Search systems are integral to accessing the world’s information. This project will research whether search systems can learn user preferences from their interactions, while being aware of the uncertainty in their predictions. The result will be a Bayesian inference framework that can inform a search system about what users are probably looking for, such that the system can automatically adapt itself to better match user preferences.
Project members: Harrie Oosterhuis, Oscar Ramirez Milian
End date: 31 July 2027
Funded by: NWO VENI
Internal project number: 62004855
https://www.nwo.nl/en/researchprogrammes/nwo-talent-programme/projects-veni/veni-2022
Health data is becoming available more easily and quickly, both to people using the applications and to health (care) professionals and researchers. The ability to connect all this data - both in terms of types of data and over longer periods of time, generated by patients as well as healthcare providers and researchers - enables innovative, powerful AI-based analytics that improve the effectiveness of research findings to support health (care) decisions. To reach this potential, we aim to solve several challenges to enable our researchers and staff to offer innovative healthcare solutions, based on sound AI models fed by reliable datasets embedded in a data-driven profesional infrastructure.
Project members: Johannes Textor, Gabriel Bucur, Franka Buytenhuijs, Tom Heskes
End date: 31 December 2027
Funded by: The Reinier Post Foundation
Internal project number: 62004606, 69000085
Most people think of cells as static, but cell movement is crucial in health and disease. For example, immune cells defending us against viruses or cancer critically rely on motion as they navigate the maze of tissues in the human body, interact and communicate with other cells, search for signs of anomalies, and swarm to sites of infection. Special microscopes can record these processes in time-lapse images that are rich in information but limited in the amount of (annotated) data for any given application. As a result, most existing AI techniques are not directly applicable to new data and — as of yet — no robust methods exist to decode these time-lapse images and zoom in on the where, when, and how of key immunological events. In this project, we combine AI with simulations to overcome the current impasse in exploiting cell movement data.
Project members: Inge Wortel, Lin Wouters, Koert Schreurs, David Cicchetti
End date: 30 November 2028
Funded by: NWO, NGF AiNed Fellowship, grant number NGF.1607.22.020
Internal project number: 62004685
https://www.nwo.nl/en/news/ained-fellowship-grant-for-dr-inge-wortel
OpenWebSearch.EU is a Horizon Europe project to develop and pilot the core for a European Open Web Index (OWI) and the foundation of an open and extensible European Open Web Search and Analysis Infrastructure (OWSAI) by bringing together strong European players, who jointly define, develop and pilot an open technological backbone for cooperative web search. The proposed pilot infrastructure will demonstrate, how search applications and web-based AI data products can be realized through cooperative crawling, analysis, storing and indexing of web content. The project will demonstrate the feasibility and potential of an open European web index and how it stimulates a competitive web search and web data product market. Therefore, the pilot aims to reach a technology readiness level (TRL) of 5.
Project members: Arjen de Vries, Djoerd Hiemstra, Gijs Hendriksen, Daria Alexander
End date: 31 August 2025
Funded by: EU Horizon under grant agreement no. 101070014.
Internal project number: 62004307
The PersOn project aims to develop explainable, maintainable, and trustworthy decision support systems for Personalised Care in Oncology. Our focus is on combining modern causal methodologies and explainable AI techniques to help patients make better informed decisions on impact and consequences of various available treatment alternatives for cancer, that are tailored to their own personal needs and circumstances.
Project members: Tom Claassen, Moabi Mokhoro
End date: 29 February 2028
Funded by: NWO-TTW (Perspectief 2021-2022)
Internal project number: 62005037
https://www.personalisedcareinoncology.nl
Like our brain, our immune system can learn. The researchers will build computer models of the immune system and train these to recognize text and images to understand how the system learns, forgets, and gets confused. This will help to design therapies that use the immune system, such as vaccines.
