Researchers developed an AI algorithm to predict the properties of new 2D materials with point defects, achieving 3.7 times greater accuracy than other machine learning algorithms. The model operates 1000 times faster than quantum mechanical computations and can handle multiple defects simultaneously.
Researchers create a new privacy metric, Probably Approximately Correct (PAC) Privacy, that enables the addition of minimal noise to protect sensitive data. The algorithm automatically determines the optimal amount of noise needed without requiring knowledge of the inner workings of the model or training process.
A Lehigh University professor has received $4 million in NIH grants to develop an AI-driven approach for precision mental health diagnosis and care. The project aims to identify biomarkers in the brain that can predict treatment response and personalize interventions for patients with depression and other mental disorders.
A new machine learning-based simulation method called Materials Learning Algorithms (MALA) has been developed, enabling accurate electronic structure calculations at large scales. MALA achieves this by utilizing a hybrid approach that combines physics-based approaches with machine learning to predict the electronic structure of materials.
The study combines real and robotic insects to understand how they sense forces in their limbs while walking. Campaniform sensilla (CS) are force receptors found in insect limbs that respond to stress and strain, providing critical information for controlling locomotion.
The University of Houston's CYBER-CARE research center aims to prevent cyberattacks that could compromise the safe movement of people and goods in the US. The center will focus on four goals, including exploring advanced theories to mitigate the impact of large-scale cyberattacks.
Researchers at EPFL have found a way to teach quantum computers to learn and process information using principles inspired by quantum mechanics. By training quantum neural networks (QNNs) on a few simple examples called 'product states', the computer can effectively grasp complex dynamics of entangled quantum systems.
Researchers at Nagoya University developed an AI-based technique to predict crystal orientation in polycrystalline materials, revolutionizing the industry. The method uses optical photographs and reduces measurement time from 14 hours to 1.5 hours, enabling large-area materials analysis.
A new computer model forecasts yield for four key crops in the southeastern US, drawing on climate, groundwater, and agricultural data. The tool helps farmers and water resource managers identify ways to maximize crop yields while efficiently utilizing water and energy.
A team of researchers at UC Irvine has developed a freely available computer model to estimate the economic costs of hurricanes and typhoons. The model combines data from climate change science and household vulnerability information, providing return periods of asset losses and helping countries better prepare for these disasters.
Research highlights how generative AI models encode biases and negative stereotypes in their users, particularly marginalised groups. This can lead to the mass generation and spread of nonsensical information, influencing human beliefs and perpetuating existing inequalities.
A new study models the spread of African swine fever in US swine farms, finding that control actions can reduce secondary infections by up to 79% but an outbreak could still be persistent and costly. The model suggests that between-farm movements are the primary route of transmission.
Researchers at the University of Washington created an app called FeverPhone that uses existing phone sensors and screens to estimate whether people have fevers. The app was tested on 37 patients in an emergency department and showed accuracy comparable to consumer thermometers, with potential for early intervention in viral outbreaks.
A virtual reality project, Qikiqtaruk: Arctic at Risk, visualizes the impacts of climate change in the Canadian Arctic. The project, created by National Geographic Explorers and local communities, uses immersive technology to transport users to an island experiencing rapid thawing and environmental changes.
Researchers have developed a simulation of how people behave on roads based on cognitive theories, accurately reproducing pedestrian and driver behaviors in common scenarios. The model predicts complex underlying cognitive mechanisms that contribute to the difficulty in creating self-driving vehicles.
The UK is investing £11 million to improve forecast accuracy for extreme weather events like storms, floods and droughts. Scientists are focusing on atmospheric turbulence to create more detailed models.
A team of researchers from Syracuse University and Texas A&M University applied a machine learning model to explore the sources of salinization and alkalinization in U.S. watersheds. The study found that human activities, such as road salt application, were major contributors to salinity, while natural processes dominated alkalinity.
A study by Dartmouth's Geisel School of Medicine found that Medicare fraud in home healthcare billing spread rapidly across U.S. regions between 2002 and 2009, driven by characteristics such as shared patients, high expenditures, and rapid growth in the number of home health agencies. The researchers developed a novel network analysis ...
The study uses neural recordings and computer modeling to show that phonetic information is encoded differently when speech stands out versus being drowned out. This finding could help develop more accurate hearing aids.
