden)
Workshop on Mechanisms for Governing Responsible AI (August 2025)
Funded by the National Institute for Informatics (NII), Tokyo, Japan
OTHER (INVOLVED AS A RESEARCHER)
Circular Resource Planning for IT (RePlanIT)(2022-2024)
The aim of the project is to develop and test a new methodology, Circular Resource Planning for IT. It should enable suppliers and users of IT services to manage their hardware in a circular way. In practice this means: double the lifetime of the equipment, slowing down replacement cycles, while running the hardware on maximum energy efficiency. The result of the project is, firstly, a prototype of the RePlanIT system that is developed and validated in practical real-life environments in the municipality of Amsterdam and other big IT consumers in the business market. Secondly, with the research into preconditions for trust, behavior, and acceptance of circular IT, the project provides insight into how to include stakeholders so that they actually make circular choices.
Results:
Ontology: Digital Product Passports of ICT
Kurteva, A., McMahon, K., Bozzon, A. and Balkenende, R., 2024. Semantic Web and its role in facilitating ICT data sharing for the circular economy: An ontology survey. Semantic Web, 15(5), pp.2035-2067.
Kurteva, A., van der Valk, C., McMahon, K., Bozzon, A. and Balkenende, R., 2024. RePlanIT ontology for FAIR digital product passports of ICT: Laptops and data servers. Semantic Web journal.
Chirvasuta, T., Kurteva, A., Hofman, W., Rukanova, B. and Tan, Y.H., 2025, March. Aligning the FEDeRATED Upper Ontology with Battery and Electronics Ontologies to Aid Circular Economy Monitoring in Practice. In Future of Information and Communication Conference (pp. 44-61). Cham: Springer Nature Switzerland.
Smart Dispatcher for Secure and Controlled Sharing of Distributed Personal and Industrial Data (smashHit)(2020-2022)
The objective of smashHit is to assure trusted and secure sharing of data streams from both personal and industrial platforms, needed to build sectorial and cross-sectorial services, by establishing a GDPR-compliant framework for processing of data owner consent and legal rules and effective contracting, as well as joint security and privacy preserving mechanisms.
Results:
Chhetri, T.R., Kurteva, A., DeLong, R.J., Hilscher, R., Korte, K. and Fensel, A., 2022. Data protection by design tool for automated GDPR compliance verification based on semantically modeled informed consent. Sensors, 22(7), p.2763.
Kurteva, A., Chhetri, T.R., Pandit, H.J. and Fensel, A., 2024. Consent through the lens of semantics: State of the art survey and best practices. Semantic Web, 15(3), pp.647-673.
Rasmusen, S.C., Penz, M., Widauer, S., Nako, P., Kurteva, A., Roa-Valverde, A. and Fensel, A., 2022. Raising consent awareness with gamification and knowledge graphs: an automotive use case. International Journal on Semantic Web and Information Systems (IJSWIS), 18(1), pp.1-21.
Tauqeer, A., Kurteva, A., Chhetri, T.R., Ahmeti, A. and Fensel, A., 2022. Automated GDPR contract compliance verification using knowledge graphs. Information, 13(10), p.447.
Bless, C., Dötlinger, L., Kaltschmid, M., Reiter, M., Kurteva, A., Roa-Valverde, A.J. and Fensel, A., 2021. Raising awareness of data sharing consent through knowledge graph visualisation. In Further with Knowledge Graphs (pp. 44-57). IOS Press.
Kurteva, A., Chhetri, T.R., Tauqeer, A., Hilscher, R., Fensel, A., Nagorny, K., Correia, A., Zilverberg, A., Schestakov, S., Funke, T. and Demidova, E., 2023. The smashHitCore ontology for GDPR-compliant sensor data sharing in smart cities. Sensors, 23(13), p.6188.
Bushati, G., Rasmusen, S.C., Kurteva, A., Vats, A., Nako, P. and Fensel, A., 2024. What is in your cookie box? Explaining ingredients of web cookies with knowledge graphs. Semantic Web, 15(5), pp.1593-1609
Ontologies: smashHitCore, OntoCookie
CampaNEO (2019-2024)
In the CampaNeo project, an open platform will be developed on which private and public institutions can create campaigns and collect and analyze vehicle data in real time. The goal is to set up a prototype platform for secure campaign-based data collection in Hanover, Wolfsburg and in cross-regional scenarios, as well as the implementation of the first smart use cases based on the campaign data. The focus is in particular on the data ownerships of vehicle owners and the traceability of data processing. The analysis of vehicle sensor data (e.g. for the detection of driving behaviour, finding of driver efficiency scores, anomaly detection, etc.) requires the creation and use of models of machine learning (ML).
Dr. Anelia Kurteva 