Researchers at the University of Copenhagen have developed a prototype of an app that may potentially prescribe the optimal dose of medicine for the individual patient, as well as prevent counterfeit products.
A team of Australian researchers has designed a reliable strategy for testing physical abilities of humanoid robots. Using a blend of machine learning methods and algorithms, the research team succeeded in enabling test robots to effectively react to unknown changes in the simulated environment, improving their odds of functioning in the real world. The findings have promising implications in the broad use of humanoid robots in fields such as healthcare, education, disaster response and entertainment.
By combining cutting-edge machine learning with 19th-century mathematics, a Worcester Polytechnic Institute (WPI) mathematician is working to make NASA spacecraft lighter and more damage tolerant by developing methods to detect imperfections in carbon nanomaterials used to make composite rocket fuel tanks and other spacecraft structures.
CSHL neuroscientist Anthony Zador shows how evolution and animal brains can be a rich source of inspiration for machine learning, especially to help AI tackle some enormously difficult problems, like doing the dishes.
Researchers at Binghamton University, State University of New York researchers have found a way to improve the performance of tiny sensors that could have wide-reaching implications for electronic devices we use every day.
He solved a 127-year-old physics problem on paper and proved that off-centred boat wakes could exist. Five years later, laboratory experiments proved him right.
Researchers at the UW have used machine learning to develop a new system that can monitor factory and warehouse workers and tell them how ergonomic their jobs are in real time.
Empa has developed an innovative, electrohydraulically actuated valve train for internal combustion engines, that enables completely free adjustment of stroke and timing, while at the same time being robust and cost effective. This valve train was mounted on a serial production engine and has been running successfully for several months. The new technology saves up to 20% fuel.
Lithium fluoride crystals have recently been used to register the tracks of nuclear particles. Physicists from the Institute of Nuclear Physics of the Polish Academy of Sciences in Cracow have just demonstrated that these crystals are also ideal for detecting tracks of high-energy ions of elements even as heavy as iron.
Harvard researchers have developed a new DNA-nanotechnology-based approach called Immuno-SABER, that combines the protein targeting specificity of commonly available antibodies with a DNA-based signal-amplification strategy that enables the highly multiplexed visualization of many proteins in the same sample with pre-programmable and tunable fluorescence signals at each target site.