NEWS FEEDS
Select a tab to change feeds.
- Science Daily
- Interesting Engineering
Researchers have developed a powerful AI tool, built on the same transformer architecture used by large language models like ChatGPT, to process an entire night's sleep. To date, it is one of the largest studies, analyzing 1,011,192 hours of sleep. The model, called patch foundational transformer for sleep (PFTSleep), analyzes brain waves, muscle activity, heart rate, and breathing patterns to classify sleep stages more effectively than traditional methods, streamlining sleep analysis, reducing variability, and supporting future clinical tools to detect sleep disorders and other health risks.
Researchers have experimentally recreated another fundamental theoretical model from quantum physics, which goes back to the Nobel Prize laureate Werner Heisenberg. The basis for the successful experiment is made of tiny carbon molecules known as nanographenes. This synthetic bottom-up approach enables versatile experimental research into quantum technologies, which could one day help drive breakthroughs in the field.
Researchers have developed an AI-based learning system that recognizes strengths and weaknesses in mathematics by tracking eye movements with a webcam to generate problem-solving hints. This enables teachers to provide significantly more children with individualized support.
AI models often rely on 'spurious correlations,' making decisions based on unimportant and potentially misleading information. Researchers have now discovered these learned spurious correlations can be traced to a very small subset of the training data and have demonstrated a technique that overcomes the problem.
A team of researchers created Morpho, an open-source programmable environment that enables researchers and engineers to conduct shape optimization and design for soft materials. Applications can be for anything from artificial hearts to robot materials that mimic flesh and soft tissue.
A team unveils a versatile large language model to enhance perioperative care.
Engineers have developed a new computational approach to accurately model and predict the properties of a class of magnetic molecules called chiral helimagnets. Their work could accelerate the discovery of new materials for spintronics technologies.
An engineering student refined a century-old math problem into a simpler, more elegant form, making it easier to use and explore. Divya Tyagi's work expands research in aerodynamics, unlocking new possibilities in wind turbine design that Hermann Glauert, a British aerodynamicist and the original author, did not consider.
Researchers have developed a new technique that predicts nuclear properties in record detail. The study revealed how the structure of a nucleus relates to the force that holds it together. This understanding could advance efforts in quantum physics and across a variety of sectors, from to energy production to national security.
Researchers have developed a generative AI tool that mimics scientists to support and speed up the process of scientific discoveries.
