Imagine that you have a serious medical condition. Then imagine that when you visit a team of doctors, they could build an identical virtual ‘twin’ of the condition and simulate millions of ways to treat it until they develop an effective treatment. That is the vision of a team of scientists, led by Argonne National Laboratory.
Clinical trials are a critical tool for getting new treatments to people who need them, but research shows that difficulty finding the right volunteer subjects can undermine the effectiveness of these studies. Researchers designed and tested a new computerized solution that used artificial intelligence (AI) to effectively identify eligible subjects from Electronic Health Records (EHRs), allowing busy clinical staff to focus their limited time on evaluating the highest quality candidates
Research from Sandia National Laboratories is examining whether dragonfly-inspired computing could improve missile defense systems, which have the similar task of intercepting an object in flight, by making on-board computers smaller without sacrificing speed or accuracy.
A team of researchers led by Bill Tang of the US Department of Energy's (DOE's) Princeton Plasma Physics Laboratory (PPPL) and Princeton University recently tested its Fusion Recurrent Neural Network (FRNN) code, a novel artificial intelligence (AI) resource designed to predict plasma instabilities, on various high-performance computing (HPC) systems. A reliable way to predict and mitigate disruptions could accelerate the adoption of fusion as an environmentally friendly, virtually unlimited source of energy.
Inoviruses are filamentous viruses with small, single-stranded DNA genomes. Applying machine learning to more than 70,000 microbial and metagenome datasets, a team led by JGI scientists identified more than 10,000 inovirus-like sequences compared to the 56 previously known inovirus genomes.
Three teams who applied novel machine learning methods to successfully predict the timing of earthquakes from historic seismic data are splitting $50,000 in prize money from an open, online Kaggle competition hosted by Los Alamos National Laboratory and its partners.
NUS researchers have developed an ultra responsive and robust artificial nervous system for e-skins.
In a new publication in Nature, University of Utah chemists Jolene Reid and Matthew Sigman show how analyzing previously published chemical reaction data can predict how hypothetical reactions may proceed, narrowing the range of conditions chemists need to explore. Their algorithmic prediction process, which includes aspects of machine learning, can save valuable time and resources in chemical research.
Traffic signals serve to regulate the worst bottlenecks in highly populated areas but are not always very effective. Researchers at Penn State are hoping to use deep reinforcement learning to improve traffic signal efficiency in urban areas, thanks to a one-year, $22,443 Penn State Institute for CyberScience Seed Grant.
Rutgers researchers have created a device that can determine whether targeted chemotherapy drugs are working on individual cancer patients. The portable device, which uses artificial intelligence and biosensors, is up to 95.9 percent accurate in counting live cancer cells when they pass through electrodes, according to a study in the journal Microsystems & Nanoengineering.
Rehabilitation devices that conform to the body provide more than support for feeble or rigid muscles. With embedded AI, these 'exoskeletons' communicate with muscles when the brain cannot.
Robotics researchers at the University of California San Diego have for the first time used a commercial 3D printer to embed complex sensors inside robotic limbs and grippers. But they found that materials commercially available for 3D printing still need to be improved before the robots can be fully functional.
Value in Health, the official journal of ISPOR—the professional society for health economics and outcomes research, announced today the publication of a high-level overview of machine learning for healthcare outcomes researchers and decision makers.
Students at Rensselaer Polytechnic Institute in Troy, NY, will feel as if they are learning Chinese on the streets of Beijing this summer when an intelligent, immersive environment developed by Rensselaer and IBM Research is used in an academic credit-bearing course on campus for the first time.
HUMAN’s Diabetes DX products help to ease and improve both an early diagnosis of diabetes, but also better diabetes monitoring and management.
Scientists at Hokkaido University and Hiroshima University have found that green brittle stars with five arms show a different "pumping" movement pattern than those with six arms.
A team of Iowa State University graduate students brought home the top prize from the 20th annual Data Mining Cup, beating nearly 150 teams from 114 universities in 28 countries. The winners were announced July 3 in Berlin. The students developed a mathematical model to detect cases of fraud at self-checkouts in grocery stores.
A vegetable-picking robot that uses machine learning to identify and harvest a commonplace, but challenging, agricultural crop has been developed by engineers.
Did social media spoil the Avengers’ Endgame movie for you? Or maybe one of the Game of Thrones books? A team of researchers from the University of California San Diego is working to make sure that doesn’t happen again. They have developed an AI-based system that can flag spoilers in online reviews of books and TV shows.
Passenger and pedestrian confidence and acceptance will be key to the future and development of autonomous vehicles so researchers at WMG at the University of Warwick
University of Wisconsin-Madison engineers have devised a method to create pieces of “smart” glass that can recognize images without requiring any sensors or circuits or power sources.
Researchers at Lawrence Berkeley National Laboratory have shown that an algorithm with no training in materials science can scan the text of millions of papers and uncover new scientific knowledge. They collected 3.3 million abstracts of published materials science papers and fed them into an algorithm called Word2vec. By analyzing relationships between words the algorithm was able to predict discoveries of new thermoelectric materials years in advance and suggest as-yet unknown materials as candidates for thermoelectric materials.
New work from Los Alamos National Laboratory, the University of North Carolina at Chapel Hill, and the University of Florida is showing that artificial neural nets can be trained to encode quantum mechanical laws to describe the motions of molecules
New Cleveland Clinic-led research shows that artificial intelligence (AI) can use medical scans and health records to personalize the dose of radiation therapy used to treat cancer patients. Published today in The Lancet Digital Health, the research team developed an AI framework based on patient computerized tomography (CT) scans and electronic health records.
