Designed to identify wildlife by sound, the BirdNET app opens new avenues for citizen science

The BirdNET app, a free machine-learning powered tool that can identify more than 3,000 birds by sound alone, generates reliable scientific data and makes it easier for people to contribute citizen-science data on birds by simply recording sounds. Results of tests to measure the app’s accuracy are published in the open access journal PLOS Biology.

Sentience is beside the point when it comes to AI & ethics

Yevgeniy Vorobeychik doesn’t know exactly what sentience is. Since he’s an engineer, not a philosopher, Vorobeychik can’t say what it’s like to be a bat  or a tree or a rock. He can’t quantify the importance of embodiment to consciousness. He’s not even sure that there’s an inherent problem with people reacting to an artificial intelligence in ways similar to how they react to other people.

Mount Sinai Researchers Develop Machine Learning Model that Can Detect and Predict COVID-19 from Collected Data on Wearable Devices

Mount Sinai researchers have developed a machine learning algorithm that can determine if an individual has SARS-CoV-2 infections, the virus that causes COVID-19—with a high sensitivity and specificity—from the data collected by wearable devices.

Computer hardware mimics brain functions

A multi-institutional team, including Argonne National Laboratory, has developed a material with which computer chips can be designed to reconfigure their circuits when presented with new information. It does so by mimicking functions in the human brain.

Machine Learning Framework IDs Targets for Improving Catalysts

Chemists at the U.S. Department of Energy’s Brookhaven National Laboratory have developed a new machine-learning (ML) framework that can zero in on which steps of a multistep chemical conversion should be tweaked to improve productivity. The approach could help guide the design of catalysts — chemical “dealmakers” that speed up reactions.

VA, ORNL and Harvard develop novel method to identify complex medical relationships

A team of researchers from the Department of Veterans Affairs, Oak Ridge National Laboratory, Harvard’s T.H. Chan School of Public Health, Harvard Medical School and Brigham and Women’s Hospital has developed a novel, machine learning–based technique to explore and identify relationships among medical concepts using electronic health record data across multiple healthcare providers.

AI Could Predict Ideal Chronic Pain Patients for Spinal Cord Stimulation

Spinal cord stimulation is a minimally invasive FDA-approved treatment to manage chronic pain such as back and neck pain. The ability to accurately predict which patients will benefit from this treatment in the long term is unclear and currently relies on the subjective experience of the implanting physician. A study is the first to use machine-learning algorithms in the neuromodulation field to predict long-term patient response to spinal cord stimulation.

New brain learning mechanism calls for revision of long-held neuroscience hypothesis

In an article published today in Scientific Reports (https://www.nature.com/articles/s41598-022-10466-8), researchers from Bar-Ilan University in Israel reveal that the brain learns completely differently than has been assumed since the 20th century. The new experimental observations suggest that learning is mainly performed in neuronal dendritic trees, where the trunk and branches of the tree modify their strength, as opposed to modifying solely the strength of the synapses (dendritic leaves), as was previously thought. These observations also indicate that the neuron is actually a much more complex, dynamic and computational element than a binary element that can fire or not. Just one single neuron can realize deep learning algorithms, which previously required an artificial complex network consisting of thousands of connected neurons and synapses. The new demonstration of efficient learning on dendritic trees calls for new approaches in brain research, as well as for the generation

Scientists use machine learning to identify antibiotic resistant bacteria that can spread between animals, humans and the environment

Experts from the University of Nottingham have developed a ground-breaking software, which combines DNA sequencing and machine learning to help them find where, and to what extent, antibiotic resistant bacteria is being transmitted between humans, animals and the environment.

Matt Ajemian, Ph.D., Receives Prestigious NSF CAREER Award

Matt Ajemian, Ph.D., has received a $1,103,081 NSF CAREER grant for a project that will build fundamental knowledge on where and when large shell-crushing predators feed in order to ensure a sustainable future for shellfish species. Further, the work can provide guidance to shellfish restoration programs that are currently “flying blind” with respect to predation risk.

AF2Complex: Researchers Leverage Deep Learning to Predict Physical Interactions of Protein Complexes

Proteins are the molecular machinery that makes life possible, and researchers have long been interested in a key trait of protein function: their three-dimensional structure. A new study by Georgia Tech and Oak Ridge National Laboratory details a computational tool able to predict the structure protein complexes – and lends new insights into the biomolecular mechanisms of their function.

