English
Arabic
Chinese (Simplified)
Dutch
Esperanto
French
German
Greek
Italian
Japanese
Korean
Portuguese
Russian
Spanish
UrduScientists built a machine learning model that can rapidly predict how atoms absorb x-rays for materials science research.
Tag: Machine Learning
Supercomputer Simulations Help Researchers Predict Solar Wind Storms
Researchers at the University of New Hampshire used SDSC’s Comet supercomputer to validate a model using a machine learning technique called Dynamic Time Lag Regression (DTLR) to help predict the solar wind arrival near the Earth’s orbit from physical parameters of the Sun.
Artificial intelligence identifies, locates seizures in real-time
Research from the McKelvey School of Engineering at Washington University in St. Louis has shown that understanding brain activity as a network instead of readings from an EEG allow for more accurate and efficient detection of seizures in real-time.
Researchers use machine learning to build COVID-19 predictions
Researchers at Binghamton University, State University of New York are using machine learning to track the coronavirus and predict where it might surge next.
Neural network can determine lung cancer severity
NIBIB-funded researchers at Stanford University have created an artificial neural network that analyzes lung CT scans to provide information about lung cancer severity that can guide treatment options.
Six Argonne researchers receive DOE Early Career Research Program awards
Argonne scientists Michael Bishof, Maria Chan, Marco Govini, Alessandro Lovato, Bogdan Nicolae and Stefan Wild have received funding for their research as part of DOE’s Early Career Research Program.
Machine Learning Has a Flaw. It’s Gullible
Potential biases that limit the effectiveness of machine learning process technologies and the scope for human capital to be complementary in reducing such biases is explored by Rajshree Agarwal and Evan Starr at the University of Maryland’s Robert H. Smith…
Predicting Side Effects
At a glance:
• Scientists develop AI-based tool to predict adverse drug events
• Such events are responsible for some 2 million U.S. hospitalizations per year
• The free, open-source system could enable safer drug design, optimize drug safety
New imaging method tracks brain’s elusive networks
Understanding the source and network of signals as the brain functions is a central goal of brain research. Now, Carnegie Mellon engineers have created a system for high-density EEG imaging of the origin and path of normal and abnormal brain signals.
Argonne to collaborate with Raytheon Technologies to accelerate aircraft engine design
This new agreement will dramatically improve and reduce the computational expense of fluid dynamics models. Both partners aim to improve the design and durability of engine components.
ISPOR Short Course Program Now Offered Virtually
ISPOR—The Professional Society for Health Economics and Outcomes Research (HEOR) announced that its HEOR Short Course Program is now being offered virtually with 9 upcoming short courses in June and July.
RENEWABLE ENERGY ADVANCE
In order to identify materials that can improve storage technologies for fuel cells and batteries, you need to be able to visualize the actual three-dimensional structure of a particular material up close and in context. Researchers from the University of Delaware’s Catalysis Center for Energy Innovation (CCEI) have done just that, developing new techniques for characterizing complex materials.
Researchers use drones, machine learning to detect dangerous ‘butterfly’ landmines
Using advanced machine learning, drones could be used to detect dangerous “butterfly” landmines in remote regions of post-conflict countries, according to research from Binghamton University, State University at New York.
Using Machine Learning to Estimate COVID-19’s Seasonal Cycle
One of the many unanswered scientific questions about COVID-19 is whether it is seasonal like the flu – waning in warm summer months then resurging in the fall and winter. Now scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) are launching a project to apply machine-learning methods to a plethora of health and environmental datasets, combined with high-resolution climate models and seasonal forecasts, to tease out the answer.
How Big Data and Artificial Intelligence Can Help Improve Healthcare Decision Making
ISPOR held its second Virtual ISPOR 2020 plenary session this afternoon, “Health Economics and Outcomes Research and Clinical Decision Making—Advancing Meaningful Progress.”
Engineers develop low-cost, high-accuracy GPS-like system for flexible medical robots
Roboticists at the University of California San Diego have developed an affordable, easy to use system to track the location of flexible surgical robots inside the human body. The system performs as well as current state of the art methods, but is much less expensive.
Johns Hopkins Researchers to Use Machine Learning to Predict Heart Damage in COVID-19 Victims
Johns Hopkins researchers recently received a $195,000 Rapid Response Research grant from the National Science Foundation to, using machine learning, identify which COVID-19 patients are at risk of adverse cardiac events such as heart failure, sustained abnormal heartbeats, heart attacks, cardiogenic shock and death.
Using Big Data to Design Gas Separation Membranes
Researchers at Columbia Engineering and the University of South Carolina have developed a method that combines big data and machine learning to selectively design gas-filtering polymer membranes to reduce greenhouse gas emissions. Their study, published today in Science Advances, is the first to apply an experimentally validated machine learning method to rapidly design and develop advanced gas separation membranes.
