A doctoral student at The University of Alabama in Huntsville has been awarded a NASA Future Investigators in NASA Earth and Space Science and Technology (FINESST) fellowship to study space weather to improve predictive methods for coronal mass ejections (CME) from the Sun.
Tag: Machine Learning
Shaking Up Earthquake Studies by Increasing Access to Data, Tools and Research Results
Earthquake rupture forecast studies provide information about the probabilities of when earthquakes will occur, where they’ll take place and how strong they’ll be, but the computational tools and data aren’t available to a wide scientific community. That’s about to change.
Increasing national security with satellites that team together
Sandia National Laboratories has been working on an autonomy project led by the Air Force Research Laboratory that could improve the nation’s ability to conduct national security missions, including intelligence, surveillance, reconnaissance, climate monitoring and emergency response.
‘Computer vision’ reveals unprecedented physical and chemical details of how a lithium-ion battery works
Looking at X-ray movies with computer vision gives researchers an incredible new view of how nanoparticles in a lithium-ion battery electrode work during charging and discharging.
Not too big: Machine learning tames huge data sets
A machine-learning algorithm demonstrated the capability to process data that exceeds a computer’s available memory by identifying a massive data set’s key features and dividing them into manageable batches that don’t choke computer hardware. Developed at Los Alamos National Laboratory, the algorithm set a world record for factorizing huge data sets during a test run on Oak Ridge National Laboratory’s Summit, the world’s fifth-fastest supercomputer.
Equally efficient on laptops and supercomputers, the highly scalable algorithm solves hardware bottlenecks that prevent processing information from data-rich applications in cancer research, satellite imagery, social media networks, national security science and earthquake research, to name just a few.
Internationally recognized computational researcher Spyridon Bakas, PhD, to serve as inaugural director of Division of Computational Pathology
Indiana University School of Medicine Department of Pathology is launching a new Division of Computational Pathology and a Research Center for Federated Learning in Precision Medicine.
Machine learning tool simplifies one of the most widely used reactions in the pharmaceutical industry
University of Illinois researchers and a Swiss pharmaceutical company have developed a machine learning model that eliminates the need for extensive experimentation to determine the best conditions for an important carbon-nitrogen bond forming reaction known as the Buchwald-Hartwig reaction.
Department of Energy Announces $29 Million for Research on Machine Learning, Artificial Intelligence, and Data Resources for Fusion Energy Sciences
WASHINGTON, D.C. – Today, the U.S. Department of Energy (DOE) announced $29 million in funding for seven team awards for research in machine learning, artificial intelligence, and data resources for fusion energy sciences.
TRIAD Streamlines Edge Processing of Data in Phased-Array Antennas
As the number of elements on phased array antennas continues to grow, so does the volume of data that must be processed. To address this, researchers have developed a new approach to process that data closer to where it is generated – on the antenna subarrays themselves.
Better paths yield better AI
Like climbing a mountain via the shortest possible path, improving classification tasks can be achieved by choosing the most influential path to the output, and not just by learning with deeper networks.
AI can predict certain forms of esophageal and stomach cancer
AI can predict certain forms of esophageal and stomach cancer Michigan Medicine study says.
Down the tubes: Common PVC pipes can hack voice identification systems
Researchers are in an arms race with hackers to prevent data theft. Their standard tools include strategies like multi-factor authentication systems, fingerprint technology and retinal scans. One type of security system that is gaining popularity is automatic speaker identification, which uses a person’s voice as a passcode.
Department of Energy Announces $16 Million for Research on Artificial Intelligence and Machine Learning (AI/ML) for Nuclear Physics Accelerators and Detectors
Today, the U.S. Department of Energy (DOE) announced $16 million for fifteen projects that will implement artificial intelligence methods to accelerate scientific discovery in nuclear physics research.
Autonomous discovery defines the next era of science
Argonne National Laboratory is reimagining the lab spaces and scientific careers of the future by harnessing the power of robotics, artificial intelligence and machine learning in the quest for new knowledge.
New model reduces bias and enhances trust in AI decision-making and knowledge organization
University of Waterloo researchers have developed a new explainable artificial intelligence (AI) model to reduce bias and enhance trust and accuracy in machine learning-generated decision-making and knowledge organization.
AI model isolates olive oil ingredients that may fight Alzheimer’s
A growing body of evidence suggests extra virgin olive oil can help prevent cognitive decline due to Alzheimer’s disease. In a new study, Yale School of Medicine researchers led by Natalie Neumann, MD, trained a machine learning algorithm on current…
MD Anderson Research Highlights for August 2, 2023
The University of Texas MD Anderson Cancer Center’s Research Highlights showcases the latest breakthroughs in cancer care, research and prevention. These advances are made possible through seamless collaboration between MD Anderson’s world-leading clinicians and scientists, bringing discoveries from the lab to the clinic and back.