A recent study has found that microbes play a crucial role in storing carbon in the soil, with a four-fold greater importance than other processes. This breakthrough could lead to improved soil health and increased food security through targeted farm management practices.
Researchers updated their protein localization prediction model, MULocDeep, to provide more targeted predictions for biological discoveries. The tool helps researchers design more effective experiments and advance scientific discoveries related to drug development and treating diseases like epilepsy.
A new research effort aims to provide decision-makers with better information to understand supply chain risks, vulnerabilities, and resilience through visual analytics. The project will create a comprehensive computational and visual analytic environment to identify patterns and interdependencies in supply-demand systems.
A new Danish research project, CP-SENS, aims to develop a digital twin platform for the mechanical and construction industries. The project will provide companies with access to intelligent IT systems tailored to their needs, enabling them to adopt digital twins without significant financial investment.
A recent study published in the Proceedings of the National Academy of Sciences found that officers' first 45 words during a vehicle stop with a Black driver can indicate how the stop will end. The study discovered a unique 'linguistic signature' that characterizes escalated stops, where officers give an order without stating the reaso...
Researchers used AI to identify a compound that kills Acinetobacter baumannii, a bacterium responsible for many drug-resistant infections. The new antibiotic shows promise in combating this growing public health threat.
Researchers at MIT have developed a new approach to match 3D shapes by mapping volumes to volumes, resulting in more accurate animations and CAD designs. This method represents shapes as tetrahedral meshes that include the mass inside a 3D object, allowing for better modeling of fine parts and avoiding common artifacts.
Hanna Kokko, a renowned theoretical evolutionary biologist, has been awarded the Alexander von Humboldt Professorship for her groundbreaking research on the interplay between evolutionary and ecological factors. She will receive EUR 3.5 million to establish her research team and obtain necessary equipment and facilities.
Researchers developed AI model QUADL that can create online assessment questions indistinguishable from human-written ones. Instructors found QUADL's questions as effective as those written by humans in assessing student learning objectives. The study suggests QUADL can be a useful tool for instructors and course developers.
Researchers discovered that certain bacterial species, including lactic acid bacteria, correlate with high levels of Candida yeasts in the gut microbiome. This suggests a complex interaction between these microorganisms, where lactic acid bacteria may favor Candida proliferation while making the fungus less virulent.
Researchers develop chitosan-based coating to preserve avocados and create imaging technique to predict shelf life. The coating delays ripening, and the imaging method accurately estimates remaining shelf life, potentially improving avocado quality and availability.
Researchers used AI to analyze speech patterns of patients with Parkinson's disease, finding they spoke in shorter sentences with more verbs and fewer common nouns. The study suggests potential early detection methods for the condition through conversational analysis.
Researchers used AI to study how the hippocampus produces varied replay types efficiently and their purpose. The model showed that sequences are prioritized stochastically according to familiarity and reward positions.
The new model maximizes coverage area and minimizes response time, accounting for hot spots. It outperformed existing techniques in computational testing, improving response times regardless of traffic size.
Researchers at UChicago found a surprising connection between photosynthesis and exciton condensates, a state that allows frictionless energy flow. The discovery could lead to more efficient materials and technologies, such as superconductors.
Researchers identified three novel dual-purpose therapeutic targets using PandaOmics, which could treat both aging and glioblastoma multiforme. The target hypotheses include cyclic nucleotide gated channel subunit alpha 3 (CNGA3), glutamate dehydrogenase 1 (GLUD1) and sirtuin 1 (SIRT1).
A team of researchers from Carnegie Mellon University has developed an AI-based system to help clinicians make decisions quickly and precisely in the ICU. The system, called the AI Clinician Explorer, provides recommendations for treating sepsis based on data from over 18,000 patients.
Researchers at Cedars-Sinai created computational models to bridge the gap between
A study at Kyoto University has demonstrated the computational power of ecological networks, providing a new direction for rapidly developing AI technologies. The researchers developed two types of ecological reservoir computing that efficiently process information and can be utilized as a computational resource.
The new CALANGO software helps untangle genetic factors associated with shared characteristics, such as antibacterial resistance and agricultural improvements. It enables scientists to explore vast amounts of genomic data across thousands of organisms.
Researchers propose a 'state space' approach to reframe farming planning questions, enabling analytics and machine learning to explore optimal crop combinations and simulate different scenarios. This framework allows farmers to design diverse agricultural landscapes based on natural ecosystems, increasing crop yield and sustainability.