Making a Material World Better, Faster Now: Q&A With Materials Project Director Kristin Persson
Berkeley Lab’s Kristin Persson shares her thoughts on what inspired her to launch the Materials Project online database, the future of materials research and machine learning, and how she found her own way into a STEM career.
Computer vision helps SLAC scientists study lithium ion batteries
New machine learning methods bring insights into how lithium ion batteries degrade, and show it’s more complicated than many thought.
HU facial recognition software predicts criminality
A group of Harrisburg University of Science and Technology students and professors have developed an automated computer classifier capable of predicting with 80% accuracy and no racial bias whether someone is likely to be a criminal based solely on a picture of their face.
Jonathan W. Korn, a PhD student in Harrisburg University of Science and Technology’s Data Science program and a NYPD veteran; Prof. Nathaniel J.S. Ashby, and Prof. Roozbeh Sadeghian’s research titled “A Deep Neural Network Model to Predict Criminality Using Image Processing” will appear in the forthcoming Springer Nature – Research Book Series: Transactions on Computational Science & Computational Intelligence
Identifying Light Sources Using Artificial Intelligence
Identifying sources of light plays an important role in the development of many photonic technologies, such as lidar, remote sensing, and microscopy. Traditionally, identifying light sources as diverse as sunlight, laser radiation, or molecule fluorescence has required millions of measurements, particularly in low-light environments, which limits the realistic implementation of quantum photonic technologies. In Applied Physics Reviews, researchers demonstrated a smart quantum technology that enables a dramatic reduction in the number of measurements required to identify light sources
UAH boosts search for COVID-19 drugs using HPE Cray Sentinel supercomputer
University of Alabama in Huntsville (UAH) professor of biological science Dr. Jerome Baudry is collaborating with Hewlett Packard Enterprise (HPE) to use HPE’s Cray Sentinel supercomputer to search for natural products that are effective against the COVID-19 virus.
LLNL’s new machine learning platform generates novel COVID-19 antibody sequences for experimental testing
Lawrence Livermore National Laboratory researchers have identified an initial set of therapeutic antibody sequences, designed in a few weeks using machine learning and supercomputing, aimed at binding and neutralizing SARS-CoV-2, the virus that causes COVID-19. The research team is performing experimental testing on the chosen antibody designs.
UCI mathematicians use machine intelligence to map gene interactions
Irvine, Calif., April 29, 2020 — Researchers at the University of California, Irvine have developed a new mathematical machine-intelligence-based technique that spatially delineates highly complicated cell-to-cell and gene-gene interactions. The powerful method could help with the diagnosis and treatment of diseases ranging from cancer to COVID-19 through quantifing crosstalks between “good” cells and “bad” cells.
A new machine learning method streamlines particle accelerator operations
SLAC researchers have developed a new tool, using machine learning, that may make part of the accelerator tuning process five times faster compared to previous methods.
Machine Learning Tool Could Provide Unexpected Scientific Insights into COVID-19
A team of materials scientists at Lawrence Berkeley National Laboratory – scientists who normally spend their time researching things like high-performance materials for thermoelectrics or battery cathodes – have built a text-mining tool in record time to help the global scientific community synthesize the mountain of scientific literature on COVID-19 being generated every day.
Mayo Clinic researchers contribute unique CT data to public repository
Medical physicists at the Mayo Clinic have just made a unique library of computed tomography (CT) data publicly available so that imaging researchers can study, develop, validate, and optimize algorithms and enhance imaging hardware to produce peak-quality CT images using low radiation doses.
Machine Learning Models Predict COVID-19 Impact in Smaller Cities
“There are no simple, robust, general tools that, for example, officials in Albany could use to make projections,” said Magdon-Ismail, a professor of computer science, and expert in machine learning, data mining, and pattern recognition. “These models show that the projections vary enormously from one city to another. This knowledge could relieve some of the uncertainty that is around in developing policy.”
SLAC joins the global fight against COVID-19
The lab is responding to the coronavirus crisis by imaging disease-related biomolecules, developing standards for reliable coronavirus testing and enabling other essential research.
U.S. Department of Energy’s INCITE program seeks proposals for 2021
The INCITE program is now seeking proposals for high-impact, computationally intensive research projects that require the power and scale of DOE’s leadership-class supercomputers.
Hybrid microscope creates digital biopsies
Bioengineers have combined standard microscopy, infrared light, and artificial intelligence to assemble digital biopsies that identify important molecular characteristics of cancer biopsy samples.