Project members: Johannes Textor, Franka Buytenhuijs, Gijs Schröder, Ankur Ankan
End date: 30 June 2025
Funded by: NWO Vidi, grant number 192.084
Internal project number: 62004035
https://www.nwo.nl/en/projects/vividi192084
T cells are important to the immune system and can work together in large groups. They are constantly on the move and can enter most tissues. Activated T cells divide and gather in tissues to respond to pathogens or cancer cells. Despite often being in dense environments, such as lymphatic tissue, T cells can move smoothly. However, it is not clear how they do this because research on T-cell movement has mainly focused on individual cells and not crowd effects. We aim to understand the mechanisms that allow smooth movement of tightly packed T cells and in what situations T-cell movement can still be disrupted by emerging adverse crowding. Particularly, this can be relevant aberrant tissue environments such as tumors, where reduced crowd action of T cells is likely to occur. Our multidiscpiplinary, international team uses computer simulations (Textor), experiments (Mandl), and biophysical theories (Parisi). (Translated with DeepL.com free version)
Project members: Johannes Textor, Jan Schering
Collaborators: Judith Mandl (McGill), Daniel Parisi (ITBA, Argentina)
End date: 1 December 2024
Funded by: Human Frontiers Science Program (HFSP), Grant RGP0053.2020
Internal project number: 62004090
https://www.radboudumc.nl/en/news/2020/hfsp-grant-for-johannes-textor
Salivary gland cancer is a rare type of head-and-neck cancer with 150-200 diagnoses per year in the Netherlands, and the most aggressive subtypes have poor prognosis. To develop new treatment options, we are imaging the interactions between immune system cells and tumor cells within patient biopsies using high-resolution digital microscopy. Machine learning approaches are the state of the art for analyzing such data, but they can require very large datasets to train on, which are usually not available for rare cancer types. In our project, we will address this problem using 'transfer learning' methodology that allows machine learning algorithms to benefit from experience gained on larger datasets from more common cancer types and train more effectively on smaller datasets. Leveraging existing data and knowledge in this manner, we hope that our project will help to build a rationale for future immunotherapy treatments for salivary gland caner patients.
Project members: Johannes Textor, Evgenia Martynova
End date: 1 July 2025
Funded by: Hanarth Foundation
https://www.hanarthfonds.nl/nl/gehonoreerde-aanvragen/2020-call/johannes-textor
LESSEN aims to make the chat technology accessible for languages and domains with relatively little training data and compute power. It focuses on developing data and compute efficient chat algorithms that can make optimal use of data and offer safe and transparent task-oriented conversational agents. Dr. Hasibi receives 500K funding and works on augmenting conversational training data and developing algorithms that enrich data-hungry models with rich structured information stored in Knowledge Graphs. The consortium is led by Prof. Maarten de Rijke (UvA) and consists of University of Amsterdam, Leiden University, University of Groningen, Amsterdam University of Applied Sciences, Radboud University, Achmea, Albert Heijn, Bol.com, KPN, Rasa Technologies, Ahold Delhaize, and National police force.
Project members: Faegheh Hasibi, Heydar Soudani, Mohanna Hoveyda
End date: 31 December 2027
Funded by: NWO / NWA_ORC under project number NWA.1389.20.183
Internal project number: 62004372
When chickens in a farm become infected or have parasites, specific odours are produced. A cross-disciplinary team will combine innovative sensors, affinity layers, and machine learning to develop and test an electronic nose. This sensitive system can recognize a fingerprint of Volatile Organic Compounds and thus recognise specific diseases at an early stage, when (preventive) measures are most effective. In this project, veterinary health, industry, science professionals and societal organisations will collaborate towards developing a practically applicable poultry health monitoring system to improve chicken and public health, general welfare and reduce antibiotics/chemicals use and the environmental impact of livestock farming.
Project members: Roel Bouman, Yuliya Shapovalova, Tom Heskes
End date: 31 August 2028
Funded by: NWO / NWA_ORC under project number NWA.1389.20.123
Internal project number: 62004547
https://www.nwo.nl/en/projects/nwa138920123
For industries like agrofood, paper industry and specialty chemicals, some 40-80% of the CO2 emissions is related to the energy that is needed for heat-driven processes like separation and drying. ‘The heat is on’ focuses on heat integration, a balancing act between heat generation and use/reuse. Due to the magnitude of energy consumption, a small change to achieve more energy efficiency in one part of the process, can have substantial effects. The process optimization is realized by making use of digital twins.
Project members: Olivier Claessen, Tom Heskes, Thanh Tran
End date: 31 August 2025
Funded by: RVO Missiegedreven Onderzoek, Ontwikkeling en Innovatie (MOOI)
Internal project number: 62004058
The CORTEX consortium of 12 partners from academia, industry and society will make self-learning machines faster, to figure out how massive cosmic explosions work, and to innovative systems that benefit our society. RU will contribute to this project by developing new machine-learning algorithms for gravitational wave detection.
Project members: Alex Kolmus, Twan van Laarhoven, Tom Heskes
End date: 30 November 2025
Funded by: NWO / NWA under project number 1160.18.316
Internal project number: 62003560
https://www.astron.nl/index.php/news-and-events/news/self-learning-machines-hunt-explosions-universe
No more train delays, power outages, or failure of production machines? The PrimaVera project, funded by the Dutch National Research Agenda (NWA), represents a major step towards this goal. With predictive maintenance, or just-in-time maintenance (maintenance just before a system breaks down), the reliability of infrastructure and production resources can be increased and the costs of maintenance can be reduced.
