Sibendu Som, whose work focuses on high-fidelity simulations of power generation and propulsion systems, has been designated a fellow by the American Society of Mechanical Engineers.
Tag: Machine Learning
Is brain learning weaker than artificial Intelligence?
Can the brain, with its limited realization of precise mathematical operations, compete with advanced artificial intelligence systems implemented on fast and parallel computers? From our daily experience we know that for many tasks the answer is yes! Why is this and, given this affirmative answer, can one build a new type of efficient artificial intelligence inspired by the brain? In an article published today in Scientific Reports, researchers from Bar-Ilan University in Israel solve this puzzle.
AI and health care: DePaul and Rosalind Franklin award interdisciplinary research grants
DePaul University and Rosalind Franklin University of Science and Medicine are funding three faculty research projects that bring together artificial intelligence, biomedical discovery and health care. The competitive grants kickstart research among interdisciplinary teams, which include biologists, computer scientists, a geographer and a physicist.
UCI researchers decipher atomic-scale imperfections in lithium-ion batteries
As lithium-ion batteries have become a ubiquitous part of our lives through their use in consumer electronics, automobiles and electricity storage facilities, researchers have been working to improve their power, efficiency and longevity. As detailed in a paper published today in Nature Materials, scientists at the University of California, Irvine and Brookhaven National Laboratory conducted a detailed examination of high-nickel-content layered cathodes, considered to be components of promise in next-generation batteries.
Researchers will harness machine learning to provide residents with personalized warnings for heat emergencies
An automated heat alert system built using innovative machine learning technology could improve preparedness for extreme heat. A research team lead by Iowa State University has received a $1.2 million grant from the National Science Foundation to gather data and develop an automated heat warning system for susceptible Des Moines neighborhoods.
AI Discovers New Nanostructures
UPTON, NY—Scientists at the U.S. Department of Energy’s (DOE) Brookhaven National Laboratory have successfully demonstrated that autonomous methods can discover new materials. The artificial intelligence (AI)-driven technique led to the discovery of three new nanostructures, including a first-of-its-kind nanoscale “ladder.
Using machine learning to help monitor climate-induced hazards
Combining satellite technology with machine learning may allow scientists to better track and prepare for climate-induced natural hazards, according to research presented last month at the annual meeting of the American Geophysical Union.
Machine Learning Tackles Long COVID
There are so many unknowns about long COVID. Why is the range of symptoms so vast? How do pre-existing conditions play a role? Scientists have developed a machine learning tool to accelerate discoveries using actual patient data.
High-Pressure Systems Favor Sea-Breeze Convection Over Southeastern Texas
In the summer, sea- and bay-breeze circulations are important drivers of the weather in southeastern Texas. This research used machine learning techniques to unpack how these circulations interact with larger-scale weather systems to affect how thunderstorms form in the Houston area. These insights are helping researchers focus their study of aerosol and cloud life cycle, aerosol-cloud interactions, and air quality during the TRACER field campaign in the Houston area in 2021 and 2022.
New Computer Program ‘Learns’ to Identify Mosaic Mutations That Cause Disease
UC San Diego researchers describe a method for teaching a computer how to spot complex “mosaic mutations” using an artificial intelligence approach termed “deep learning.”
Computer Vision Is Superior to Surgeons in Identifying Spinal Implants
Computer vision model outperforms surgeons when identifying types of spinal implants.
CHOP and NJIT Researchers Develop New Tool for Studying Multiple Characteristics of a Single Cell
Researchers from Children’s Hospital of Philadelphia (CHOP) and New Jersey Institute of Technology (NJIT) developed new software that integrates a variety of information from a single cell, allowing researchers to see how one change in a cell can lead to several others and providing important clues for pinpointing the exact causes of genetic-based diseases.
Scientists use machine learning to get an unprecedented view of small molecules
A new tool to identify small molecules offers benefits for diagnostics, drug discovery, and fundamental research.
Using Machine Learning to Better Understand How Water Behaves
New research from the Georgia Institute of Technology uses machine learning models to better understand water’s phase changes, opening more avenues for a better theoretical understanding of various substances. With this technique, the researchers found strong computational evidence in support of water’s liquid-liquid transition that can be applied to real-world systems that use water to operate.
Argonne seeks STEM interns to help design the future of science
The U.S. Department of Energy’s Argonne National Laboratory seeks undergraduate and graduate students for a summer 2023 internship in robotics and instrumentation. Students will explore using robotics, artificial intelligence and machine learning.
