English
Arabic
Chinese (Simplified)
Dutch
Esperanto
French
German
Greek
Italian
Japanese
Korean
Portuguese
Russian
Spanish
UrduUsing an AI-driven decision support system to predict the severity of COVID-19 and identify best interventions, researchers analyzed electronic health record data from 5,371 patients admitted to a South Florida hospital. The study specifically aimed to forecast the likelihood of patients requiring admission to an ICU, with or without mechanical ventilation, or an intermediate care unit (IMCU). The goal was to leverage these features to enable faster and more accurate forecasting of treatment plans, potentially preventing critical conditions from worsening.
Tag: Machine Learning
From advancing X-rays to unlocking exascale: Argonne highlights from 2024
As the year comes to a close, the U.S. Department of Energy’s Argonne National Laboratory reviews some of its most notable achievements of 2024.
Breaking Barriers: Study Uses AI to Interpret American Sign Language in Real-time
A study is the first-of-its-kind to recognize American Sign Language (ASL) alphabet gestures using computer vision. Researchers developed a custom dataset of 29,820 static images of ASL hand gestures. Each image was annotated with 21 key landmarks on the hand, providing detailed spatial information about its structure and position. Combining MediaPipe and YOLOv8, a deep learning method they trained, with fine-tuning hyperparameters for the best accuracy, represents a groundbreaking and innovative approach that hasn’t been explored in previous research.
Memorial Sloan Kettering Physician-Scientists Develop Innovative Multimodal Machine Learning Model That Improves Prediction of Metastatic Breast Cancer Treatment Options
New research presented during the 2024 San Antonio Breast Cancer Symposium (SABCS) reveals a new machine learning model that could change the way metastatic breast cancer is treated in the future. By combining clinical and genomic data, physician-scientists from Memorial Sloan Kettering Cancer Center (MSK) developed a tool that could help improve predictions of how people with hormone receptor-positive, HER2-negative (HR+/HER2-) metastatic breast cancer respond to CDK4/6 inhibitors, a class of oral medications that control cell division and are often prescribed in combination with hormone therapy to treat this subset of patients.
Researchers Demonstrate New Technique for Stealing AI Models
Researchers have demonstrated the ability to steal an artificial intelligence (AI) model without hacking into the device where the model was running. The technique is novel in that it works even when the thief has no prior knowledge of the software or architecture that support the AI.
NATIONWIDE STUDY LOOKS AT WHEN AND WHERE EV OWNERS USE PUBLIC CHARGING STATIONS
Researchers at the University of Maryland are using supercomputers and machine learning methods to analyze a full year of real-time data collected from individual EV charging ports at more than 50,000 publicly available stations throughout the country. The primary focus of the study is to estimate demand and peak times at EV charging stations.
Two UC Irvine researchers named fellows by National Academy of Inventors
The National Academy of Inventors has named two University of California, Irvine researchers as fellows. Hamid Jafarkhani, Chancellor’s Professor of electrical engineering & computer science, was recognized for his pioneering contributions to signal processing for multi-antenna wireless communications systems.
The best AI strategy to recognize multiple objects in one image
Image classification is one of AI’s most common tasks, where a system is required to recognize an object from a given image. Yet real life requires us to recognize not a single standalone object but rather multiple objects appearing together in a given image.
This reality raises the question: what is the best strategy to tackle multi-object classification? The common approach is to detect each object individually and then classify them. But new research challenges this customary approach to multi-object classification tasks.
In an article published today in Physica A, researchers from Bar-Ilan University in Israel show how classifying objects together, through a process known as Multi-Label Classification (MLC), can surpass the common detection-based classification.
Machine Learning for Predicting Corporate Violations: How Do CEO Characteristics Matter?
Abstract Based on upper echelon theory, we employ machine learning to explore how CEO characteristics influence corporate violations using a large-scale dataset of listed firms in China for the period 2010–2020. Comparing ten machine learning methods, we find that eXtreme…
Analyzing multiple mammograms improves breast cancer risk prediction
A new method of analyzing mammograms — developed by researchers at WashU Medicine — identified individuals at high risk of developing breast cancer more accurately than the standard, questionnaire-based method did. The new method, powered by artificial intelligence, could help diagnose cancer earlier and guide recommendations for earlier screening, additional imaging or risk-reducing medications.