Recent developments include a novel biomarker that may predict the aggressiveness of pancreatic cancer precursors, insights into the structure and function of a breast and ovarian cancer susceptibility gene, a new approach to overcoming treatment resistance in ovarian cancer, distinguishing features of young-onset rectal cancer, a biomarker and potential target for metastatic lung cancer, machine learning models to better predict outcomes of patients with mantle cell lymphoma (MCL), and a promising therapy for patients with relapsed/refractory MCL.
Machine learning, blockchain technology could help counter spread of fake news
A proposed machine learning framework and expanded use of blockchain technology could help counter the spread of fake news by allowing content creators to focus on areas where the misinformation is likely to do the most public harm, according to new research from Binghamton University, State University of New York.
Study Identifies Pitfalls, Solutions for Using AI to Predict Opioid Use Disorder
Researchers examined peer-reviewed journal papers and conducted the first systematic review analyzing not only the technical aspects of machine learning applied to predicting opioid use, but also the published results.
New algorithm may fuel vaccine development
Immune system researchers have designed a computational tool to boost pandemic preparedness. Scientists can use this new algorithm to compare data from vastly different experiments and better predict how individuals may respond to disease.
Researchers use Argonne X-rays to find the best antibodies
Antibody therapies are only effective if the antibodies do what we want them to do. This research can help scientists determine if an antibody is likely to stick to something other than the intended target, which should lessen the amount of time wasted with overly sticky antibodies.
New research shows AI can ask another AI for a second opinion on medical scans
Researchers at Monash University have designed a new co-training AI algorithm for medical imaging that can effectively mimic the process of seeking a second opinion.
nference and Vanderbilt University Medical Center sign agreement to advance real-world evidence generation in complex disease populations
nference, a science-first software company transforming health care by making biomedical data computable, and Vanderbilt University Medical Center, a leading academic medical center, have announced a strategic agreement aimed at advancing research through the deployment of nference’s state-of-the-art federated clinical analytics platform.
Researchers Design Multiclass Cancer Diagnostic Tool Using AI, MicroRNA
MicroRNAs, or miRNAs, regulate genes and biological processes in the human body, including cancer formation and development. To explore the feasibility of miRNAs as cancer biomarkers, researchers created a multiclass cancer diagnostic model using miRNA expression profiles. The study examined the relationship between the composition of miRNAs and various types of cancers. Findings suggest that miRNAs may be highly unique to specific cancerous tissues and can be strong biomarkers for detection and classification in both research and the clinical field
Artificial intelligence and epilepsy: Dr. Christian Bosselmann
What’s the role of artificial intelligence in epilepsy research and care? Dr. Alina Ivaniuk talks with Dr. Christian Bosselmann about the potential uses and dangers of AI in epilepsy, including ChatGPT and machine learning.
Using AI to save species from extinction cascades
Algorithms can predict what movies or songs you might like, but they can also predict which species a predator would most likely eat.
Machine learning takes materials modeling into new era
Researchers have now pioneered a machine learning-based simulation method that supersedes traditional electronic structure simulation techniques. Their Materials Learning Algorithms (MALA) software stack enables access to previously unattainable length scales.
AI and CRISPR Precisely Control Gene Expression
The study by researchers at New York University, Columbia Engineering, and the New York Genome Center, combines a deep learning model with CRISPR screens to control the expression of human genes in different ways—such as flicking a light switch to shut them off completely or by using a dimmer knob to partially turn down their activity. These precise gene controls could be used to develop new CRISPR-based therapies.
New Insights on the Prevalence of Drizzle in Marine Stratocumulus Clouds
Detecting drizzle in its early stages in marine stratocumulus clouds is important for studying how water in clouds becomes rainfall. However, detecting the initial stages of drizzle is challenging for ground-based remote-sensing observations.
Digital Science expands Executive Team for AI future
Digital Science has expanded its Executive Team to reflect its current steep growth trajectory and further develop its market-leading capabilities in Artificial Intelligence (AI) and related technologies.
Could smart watches and wearable devices protect our military?
Could smart watches and wearable devices give our military the edge when it comes to protecting defence personnel against biological and chemical warfare threats?
The quest to develop fair and ethical algorithms in medical imaging
This interview with Maryellen Giger, PhD, delves into the creation of the MIDRC imaging repository, how its data can be used to develop and evaluate AI algorithms, ways that bias can be introduced—and potentially mitigated—in medical imaging models, and what the future may hold.
Create an independent body to regulate AI and prevent it from discriminating against disadvantaged groups
Qihang Lin, associate professor of business analytics at the University of Iowa’s Tippie College of Business, studies artificial intelligence and discrimination with a National Science Foundation grant. Based on his research, he believes an independent third-party organization must be created…
Amid volumes of mobile location data, new framework reduces consumers’ privacy risk, preserves advertisers’ utility
In a new study, researchers used machine learning to create and test a framework that quantifies personalized privacy risks; performs personalized data obfuscation; and accommodates a variety of risks, utilities, and acceptable levels of risk-utility tradeoff.
