果冻传媒 secures three AI Research Grants from NGF AINED XS Europe
We are pleased to announce that three 果冻传媒 research projects have received grants from the NGF AINED XS Europe initiative. These grants support innovative and high-risk ideas in artificial intelligence (AI). The projects cover various applications, including AI in robotics, better MRI results, and underwater satellite communication. Each project is done in collaboration with a European partner.
Congratulations to all recipients of these grants!
Awarded Projects
- AI-SUSAT: Led by Dr. Y.C.G. G眉ltekin, this project focuses on secure communication between satellites and submarines using AI to improve signal processing.
- CONTACT-AI: Led by Dr. W.M. Kouw, this project aims to help walking robots navigate by touch when vision is unclear, using new AI techniques.
- QP-GPT: Led by Dr. C.M. Scannell, this project uses AI to improve MRI scans by modeling blood flow, helping doctors make better decisions.
About the Call
In 2024, the AiNed Foundation collaborated to create this call, resulting in 40 projects. Nearly 鈧�800,000 was distributed in this final round. The focus was on adventurous research and exploring new AI ideas. The goal is to advance science, whether the results are positive or negative.
About the National Growth Fund Program AiNed
This call is part of the National Growth Fund program AiNed, which promotes AI development in Dutch companies and governments. The program received 鈧�204.5 million in 2021 and will be part of the AI Coalition for the Netherlands from 2025.
Programs for the National Growth Fund
NWO runs programs funded by the National Growth Fund, supporting research and innovation. These programs help improve the economy and well-being in the Netherlands through collaboration between public and private sectors.
AI-SUSAT: Artificial Intelligence for Secure Underwater and SATellite Communications
Led by Dr. Y.C.G. G眉ltekin of the department of Electrical Engineering.
Reliable communication networks that connect national and regional entities are crucial for the safety of their citizens. An important aspect of these networks is communication with submarines. Satellite-to-underwater laser communication is therefore vital in the next generation of space networks. Due to the challenging nature of propagation through the atmosphere and saltwater, traditional signal processing algorithms cannot support satellite-to-underwater laser links.
This project will develop data-driven algorithms to predict channel conditions and optimize laser signals. These algorithms will be the first to connect submarines with the mainland and complement global space communication networks.
CONTACT-AI: CONTact in ACTion through Active Inference
Led by Dr. W.M. Kouw of the department of Electrical Engineering.
Physical interaction with the real world is a significant challenge in AI. CONTACT-AI explores new probabilistic techniques, based on computational neuroscience, to enable walking robots to explore by touch when vision provides unclear information. Explainable models are used to allow an intelligent robot to switch between walking and dynamic interactions with obstacles.
The intended implementation (Bayesian machine learning via information flows on factor graphs) is computationally efficient enough to run on small micro-computers onboard the robot. CONTACT-AI provides methods for embodied AI systems that improve the market for walking robots in terms of robustness and autonomy.
QP-GPT: A Foundation Model for Quantitative Perfusion MRI
Led by Dr. C.M. Scannell of the department of Biomedical Engineering.
This project focuses on the crucial role of blood flow, or perfusion, in clinical decision-making. The aim is to use AI to model perfusion in MRI scans instead of relying on the subjective interpretation of doctors. It enhances the training of AI models for quantifying perfusion by creating a foundation model that can quickly adapt to specific patient data.
This approach makes better use of large datasets without expert annotations and integrates physical laws, resulting in faster and more reliable decisions for patients.