AI and human-movement research intersect in a study that enables precise estimation of hand muscle activity from standard video recordings. Using a deep-learning framework trained on a large, comprehensive multimodal dataset from professional pianists, the researchers introduce a system that accurately reconstructs muscle activation patterns without sensors. This advancement provides a low-cost, non-invasive method for analyzing fine motor control, optimizing rehabilitation strategies, enhancing performance training, and informing future developments in human-machine interaction.

In an increasingly acute surgeon shortage, artificial intelligence could help fill the gap, coaching medical students as they practice surgical techniques.

A new tool, trained on videos of expert surgeons at work, offers students real-time personalized advice as they practice suturing. Initial trials suggest AI can be a powerful substitute teacher for more experienced students.

Europe, 18.11.2025 - As Europe faces the dual challenge of ensuring food security and environmental sustainability, a new CBE JU-funded research project aims to deliver more resource-efficient food, agriculture, and aquafeed products from microalgae. The ALLIANCE project will optimise microalgae cultivation and processing to reduce costs, resource input, and waste, expanding consumer access to sustainable and affordable microalgae-based products. 

Electrochemists Rutha Jäger of the University of Tartu and Eneli Härk of the Helmholtz-Zentrum Berlin mapped the atomic structure of this iron-nitrogen-carbon catalyst, demonstrating how it might compete with costly precious metals in fuel cell technology. The article “Small-Angle X-ray Scattering Monitoring of Porosity Evolution in Iron–Nitrogen–Carbon Electrocatalysts” was published in ACS Nano, a ranked in the top 5 in the Nanoscience & Nanotechnology and the Multidisciplinary Materials Science.

A team of researchers has built one of the most detailed open maps of emerging technologies yet assembled, allowing governments, companies and investors in the United States and worldwide to see what sits inside big fields like artificial intelligence and quantum computing, how fast each technology is growing and how deeply it is rooted in science.

Deciphering true active sites under identical mass transport conditions is crucial for understanding catalytic mechanisms. By establishing uniform mass transfer and implementing controlled experiments to eliminate interfering factors, the research team identified Cu(100) grain boundaries as the key sites driving efficient C₂₊ production. Advanced characterization and theoretical calculations confirmed these sites facilitate asymmetric C–C coupling between *CHO and *CO intermediates, providing critical insights for rational catalyst design.

Co atoms are uniformly incorporated in NiS nanoparticles to fabricate homogeneous NiCoS cocatalyst on TiO₂ surface by a facile photosynthesis strategy. The optimized NiCoS/TiO₂(1:2) photocatalyst display the highest H₂ production performance, outperforming the NiS/TiO₂ and CoS/TiO₂ samples. The incorporated Co atoms break the electron distribution symmetry in NiS, thus essentially increasing electron density of S atoms to weaken S-H_ad bonds for efficient H_ad adsorption and desorption, endowing the NiCoS cocatalysts with a highly active H₂ evolution process. The integrated homogeneous NiCoS nanoparticles with TiO₂ could rapidly transfer photogenerated electrons and efficiently facilitate the interfacial H₂ evolution process, thus achieving enhanced photocatalytic H₂ generation activity.