Dark matter, neutrinos and drug discovery: how AI is powering SLAC science and technology
Check out the second of a two-part series exploring how artificial intelligence helps researchers from around the world perform cutting-edge science with the lab’s state-of-the-art facilities and instruments. Read part one here. In this part you’ll learn how AI is playing a key role in helping SLAC researchers find new galaxies and tiny neutrinos, and discover new drugs.
Scientists Create Model to Make MRI More Accurate, Reliable
The new model, developed by researchers at the UNC School of Medicine, can produce more accurate and reliable analysis of brain structures, which is critical for early detection, medical diagnosis, and neurological research.
Taming big data and particle beams: how SLAC researchers are pushing AI to the edge
Check out the first of a two-part series exploring how artificial intelligence helps researchers from around the world perform cutting-edge science with the lab’s state-of-the-art facilities and instruments. In this part you’ll learn how SLAC researchers collaborate to develop AI tools to make molecular movies, speeding up the discovery process in the era of big data.
A Film Capacitor That Can Take the Heat
Berkeley Lab and several collaborating institutions have successfully demonstrated a machine-learning technique to accelerate discovery of materials for film capacitors — crucial components in electrification and renewable energy technologies.
MERMAID Named Winner of 2024-2025 Amazon Web Services IMAGINE Grant for Nonprofits
Wildlife Conservation Society (WCS) today announced it has been selected as a winner of the 2024 Amazon Web Services (AWS) IMAGINE Grant, a public grant opportunity open to registered 501(c) nonprofit organizations in the United States who are using technology to solve the world’s most pressing challenges.
Energy Performance of Building Refurbishments: Predictive and Prescriptive AI-based Machine Learning Approaches
Abstract The energy performance (EP) of buildings is critical for European governments to meet their decarbonization targets by 2050. In the context of European Union (EU) policies, which subsidize citizen-led building renovations, it is imperative to ascertain the efficacy of…
Dragon 5 unleashed: charting new frontiers in earth science
The journal Geo-Spatial Information Science will soon release a special issue showcasing the mid-term achievements of the China-Europe Earth Observation project, “Dragon 5.” Launched in July 2020, the initiative has made significant strides in Earth sciences, fostering cross-border collaboration and advancing the use of satellite data.
Deciphering city skies: AI unveils GNSS error identification
Faced with the persistent challenge of Non-Line-of-Sight (NLOS) errors in urban Global Navigation Satellite Systems (GNSS) navigation, researchers have introduced an innovative solution powered by Artificial Intelligence (AI). By leveraging the Light Gradient Boosting Machine (LightGBM), this method analyzes multiple GNSS signal features to accurately identify and differentiate NLOS errors.
AI-enhanced satellite carbon monoxide fast retrieval
A recent study presents a radiative transfer model-driven machine learning technique for retrieving carbon monoxide from the world’s first hyperspectral Geostationary Interferometric Infrared Sounder (GIIRS) onboard Fengyun-4B (FY-4B) satellite, providing complementary insights into air quality and pollutant transport over East Asia.
How does the information ecosystem influence politics?
How does the information ecosystem influence politics?
Neuro-oncology experts reveal how to use AI to improve brain cancer diagnosis, monitoring, treatment
An international team of neuro-oncology researchers and clinicians has released new recommendations for good clinical practice regarding the use of artificial intelligence methods to more accurately diagnose, monitor and treat brain cancer.
Researchers Reveal Why a Key Tuberculosis Drug Works Against Resistant Strains
Rutgers Health study uncovers vulnerabilities in drug-resistant TB, offering hope for improved treatments.