Existing predictive maintenance techniques only work for small-scale systems and are difficult to scale up. Choices made in one place in the chain have an important influence on other processes in the chain. The choice of a certain type of sensors and measurements influences the type of predictions that can be made, and therefore also the quality of the predictions. That is why cross-level optimization methods are being developed within PrimaVera.
Project members: Roel Bouman, Tom Heskes
End date: 31 October 2025
Funded by: NWO / NWA under project number 1160.18.238
Internal project number: 62003689
https://primavera-project.com/
The objective of the 6-year project MOCIA is to develop and validate AI algorithms for identifying non-invasive modifiable risk and protective factors and for designing scoring tools to quantify risk of cognitive decline.
Project members: Elena Marchiori, Wieske de Swart, Jesse Krijthe, 1 PostDoc, 1 PhD candidate
End date: 31 August 2027
Funded by: NWO Crossover programme, project number 17611
Internal project number: 62003671
http://www.cs.ru.nl/~elenam/mocia.html
This project AVIATOR aims to provide a step change in resolution and speed of visual inspection in large-scale safety critical composite structures such as airplanes by creating novel autonomous UAVs with combined vision and tactile capacities and use of advanced artificial algorithms. Currently, visual inspection is conducted by skilled operators, allowing room for human errors, and health and safety (H&S) concerns. AVIATOR will remove humans from the loop, and increase the productivity, reliability, and resolution of inspection, reducing the costs and downtime associated with inspection, and reducing the H&S risks of difficult to access locations.
Project members: Elena Marchiori
End date: 30 April 2028
Funded by: NWO 20430
Internal project number: 62004703
https://www.nwo.nl/en/projects/20430
The main goal of the AI-CODE project is to evolve state-of-the-art research results (tools, technologies, and know-how) from the past and ongoing EU-funded research projects focused on disinformation to a novel ecosystem of services that will proactively support media professionals in trusted information production through AI. First, the project aims to identify, analyse, and understand future developments of next-generation social media in the context of rapid development of generative Artificial Intelligence and how such a combination can impact the (dis)information space. Second, the project aims to provide media professionals with novel AI-based services to coach them how to work in emerging digital environments and how to utilise generative AI effectively and credibly, to detect new forms of content manipulation, as well as to assess the reputation and credibility of sources and their content.
Project members: Martha Larson, Randi Cecchine, Ilona Wilmont
End date: 30 November 2026
Funded by: EU Horizon
Internal project number: 62004936
https://cordis.europa.eu/project/id/101135437
The ongoing digitalization is transforming all aspects of life, necessitating a balance between leveraging technological advancements and addressing global climate and environmental crises while upholding human values. Addressing these challenges requires an integrated approach combining AI, software, and emerging technologies such as quantum and neuromorphic computing, along with considerations for safety, security, energy efficiency, and ethical standards. A COMET centre bridges research with industrial applications, offering sustainable solutions through an integrated software and AI engineering cycle that includes data and AI modeling, software evolution, and compliance with standards and regulations. The research agenda focuses on leveraging emerging computing technologies to solve complex problems, developing personalized AI systems, advancing no-code and low-code software engineering, and ensuring compliance with standards. The centre’s expertise and successful projects support these research activities and facilitate continuous knowledge and technology transfer to its partners.
RU contributes as a partner in this project through the exchange of research on, mainly, anomaly detection and physics-informed neural networks.
Project members: Janneke Verbeek, Olivier Claessen, Roel Bouman, Yuliya Shapovalova, Tom Heskes
End date: 31 December 2026
Funded by: COMET
Internal project number: 62004841
The AI for Energy Grids Lab is focused on developing methods and tools that use grid data to improve the efficiency, sustainability, and reliability of the medium-low voltage grid. It combines the expertise of Alliander data scientists, electrical engineers, and the latest digitalization programs for grid data, with academic expertise on methods from artificial intelligence. The lab’s collaboration network includes all Dutch Distribution system operators, as well as academic institutions such as Delft University of Technology, Radboud University, and the University of Twente.
The RU contributes through research on graph neural networks for evaluating the reliability of electricity grids.
Project members: Charlotte Cambier van Nooten, Yuliya Shapovalova, Tom Heskes
End date: 31 December 2027
Funded by: NWO ROBUST
Internal project number: 62004863
https://www.ru.nl/en/research/research-news/robust-ai-programme-receives-additional-eu25-million-in-funding-from-dutch-research-council https://www.icai.ai/labs/ai-for-energy-grids-lab