Robot ‘chef’ learns to recreate recipes from watching food videos
Researchers have trained a robotic ‘chef’ to watch and learn from cooking videos, and recreate the dish itself.
June 2023 Issue of Neurosurgical Focus: “Machine Learning in Neurosurgery”
Announcement of contents of the June 2023 issue of Neurosurgical Focus
We are in the midst of an AI-driven revolution in materials research where the confluence of automated experiments and machine learning are redefining the pace of materials discovery.
Keith A. Brown BS Physics, Massachusetts Institue of Technology PhD Applied Physics, Harvard University Postdoc in Chemistry, Northwestern University Contact: [email protected] Keith currently runs the KABlab, a research group at Boston University that studies approaches to accelerate the development of advanced…
Issa-kun, the artificial intelligence haiku poet
Associate Professor Tomohisa Yamashita and his colleagues at the Laboratory of Harmonious Systems Engineering devote their research to Artificial Intelligence (AI) for the benefit of human happiness. One of their breakthroughs is the birth of Issa-kun, a haiku generator.
New Articles on Using Machine Learning to Predict Mammalian Acute Oral Toxicity and the Effects of Vinyl Chloride on Metabolism
The May 2023 issue of Toxicological Sciences includes articles on profiling mechanisms that drive acute oral toxicity in mammals and its prediction via machine learning and how vinyl chloride enhances high-fat diet-induced proteome alterations in the mouse pancreas related to metabolic dysfunction.
Artificial Intelligence Catalyzes Gene Activation Research and Uncovers Rare DNA Sequences
Biologists have used machine learning, a type of AI, to identify “synthetic extreme” DNA sequences with specifically designed functions in gene activation. They tested 50 million DNA sequences and found synthetic DNA sequences with activities that could be useful in biotechnology and medicine.
Evolutionary reinforcement learning promises further advances in machine learning
Evolutionary reinforcement learning is an exciting frontier in machine learning, combining the strengths of two distinct approaches: reinforcement learning and evolutionary computation.
Researchers Show That a Machine Learning Model Can Improve Mortality Risk Prediction for Cardiac Surgery Patients
A machine learning-based model that enables medical institutions to predict the mortality risk for individual cardiac surgery patients has been developed by a Mount Sinai research team, providing a significant performance advantage over current population-derived models.
Engineers building tools to improve quality, production of disease-fighting cells
Iowa State University engineers are developing advanced tools for cell manufacturing that could improve the cost and availability of therapeutic cells capable of fighting diseases such as cancers, heart disease, lupus and other autoimmune diseases.
AI study finds that patients with Parkinson’s disease speak differently to healthy patients
Using artificial intelligence (AI) to process natural language, a research group evaluated the characteristics of speech among patients with Parkinson’s disease (PD).
Rensselaer Researcher Uses Artificial Intelligence To Discover New Materials for Advanced Computing
A team of researchers led by Rensselaer Polytechnic Institute’s Trevor David Rhone, assistant professor in the Department of Physics, Applied Physics, and Astronomy, has identified novel van der Waals (vdW) magnets using cutting-edge tools in artificial intelligence (AI). In particular, the team identified transition metal halide vdW materials with large magnetic moments that are predicted to be chemically stable using semi-supervised learning.
Fire Hydrant Hydrophones Find Water Leaks #ASA184
Acoustic monitoring is the go-to solution for locating a leak in a large urban pipe network, as the sounds from leaks are unique and travel far in water, but even this method struggles in complex systems. To tackle the problem, Pranav Agrawal and Sriram Narasimhan from UCLA developed algorithms that operate on acoustic signals collected via hydrophones mounted on fire hydrants. In doing so, the team can avoid costly excavation and reposition the devices as needed. Combined with novel probabilistic and machine-learning techniques to analyze the signals and pinpoint leaks, this technology could support water conservation efforts.
AI developed in the UK is the world leader in identifying the location and expression of proteins
A new advanced artificial intelligence (AI) system has shown world-leading accuracy and speed in identifying protein patterns within individual cells.
Cedars-Sinai Establishes Center for Artificial Intelligence Research and Education
The Cedars-Sinai Department of Computational Biomedicine recently sharpened its focus on advancing artificial intelligence and machine learning by establishing the Center for Artificial Intelligence Research and Education.
What really killed COVID-19 patients: it wasn’t a cytokine storm
Secondary bacterial infection of the lung (pneumonia) was extremely common in patients with COVID-19, affecting almost half the patients who required support from mechanical ventilation.
Scientists develop pioneering artificial intelligence method to fight urban air pollution
99% of the world’s population breathes air that exceeds the limits recommended by the World Health Organization (WHO). This scenario is exacerbated in urban areas where more than 50% of the world’s population is concentrated.