AI Model Proactively Predicts if a COVID-19 Test Might be Positive or Not
Researchers trained five classification algorithms to create an accurate model to predict COVID-19 test results. Results identify the key symptom features associated with COVID-19 infection and provide a way for rapid screening and cost effective infection detection. Findings reveal that number of days experiencing symptoms such as fever and difficulty breathing play a large role in COVID-19 test results. Findings also show that molecular tests have much narrower post-symptom onset days compared to post-symptom onset days of serology tests. As a result, the molecular test has the lowest positive rate because it measures current infection.
Argonne researchers awarded joint projects in advanced computing
Argonne scientists were awarded Scientific Discovery through Advanced Computing projects in nuclear and high energy physics, and Earth system model development. They will partner with DOE national labs to connect experts and high performance computers.
Finding the right AI for you
The human genome is three billion letters of code, and each person has millions of variations. While no human can realistically sift through all that code, computers can.
Listen to the Toilet — It Could Detect Disease #ASA183
Researchers describe how a noninvasive microphone sensor could identify bowel diseases without collecting any identifiable information. They tested the technique on audio data from online sources, transforming each audio sample of an excretion event into a spectrogram, which essentially captures the sound in an image. The images were fed to a machine learning algorithm that learned to classify each event based on its features. The algorithm’s performance was tested against data with and without background noises.
Machine Learning Diagnoses Pneumonia by Listening to Coughs #ASA183
Researchers have developed a machine learning algorithm to identify cough sounds and determine whether the subject is suffering from pneumonia. Because every room and recording device is different, they augmented their recordings with room impulse responses, which measure how the acoustics of a space react to different sound frequencies. By combining this data with the recorded cough sounds, the algorithm can work in any environment.
No ‘one size fits all’ solution to treating early-onset psychosis
Gold standard treatment plans for people with early psychosis have a patchy success rate, suggesting the need to develop more tailored approaches.
New Machine Learning Calculations May Predict Narrowing of Coronary Artery
Article title: Deep learning-based prediction of coronary artery stenosis resistance Authors: Hao Sun, Jincheng Liu, Yili Feng, Xiaolu Xi, Ke Xu, Liyuan Zhang, Jian Liu, Bao Li, Youjun Liu From the authors: “The present study proposed a method to predict…
Adapting language models to track virus variants
Groundbreaking research by Argonne National Laboratory finds new method to quickly identify COVID-19 virus variants. Their work wins the Gordon Bell Special Prize.
Machine learning model builds on imaging methods to better detect ovarian lesions
Research from Quing Zhu’s lab yields a novel method to use ultrasound to enhance machine learning’s ability to accurately diagnose – or rule out – ovarian cancer.
Teaching photonic chips to learn
A multi-institution research team has developed an optical chip that can train machine learning hardware.
A possible game changer for next generation microelectronics
Researchers have discovered new properties of tiny magnetic whirlpools called skyrmions. Their pivotal discovery could lead to a new generation of microelectronics for memory storage with vastly improved energy efficiency.
Argonne scientists promote FAIR standards for managing artificial intelligence models
Argonne computational scientists adopt new framework for making AI models more findable, accessible, interoperable and reusable.
Johns Hopkins APL Releases First-Ever Global Estimates for Road Transportation Greenhouse Emissions Leveraging Artificial Intelligence and Satellite Images
APL scientists have leveraged the global coverage of satellite imagery and the strengths of machine learning to create the first automated approach for estimating greenhouse gas emissions from the road transportation sector.
New technology to reduce potholes
Researchers have developed new “intelligent compaction” technology, which integrates into a road roller and can assess in real-time the quality of road base compaction.
Detecting Nuclear Threats with Artificial Reasoning
PNNL researchers use machine learning and data analytics to assist with detection of nuclear proliferation and nuclear material trafficking.
Scientists develop new algorithm that may provide insights into battery corrosion
New method provides insight into how materials evolve in real-time.
Deep learning underlies geographic dataset used in hurricane response
Over the past seven years, researchers in ORNL’s Geospatial Science and Human Security Division have mapped and characterized all structures within the United States and its territories to aid FEMA in its response to disasters.
New machine-learning simulations reduce energy need for mask fabrics, other materials
A new computational effort between Argonne and 3M promises to reduce energy consumption without sacrificing material quality in the production of nonwoven plastics, commonly used in surgical masks.
FAU Lands $1.2 Million NSF Grant to Transform Prosthetic Hand Control
Current prosthetic hands have five individually actuated digits, yet only one grasp function can be controlled at a time, which makes sophisticated tasks largely impossible.
