News

Researchers from the University of Copenhagen and Rigshospitalet have used data on more than 230,000 intensive care patients to develop a new algorithm. Among other things, it uses disease history from the past 23 years to predict patients' chances of survival in intensive care units.

A new University of California, Irvine-led pilot study finds that crowdsourced "crash alerts" occur three minutes prior to their corresponding California Highway Patrol (CHP)-reported crash, suggesting that using these data could mean the difference between life and death.

Virtual reality (VR) can identify early Alzheimer's disease more accurately than "gold standard" cognitive tests currently in use, suggests new research from the University of Cambridge.

Scientists have found that dozens of genes, previously thought to have similar roles across different organisms, are in fact unique to humans and could help explain how our species came to exist.

Leveraging artificial intelligence techniques, researchers have demonstrated that mutations in so-called 'junk' DNA can cause autism.

Researchers have achieved material magnetization switching on the shortest timescales, at a minimal energy cost, thus creating a prototype of energy-efficient data storage devices.

The app sends sound waves into the ear and measures how the sound waves change as they bounce off the eardrum. Different sounds reflect the amount of fluid build-up, which occurs during ear infections – the most common reason for parents bringing their children to a pediatrician.

Octopus “suckers" are the inspiration for the development of a new graphene-based adhesive biosensor that could prove more robust than previous technology.

Archaeology researchers are benefitting from the University’s first high performance computing (HPC) system. Revolutionising the capacity for data collation, the HPC cluster enables the archaeological team to effectively preserve endangered or destroyed heritage across the world, the Temple of Bel in Palmyra, Kathmandu and Notre Dame.

North Carolina State University researchers have developed a new framework for building deep neural networks via grammar-guided network generators. In experimental testing, the new networks - called AOGNets - have outperformed existing state-of-the-art frameworks, including the widely-used ResNet and DenseNet systems, in visual recognition tasks.