Researchers used computational modeling to identify ultrastable MOF structures, which could be useful for gas storage and catalysis. The study found that about 10,000 of the predicted structures were stable enough for these applications, with high deliverable capacities for methane.
Max Planck scientists explore the possibilities of artificial intelligence in materials science, discussing how combining physics-based modeling with AI can unlock complex material designs. The research focuses on overcoming limitations of traditional methods and handling sparse, noisy data.
A new model of DNA flexibility has been developed, providing results of unprecedented quality and characterizing precision and efficiency at the computational level. The study presents a systematic and comprehensive analysis of DNA movement correlations and introduces a new method to capture them.
A WPI-led team used computational modeling to create a detailed picture of the SARS-COV-2 virus envelope, revealing its elliptical shape and changing structure. This discovery could lead to more effective therapies and vaccines, as well as a better understanding of the virus's properties.
A recent study from Brigham Young University proves that artificial intelligence can respond to complex survey questions just like a real human. The researchers found high correspondence between how AI and humans voted in 2012, 2016, and 2020 U.S. presidential elections.
Researchers at NIST have developed a new method of digitally simulating hurricanes using AI techniques, accurately representing the trajectory and wind speeds of real storms. The simulations can help develop improved guidelines for building design in hurricane-prone regions.
Researchers found that fish in large schools are more willing to take risks and tune down their sensitivity to social cues, reducing the likelihood of responding to false alarms. This dynamic adjustment allows individuals to maintain control over their behavior, suggesting a potential evolutionary advantage in coping with misinformation.
A new study found that repeated requests for personal data increase disclosure, despite unchanged concerns about privacy. Researchers suggest practical measures to reduce this effect and encourage mutually beneficial sharing.
Researchers at the Human Brain Project present novel clinical uses of advanced brain modelling methods, enabling clinicians to simulate epileptic seizures and identify target areas. The approach has broad applicability in neuroscience, medicine, and neurotechnology, with potential improvements in data resolution and patient specificity.
Researchers developed a computer model based on human brain mechanisms to improve speech comprehension. The model extracts multilevel information from ongoing speech and uses non-linguistic knowledge for disambiguating word meanings. This approach is more human-like than existing language models like ChatGPT.
Richard McIndoe is leading a national research initiative to advance understanding of diabetes and obesity through the National Centers for Metabolic Phenotyping in Live Models of Obesity and Diabetes (MPMOD). The MPMOD initiative provides access to advanced testing services, including bariatric surgery on mice, to enable new insights ...
QUT researchers have solved a long-held geological conundrum about how diamonds formed in the deep roots of the earth's ancient continents. The study used computer modeling on an ancient rock sample to determine that diamonds are rare today and were always rare, challenging the existing explanation.
Researchers develop unsupervised machine learning algorithm to classify osteosarcoma at diagnosis based on gene expression modules. This approach enables personalized treatment strategies for osteosarcoma patients.
ISB researchers constructed a biological body mass index that offers a more accurate representation of metabolic health. The team found that even with no weight loss, individuals can be getting healthier biologically through positive lifestyle changes.
Antimicrobial resistance poses a major threat to human health, with an estimated 4.95 million deaths worldwide in 2019. Researchers identified four research priorities to improve predictive models for antimicrobial-resistant organisms, including better communication and data collection.
Researchers developed an economic-epidemiological model to assess the impact of no closures. The study found that California's unemployment rate would have been lower, but deaths and hospitalizations from COVID-19 would have increased significantly, exacerbating current inequities.
Researchers at University of Birmingham develop AI diagnostic tool to predict ulcerative colitis flare-ups with 89% accuracy. The system identifies markers of inflammation and healing, providing analytical support for clinicians in managing the disease.
Researchers at Cornell University developed a new model called swarmalators, which can simulate swarming behaviors and synchronized timing in microrobots. The model mimics diverse emergent phenomena, such as aggregation, dispersion, and vortices, and can be used for precision medicine and drone applications.
Researchers seek to develop algorithms providing meaningful explanations for AI decision-making, enabling higher human trust and adoption in fields like science. The project focuses on symbolic reasoning and estimating explanation accuracy, addressing the need for transparent AI systems.
A review of 25 years of AI health tech research found that only 24% of studies include patient-reported outcomes, but there has been an increase in recent years. Experts emphasize the importance of integrating patient voices into AI models to support personalized care and prevent digitalization of healthcare.