Capturing 3D microstructures in real time
Argonne researchers have invented a machine-learning based algorithm for quantitatively characterizing material microstructure in three dimensions and in real time. This algorithm applies to most structural materials of interest to industry.
‘CoronaCheck’ website combats spread of misinformation
Cornell researchers have developed an automated system that uses machine learning, data analysis and human feedback to automatically verify statistical claims about the new coronavirus.
Fake Russian Twitter accounts politicized discourse about vaccines
Activity from phony Twitter accounts established by the Russian Internet Research Agency between 2015 and 2017 may have contributed to politicizing Americans’ position on the nature and efficacy of vaccines, a health care topic which has not historically fallen along party lines, according to new research published in the American Journal of Public Health.
Argonne’s researchers and facilities playing a key role in the fight against COVID-19
Argonne scientists are working around the clock to analyze the virus to find new treatments and cures, predict how it will propagate through the population, and make sure that our supply chains remain intact.
Argonne uses artificial intelligence to improve the safety and design of advanced nuclear reactors
Argonne scientists and engineers are looking toward AI — specifically, machine learning — to help us better understand the mechanics that govern nuclear reactors.
Study uses AI to estimate unexploded bombs from Vietnam War
Researchers have used artificial intelligence to detect Vietnam War-era bomb craters in Cambodia from satellite images – with the hope that it can help find unexploded bombs.
Berkeley Lab Cosmologists Are Top Contenders in Machine Learning Challenge
In a machine learning challenge dubbed the 2020 Large Hadron Collider Olympics, a team of cosmologists from Berkeley Lab developed a code that best identified a mock signal hidden in simulated particle-collision data.
Composing New Proteins with Artificial Intelligence
Proteins are the building blocks of life and scientists have long studied how to improve them or design new ones. Traditionally, new proteins are created by mimicking existing proteins or manually editing their amino acids. This process is time-consuming, and it is difficult to predict the impact of changing an amino acid. In APL Bioengineering, researchers explore how to create new proteins by using machine learning to translate protein structures into musical scores, presenting an unusual way to translate physics concepts across domains.
Applying Deep Learning to Automate UAV‐Based Detection of Scatterable Landmines
Recent advances in unmanned‐aerial‐vehicle‐ (UAV‐) based remote sensing utilizing lightweight multispectral and thermal infrared sensors allow for rapid wide‐area landmine contamination detection and mapping surveys. We present results of a study focused on developing and testing an automated technique of…
Designing plastic to break down in the ocean is possible, but is it practical?
In a study, the researchers used a machine learning algorithm to classify more than 110 types of plastics, including commercial and lab-made varieties, to better understand how they might degrade in the ocean.
Stargazing with Computers
Astrophysicists supported by the Department of Energy’s Office of Science are developing these guides in the form of computer models that rely on machine learning to examine the LSST data.
Machine learning reveals earth tremor and slip occur continuously, not intermittently
Applying deep learning to seismic data has revealed tremor and slip occur at all times—before and after known large-scale slow-slip earthquakes—rather than intermittently in discrete bursts, as previously believed.
Computers scour satellite imagery to unveil Madagascar’s mysteries
Scientists may be a step closer to solving some of anthropology’s biggest mysteries thanks to a machine learning algorithm that can scour through remote sensing data, such as satellite imagery, looking for signs of human settlements, according to an international team of researchers.
Machine Learning Identifies Personalized Brain Networks in Children
Machine learning is helping Penn Medicine researchers identify the size and shape of brain networks in individual children, which may be useful for understanding psychiatric disorders. In a new study published in Neuron, a multidisciplinary team showed how brain networks unique to each child can predict cognition. The study is the first to show that functional neuroanatomy can vary greatly among kids, and is refined during development.
Argonne engineers streamline jet engine design
Argonne scientists are combining one-of-a-kind x-ray experiments with novel computer simulations to help engineers at aerospace and defense companies save time and money.
New Robot Does Superior Job Sampling Blood
In the future, robots could take blood samples, benefiting patients and healthcare workers alike. A Rutgers-led team has created a blood-sampling robot that performed as well or better than people, according to the first human clinical trial of an automated blood drawing and testing device.
We Know AI is Biased; This Design Approach May Help Fix It
Bias in artificial intelligence is well established. Researchers are now proposing that developers incorporate the concept of “feminist design thinking” into their process as a way of improving equity – particularly in the development of software used in hiring.
CFN Staff Spotlight: Xiaohui Qu Bridges the Data Science-Materials Science Gap
As a staff member in the Theory and Computation Group at Brookhaven Lab’s Center for Functional Nanomaterials, Qu applies various approaches in artificial intelligence to analyze experimental and computational nanoscience data.