Media Tip: Cyberthreats are growing – so are patents for technology to combat them
Patent data analysis highlights the leading companies in cybersecurity innovations At a time when public trust has been undermined by strings of cyberattacks and cyber spying, IFI CLAIMS Patent Services – the industry’s most trusted patent data provider – has…
Machine learning in international business
Abstract In the real world of international business, machine learning (ML) is well established as an essential element in many operations, from finance and logistics to marketing and strategy. However, ML as an analytical tool is still far from widespread…
Flow of the future: AI models tackle complex particle drag coefficients
Researchers have made a groundbreaking advance in fluid dynamics, using machine learning to accurately predict the drag coefficients of complex-shaped particles. This technological leap promises to significantly enhance our understanding of how particles behave in fluid flows, a key aspect in various industrial and environmental processes.
Everything you always wanted to know about large language models for science (but were afraid to ask)
Large language models are changing the way that people create and communicate, but they can also change the way we do science. Researchers from Argonne National Laboratory hope to demystify these tools and share how they’re shaping future research.
Could Poor Sleep in Middle Age Speed Up Brain Aging?
People in early middle age who have poor sleep quality, including having difficulty falling or staying asleep, have more signs of poor brain health in late middle age, according to a study published in the October 23, 2024, online issue of Neurology®, the medical journal of the American Academy of Neurology.
AI model predicts patients at most risk of complication during treatment for advanced kidney failure
A study led by the University of Portsmouth in England and Portsmouth Hospitals University NHS Trust (PHUT) has developed an AI model to predict which patients are most at risk of their blood pressure dropping during dialysis; a condition known as intradialytic hypotension (IDH).
How does worker mobility affect business adoption of a new technology? The case of machine learning
Abstract Research Summary We investigate how worker mobility influences the adoption of a new technology using state-level changes to the enforceability of noncompete agreements as an exogenous shock to worker mobility. Using data on over 153,000 establishments from 2010 and…
Are brain delays a computational disadvantage?
Biological components are less reliable than electrical ones, and rather than instantaneously receive the incoming signals, the signals arrive with a variety of delays.
New AI models of plasma heating lead to important corrections in computer code used for fusion research
New artificial intelligence models for plasma heating can do more than was previously thought possible, not only increasing the prediction speed 10 million times while preserving accuracy but also correctly predicting plasma heating in cases where the original numerical code failed.
Research to use machine learning to ’reverse-engineer’ new composite materials
Professors at Binghamton University, State University of New York have received NSF grant for deep-learning model that can customize microarchitecture based on specific needs
Bar-Ilan University researchers available for comment on Nobel Prize winning research in physics
The following experts in physics, brain science, computer science and additional fields can comment on the awarding of the Nobel Prize in Physics for 2024 to U.S. scientist John Hopfield and British-Canadian Geoffrey Hinton for their discoveries and inventions that laid the…
AIP Congratulates 2024 Nobel Prize Winners in Physics
The 2024 Nobel Prize in physics was awarded to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
Implementing medical imaging AI: issues to consider
As AI is deployed in clinical centers across the U.S., one important consideration is to assure that models are fair and perform equally across patient groups and populations. To better understand the fairness of medical imaging AI, a team of researchers trained over 3,000 models spanning multiple model configurations, algorithms, and clinical tasks.
Inaugural summit to explore artificial intelligence
A new virtual conference will explore how artificial intelligence (AI) can help health care providers and scientists efficiently analyze vast amounts of data and make more informed decisions, the Endocrine Society announced today.
Feet First: AI Reveals How Infants Connect with Their World
Researchers explored how infants act purposefully by attaching a colorful mobile to their foot and tracking movements with a Vicon 3D motion capture system. The study tested AI’s ability to detect changes in infant movement patterns. Findings showed that AI techniques, especially the deep learning model 2D-CapsNet, effectively classified different stages of behavior. Notably, foot movements varied significantly. Looking at how AI classification accuracy changes for each baby gives researchers a new way to understand when and how they start to engage with the world.
New AI model efficiently reaches clinical-expert-level accuracy in complex medical scans
UCLA researchers have developed a deep-learning framework that teaches itself quickly to automatically analyze and diagnose MRIs and other 3D medical images – with accuracy matching that of medical specialists in a fraction of the time.