Machine Learning Helps Predict Protein Functions

To engineer proteins for specific functions, scientists change a protein sequence and experimentally test how that change alters its function. Because there are too many possible amino acid sequence changes to test them all in the laboratory, researchers build computational models that predict protein function based on amino acid sequences. Scientists have now combined multiple machine learning approaches for building a simple predictive model that often works better than established, complex methods.

Artificial intelligence paves the way to discovering new rare-earth compounds

Artificial intelligence advances how scientists explore materials. Researchers from Ames Laboratory and Texas A&M University trained a machine-learning (ML) model to assess the stability of rare-earth compounds. The framework they developed builds on current state-of-the-art methods for experimenting with compounds and understanding chemical instabilities.

LLNL-led team uses machine learning to derive black hole motion from gravitational wave data

A team including a Lawrence Livermore National Laboratory (LLNL) mathematician and collaborators at the University of Massachusetts, Dartmouth and the University of Mississippi, has developed a machine learning-based technique capable of automatically deriving the motion of binary black holes from raw gravitational wave data.

Novel Tag Provides First Detailed Look into Goliath Grouper Behavior

A study is the first to reveal detailed behavior of massive goliath groupers. Until now, no studies have documented their fine-scale behavior. What is known about them has been learned from divers, underwater video footage, and observing them in captivity. Using a multi-sensor tag with a three axis accelerometer, gyroscope and magnetometer as well as a temperature, pressure and light sensor, a video camera and a hydrophone, researchers show how this species navigates through complex artificial reef environments, maintain themselves in high current areas, and how much time they spend in different cracks and crevices – none of which would be possible without the tag.

Researchers create a breakthrough tool for superfast molecular movies

Certain biological events, such as proteins changing their shapes to perform some functions, occur so quickly that current methods of molecular imaging cannot capture them. Now, a research team has created a machine-learning technique that can “fill in” missing data needed to document proteins in action in time scales of a few quadrillionths of a second.

DOE grants will help advance AI techniques to address data challenges

Argonne scientists have received two high-profile grants from the U.S. Department of Energy that will help scientists at the U.S. National Laboratories take advantage of the latest developments in machine learning technology.

Computational discovery of complex alloys could speed the way to green aviation

Experts at the U.S. Department of Energy’s Ames Laboratory and their collaborators have identified the way to tune the strength and ductility of a class of materials called high-entropy alloys. The discovery may help power-generation and aviation industry develop more efficient engines.

UA Little Rock Postdoctoral Researcher Receives $40K Grant to Create Predictive Modeling of Refugee Numbers

The Arkansas Economic Development Commission, using flow-through funding from the National Science Foundation, has awarded a postdoctoral research fellow at UA Little Rock a grant worth more than $40,000 to create a machine learning model to predict refugee counts in the United States.

All About Eve

New AI model called EVE, developed by scientists at Harvard Medical School and Oxford University, outperforms other AI methods in determining whether a gene variant is benign or disease-causing.
When applied to more than 36 million variants across 3,219 disease-associated proteins and genes, EVE indicated more than 256,000 human gene variants of unknown significance that should be reclassified as benign or pathogenic.

AI-driven dynamic face mask adapts to exercise, pollution levels

Researchers reporting in ACS Nano have developed a dynamic respirator that modulates its pore size in response to changing conditions, such as exercise or air pollution levels, allowing the wearer to breathe easier when the highest levels of filtration are not required.

FAU Receives NSF Grant to Explore Trait Evolution Across Species

The NSF grant will enable scientists to elucidate trait evolution across species using statistical and supervised machine learning approaches to vigorously and accurately predict general and specific evolutionary mechanisms that also will be applicable to various genomic and transcriptomic data for evolutionary discovery.

New machine learning method to analyze complex scientific data of proteins

Scientists have developed a method using machine learning to better analyze data from a powerful scientific tool: nuclear magnetic resonance (NMR). One way NMR data can be used is to understand proteins and chemical reactions in the human body. NMR is closely related to magnetic resonance imaging (MRI) for medical diagnosis.

Argonne and Parallel Works Inc. win FLC recognition for commercializing lab’s machine learning-based design optimization software technology

Argonne and Parallel Works, Inc., won the Federal Laboratory Consortium’s Midwest Regional Award for Excellence in Technology Transfer for bringing Argonne’s Machine Learning-Genetic Algorithm (ML-GA) design optimization software to commercialization.

Department of Energy Invests $1 Million in Artificial Intelligence Research for Privacy-Sensitive Datasets

The U.S. Department of Energy (DOE) announced $1 million for a one-year collaborative research project to develop artificial intelligence (AI) and machine learning (ML) algorithms for biomedical, personal healthcare, or other privacy-sensitive datasets.