Capacitors, given their high energy output and recharging speed, could play a major role in powering the machines of the future, from electric cars to cell phones. However, the biggest hurdle for capacitors as energy storage devices is that they store much less energy than a similar-sized battery. Researchers at Georgia Institute of Technology are tackling that problem by using supercomputers and machine learning techniques to ultimately find ways to build more capable capacitors.
Many patients, especially those who are anesthetized or emotionally challenged, cannot communicate precisely about their pain.
Rutgers computer scientists used artificial intelligence to control a robotic arm that provides a more efficient way to pack boxes, saving businesses time and money.
A new study demonstrates, for the first time, that "social robots" used in support sessions held in pediatric units at hospitals can lead to more positive emotions in sick children.
Researchers have introduce supervised machine learning as a modern approach and new value-added complementary tool in cognitive brain health assessment and related patient care and management.
How do you determine the measurable “things” that describe the nature of our universe? To answer that question, researchers used CosmoFlow, a deep learning technique, running on a National Energy Research Scientific Computing Center supercomputer. They analyzed large, complex data sets from 3-D simulations of the distribution of matter to answer that question. The team showed that CosmoFlow offers a new platform to gain a deeper understanding of the universe.
With a recent award from the Defense Advanced Research Projects Agency, researchers from the Johns Hopkins University Applied Physics Laboratory (APL) in Laurel, Maryland, will develop a brain-machine interface that will enable the control of complex systems at the speed of thought.
UW researchers have developed a new tool to monitor people for cardiac arrest while they’re asleep — all without touching them. The tool is essentially an app for a smart speaker or a smartphone that allows it to detect the signature sounds of cardiac arrest and call for help.
Without being aware of it, people sometimes wrongly perceive tactile sensations. A new study in the scientific journal Current Biology shows how healthy people can sometimes misattribute touch to the wrong side of their body
With the assistance of artificial intelligence, researchers at Argonne are developing new ways to extract insights about the electric grid from mountains of data, with the goal of ensuring reliability and efficiency. The work combines Argonne's long-standing grid expertise with its advanced computing facilities and experts.
Citizens from the island of Aneityum in the Republic of Vanuatu are working with faculty from Binghamton University, State University of New York to test their true value as humans.
The integrated Translational Health Research Institute of Virginia (iTHRIV) has awarded funding to four multi-institutional research projects through the Pilot Translational and Clinical Studies Program.
Computer scientists from the University of California, Irvine are making a splash in the art world this year through their participation in Italy’s Venice Biennale, one of the oldest and most prestigious cultural festivals. The team – led by Alexandru Nicolau, UCI Distinguished Professor and chair of computer science, and Alexander Veidenbaum, UCI professor of computer science – collaborated with Israeli-Romanian artist Belu-Simion Fainaru to create three art installations for the event.
A team of NIBIB-funded bioengineers at Rennselaer Polytechnic Institute developed an AI technique to rapidly convert low-dose CT scans to superior images compared to a conventional technique. Low-dose CT minimizes x-ray radiation to a patient.
Machine learning has the potential to vastly advance medical imaging, particularly computerized tomography (CT) scanning, by reducing radiation exposure and improving image quality.
Research by neuroscientists at the University of Chicago shows how short-term, working memory uses networks of neurons differently depending on the complexity of the task at hand.
Harvard Medical School’s Media Fellowship program, now entering its 22nd year, is accepting applications for Fall 2019.
Below are summaries of recent Fred Hutch research, with links for additional background and media contacts.
Researchers at Columbia Engineering have developed a new technique based on reinforcement learning that trains a neural network model to correctly select the “best” reaction at each step of the retrosynthetic process. This form of AI provides a framework for researchers to design chemical syntheses that optimize user specified objectives such synthesis cost, safety, and sustainability. The new approach is more successful (by ~60%) than existing strategies for solving this challenging search problem.
Imagine for just a moment that your kettle could speak? What would it say? How would it feel? More importantly, what on earth would you ask it?
Sixty years ago, famous American economist Leonid Hurwicz did groundbreaking research about the economic mechanisms theory. Today, Darden expert is interested in designing mechanisms to solve big challenges like energy usage and traffic flows.
A tsunami of technology is about to change the way people live and work. In this introduction of the article collection Human Excellence in the Smart Machine Age, Professor Ed Hess explains what skills humans need to hone in order to meet the challenges of the near future.
Argonne researchers are transforming America's transportation and energy systems with machine learning, an iterative version of artificial intelligence.
The overpumping of groundwater in California has led to near environmental catastrophe in some areas – land is sinking, seawater is intruding, and groundwater storage capacity has shrunk. But researchers at Lawrence Berkeley National Laboratory believe machine learning could be part of the solution to restoring groundwater to sustainable levels and quality.
A team from Cornell University associate professor Max Zhang’s lab will work with the Environmental Protection Agency (EPA) over the next year on a machine learning model designed to predict fossil fuel emissions. The project was a winning entry in the EPA-sponsored EmPOWER Air Data Challenge.
RSS
Medicine keyboard_arrow_right
Sciencekeyboard_arrow_right
Life keyboard_arrow_right
Business keyboard_arrow_right
Journal News keyboard_arrow_right
By Location keyboard_arrow_right
Meetings, Grants, and Events keyboard_arrow_right