Replacing hype about artificial intelligence with accurate measurements of success
A new paper in Nature Machine Intelligence notes that journal articles reporting how well machine learning models solve certain kinds of equations are often overly optimistic. The researchers suggest two rules for reporting results and systemic changes to encourage clarity and accuracy in reporting.
Ceevra 3D Models Improve Outcomes for Patients Undergoing Prostate Cancer Surgery
In a multisite randomized controlled trial published in JAMA Network Open in September 2024, the use of Ceevra 3D models in robotic prostatectomy procedures were shown to reduce risk of cancer recurrence, improve functional outcomes, and improve rates of trifecta outcomes.
Postdoc Takes Multipronged Approach to Muon Detection
2024 JSA Postdoctoral Prize Winner Debaditya Biswas will combine different particle identification methods with machine learning to detect muons hidden in a sea of pions.
Department of Energy Announces $68 Million in Funding for Artificial Intelligence for Scientific Research
The use of Artificial Intelligence (AI) in scientific research is a top priority at the Department of Energy (DOE), which today announced $68 million in funding for 11 multi-institution projects, comprising 43 awards.
Using AI to prevent ruptured brain aneurysms
Bioengineering Ph.D. student Holly Berns won a grant from the Brain Aneurysm Foundation to study how AI and other new technologies can change how aneurysms are discovered and treated. Her project will use AI and machine learning to examine how arteries leading to the brain are tilted and whether that tilt contributes to the formation and rupture of brain aneurysms.
FAU Engineering Professor Achieves Milestone as Highly Cited Google Scholar
Dr. Khoshgoftaar’s scientific publications have garnered more than 63,500 citations during his distinguished career at FAU (1985 to present), yielding a Google Scholar h-index of 95.
Notre Dame researchers create new tool to analyze embodied carbon in more than 1 million buildings in Chicago
The impact of embodied carbon in the built environment has been difficult to assess, due to a lack of data. To address that knowledge gap, Ming Hu, the associate dean for research, scholarship and creative work in Notre Dame’s School of Architecture, and Siavash Ghorbany, a Notre Dame graduate student in civil and environmental engineering, have created a new tool to analyze the embodied carbon in more than 1 million buildings in Chicago. Their recently published research identifies 157 different architectural housing types in the city and provides the first ever visual analysis tool to evaluate embodied carbon at a granular level and to help inform policymakers seeking to strategically plan for urban carbon mitigation.
New tool detects fake, AI-produced scientific articles
A team including faculty at Binghamton University, State University of New York has created a machine-learning algorithm that can detect up to 94% of bogus academic papers — nearly twice as successfully as more common data-mining techniques.
$1.8M NIH Grant to FAU Engineering Fuels Quest to Decode Human Evolution
FAU has received a five-year NIH grant to further research on designing and applying statistical methods to identify regions of the genome affected by natural selection, which is an important evolutionary force that enables humans to adapt to new environments and fight disease-causing pathogens.
Machine learning predicts which patients will continue taking opioids after hand surgery
A machine learning algorithm performs well in predicting the risk of persistent opioid use after hand surgery, reports a study in the August issue of Plastic and Reconstructive Surgery®, the official medical journal of the American Society of Plastic Surgeons (ASPS). The journal is published in the Lippincott portfolio by Wolters Kluwer.
Swifter simulations for modern science. All of it
In a machine learning paper recently published in the journal npj Computational Materials, a team of researchers from Sandia National Laboratories and Brown University have introduced a universal way to accelerate virtually any kind of simulation.
Illinois researchers develop near-infrared spectroscopy models to analyze corn kernels, biomass
In the agricultural and food industry, determining the chemical composition of raw materials is important for production efficiency, application, and price. Traditional laboratory testing is time-consuming, complicated, and expensive. New research from the University of Illinois Urbana-Champaign demonstrates that near-infrared (NIR) spectroscopy and machine learning can provide quick, accurate, and cost-effective product analysis.