AI model using daily step counts predicts unplanned hospitalizations during cancer therapy
An artificial intelligence (AI) model developed by researchers can predict the likelihood that a patient may have an unplanned hospitalization during their radiation treatments for cancer. The machine-learning model uses daily step counts as a proxy to monitor patients’ health as they go through cancer therapy, offering clinicians a real-time method to provide personalized care. Findings will be presented today at the American Society for Radiation Oncology (ASTRO) Annual Meeting.
Study finds that artificial intelligence can determine race from medical images
Researchers have found that AI models could accurately predict self-reported race in several types of medical images, suggesting that race information could be unknowingly incorporated into image analysis models.
5 big strides from Argonne towards nuclear energy’s future
Nuclear energy is an exciting carbon-free energy source. Recent work at Argonne National Laboratory shows how nuclear energy can improve and why it is such an enticing resource in the fight against climate change.
Machine Learning Takes Hold in Nuclear Physics
Scientists have begun turning to new tools offered by machine learning to help save time and money. In the past several years, nuclear physics has seen a flurry of machine learning projects come online, with many papers published on the subject. Now, 18 authors from 11 institutions summarize this explosion of artificial intelligence-aided work in “Machine Learning in Nuclear Physics,” a paper recently published in Reviews of Modern Physics.
AACN Research Grants Influence Nursing Practice
The American Association of Critical-Care Nurses announces the newest recipients of its annual research grants and invites clinicians and researchers to submit projects online by Oct. 28, 2022, for the next application cycle. AACN will award up to three $50,000 Impact Research Grants in 2023, as well as co-sponsoring the AACN-Sigma Critical Care Grant, with up to $10,000 in funding.
Common Approach to Demystify Black Box AI Not Ready for Prime Time, Study Finds
Clinical AI tools hold the promise to transform the practice of medicine, but lack of transparency in some tools is an ongoing challenge.
Coalition for Health AI Updates Progress and Plans to Issue Guidelines for the Responsible Use of AI in Healthcare
The coalition focused on the foundational themes of Bias, Equity, and Fairness in its first in a series of workshops aimed at developing guidelines for the responsible use of AI in healthcare.
Scientists use machine learning to accelerate materials discovery
Scientists at Argonne National Laboratory have recently demonstrated an automated process for identifying and exploring promising new materials by combining machine learning (ML) and high performance computing.
Helping companies improve energy efficiency through high performance computing
The U.S. Department of Energy (DOE) has awarded DOE’s Argonne National Laboratory with $600,000 in federal funding to work on two new projects that will advance cutting edge manufacturing and clean energy technologies.
Unreliable neurons improve brain functionalities
Neuronal silencing periods facilitate an advantageous mechanism for temporal sequence identification and demonstrate a useful new AI mechanism for ATM’s equipped with secure handwriting recognition.
Machine learning creates opportunity for new personalized therapies
Researchers at the University of Michigan Rogel Cancer Center have developed a computational platform that can predict new and specific metabolic targets in ovarian cancer, suggesting opportunities to develop personalized therapies for patients that are informed by the genetic makeup of their tumors. The study appeared in Nature Metabolism.
Mutational signature linking bladder cancer and tobacco smoking found with new AI tool
UC San Diego researchers have for the first time discovered a pattern of DNA mutations that links bladder cancer to tobacco smoking. The work could help researchers identify what environmental factors, such as exposure to tobacco smoke and UV radiation, cause cancer in certain patients. It could also lead to more customized treatments for a patient’s specific cancer.
Researchers Aim to Use AI to Predict Rare Diseases
Penn Medicine researchers will help lead development of an algorithm to flag patients at risk of rare disease thanks to a $4.7 million NIH grant
Mount Sinai Researchers Use Artificial Intelligence to Uncover the Cellular Origins of Alzheimer’s Disease and Other Cognitive Disorders
Deep learning models represent “an entirely new paradigm for studying dementia”
Researchers combine data science and machine learning techniques to improve traditional MRI image reconstruction
University of Minnesota Twin Cities researchers have found a way to improve the performance of traditional Magnetic Resonance Imaging (MRI) reconstruction techniques, allowing for faster MRIs without relying on the use of newer deep learning methods.
UC San Diego Joins NIH ‘Bridge to Artificial Intelligence’ Program
UC San Diego scientists will lead several components of Bridge2AI, a new NIH-funded program to promote the use of AI in health and research.