Add BrightSurf on Google Email

Drug discovery on an unprecedented scale

A recent study published in the Journal of Chemical Information and Modeling presents a significant breakthrough in accelerating giga-scale virtual screens using machine learning. The researchers successfully reduced processing time by 10-fold for 1.56 billion drug-like molecules, identifying top-scoring compounds in under ten days.

SourceUniversity of Eastern Finland·JournalJournal of Chemical Information and Modeling·TypeComputational simulation/modeling·DateSep 25, 2023

Machine learning unravels mysteries of atomic shapes

Researchers used machine learning to expand and accelerate work on 'atomic shapes,' fundamental pieces of geometry in higher dimensions. The breakthrough identifies shapes and their properties, such as dimension, accelerating new insights across Pure Mathematics.

SourceUniversity of Nottingham·JournalNature Communications·TypeComputational simulation/modeling·DateSep 25, 2023

AI increases precision in plant observation

Researchers at the University of Zurich developed PlantServation, a method that enables scientists to observe plants with great precision using AI and machine learning. The technique allows for the analysis of millions of images taken from various weather conditions, providing insights into how plants respond to environmental factors.

SourceUniversity of Zurich·JournalNature Communications·TypeImaging analysis·DateSep 22, 2023
Nikon Monarch 5 8x42 Binoculars

Nikon Monarch 5 8x42 Binoculars deliver bright, sharp views for wildlife surveys, eclipse chases, and quick star-field scans at dark sites.

Machine learning models can produce reliable results even with limited training data

Researchers from University of Cambridge and Cornell University have developed a method to build machine learning models that can understand complex equations using far less training data. This breakthrough enables the construction of more time- and cost-efficient models for physics, engineering, and climate modeling applications.

SourceUniversity of Cambridge·JournalProceedings of the National Academy of Sciences·DateSep 19, 2023

Modernizing the Navy’s microgrids

The project aims to assess the operational resilience of microgrids on DoD installations and ships, using new operational resilience indexes developed by Lehigh University researcher Javad Khazaei. The team will develop a dashboard to monitor resilience indexes in real-time, providing recommendations for improving the systems.

SourceLehigh University·DateSep 19, 2023
SAMSUNG T9 Portable SSD 2TB

SAMSUNG T9 Portable SSD 2TB transfers large imagery and model outputs quickly between field laptops, lab workstations, and secure archives.

Assessing unintended consequences in AI-based neurosurgical training

A new study found that AI-tutored students caused less damage to healthy tissues and improved safety measures, but also showed negative outcomes such as reduced efficiency and speed. Human instructors are essential to promote both safety and efficiency in neurosurgical training.

SourceMcGill University·JournalJAMA Network Open·TypeRandomized controlled/clinical trial·DateSep 19, 2023

Creation of training data to estimate the states of care robot users

A research team at Toyohashi University of Technology has developed a technique to create training data for robots that estimate the state of users using machine learning. The method uses a human body link model without requiring movement analysis, enabling care robots to assist elderly with reduced burden and improved safety.

SourceToyohashi University of Technology (TUT)·JournalIEEE Access·TypeExperimental study·DateSep 19, 2023

AI and machine learning can successfully diagnose polycystic ovary syndrome

Researchers found that AI/ML based programs can successfully detect PCOS with an accuracy of 80-90%, making it a promising tool for early diagnosis and reducing the burden on patients. The study suggests integrating large population-based studies with electronic health datasets to identify sensitive diagnostic biomarkers.

SourceNIH/National Institute of Environmental Health Sciences·JournalFrontiers in Endocrinology·TypeSystematic review·DateSep 18, 2023
Apple iPhone 17 Pro

Apple iPhone 17 Pro delivers top performance and advanced cameras for field documentation, data collection, and secure research communications.

Study: No evidence that YouTube promoted anti-vaccine content during COVID-19 pandemic

A study by researchers at the University of Illinois Urbana-Champaign found that YouTube's recommendation system did not promote anti-vaccine content during the COVID-19 pandemic. The study analyzed over 27,000 video recommendations and found that users were directed to longer, more popular health-related content.

SourceUniversity of Illinois at Urbana-Champaign, News Bureau·JournalJournal of Medical Internet Research·TypeData/statistical analysis·DateSep 15, 2023

Using topology, Brown researchers advance understanding of how cells organize themselves

Using computational topology, Brown researchers have developed an algorithm that profiles shapes and spatial patterns in embryos, enabling the study of how cells assemble into tissue-like architectures. The new approach uses persistence images to rapidly compare large datasets, reducing computation time from hours to seconds.

SourceBrown University·Journalnpj Systems Biology and Applications·DateSep 14, 2023

UTHealth Houston study: Unruptured brain aneurysms may be missed in routine clinical care, but AI-powered algorithm can help

A new study from UTHealth Houston finds that AI-powered algorithm can improve detection rates of unruptured cerebral aneurysms. The study used a machine learning algorithm to analyze CT angiograms and identified 36 true aneurysms, with 24 previously not referred for follow-up.

SourceUniversity of Texas Health Science Center at Houston·JournalStroke Vascular and Interventional Neurology·DateSep 13, 2023

‘Computer vision’ reveals unprecedented physical and chemical details of how a lithium-ion battery works

A new method of analyzing nanoscale X-ray movies reveals unprecedented insights into how lithium-ion batteries store and release charge. The study suggests ways to improve the efficiency of billions of nanoparticles in electrode materials, potentially leading to faster-charging batteries.

SourceDOE/SLAC National Accelerator Laboratory·JournalNature·TypeExperimental study·DateSep 13, 2023
Fluke 87V Industrial Digital Multimeter

Fluke 87V Industrial Digital Multimeter is a trusted meter for precise measurements during instrument integration, repairs, and field diagnostics.

Scientists studied optimal multi-impulse linear rendezvous via reinforcement learning

Researchers propose a reinforcement learning-based approach to optimize multi-impulse linear rendezvous trajectories, achieving faster computation times and improved fuel efficiency compared to traditional numerical optimization methods. The algorithm uses an actor-critic architecture and advantage-weighted learning to accelerate train...

SourceBeijing Institute of Technology Press Co., Ltd·JournalSpace: Science & Technology·DateSep 12, 2023
Meta Quest 3 512GB

Meta Quest 3 512GB enables immersive mission planning, terrain rehearsal, and interactive STEM demos with high-resolution mixed-reality experiences.

Large amounts of sedentary time linked with higher risk of dementia in older adults, study shows

A new study published in JAMA found that adults over 60 who spend more than 10 hours a day engaging in sedentary behaviors like sitting are at increased risk of developing dementia. The study used wearable accelerometers to track physical activity and found that the total time spent sedentary each day was a significant predictor of dem...

SourceUniversity of Southern California·JournalJAMA·TypeObservational study·DateSep 12, 2023

Researchers discover genes behind antibiotic resistance in deadly superbug infections

Australian researchers analyzed over 1,300 Golden staph strains, linking specific genes to antibiotic resistance and the bacteria's ability to linger in the bloodstream. The study highlights the diagnostic power of integrating clinical and genomic data to develop targeted solutions for deadly superbug infections.

SourceThe Peter Doherty Institute for Infection and Immunity·JournalCell Reports·TypeData/statistical analysis·DateSep 12, 2023

Not too big: Machine learning tames huge data sets

A Los Alamos-developed machine learning algorithm successfully processed massive data sets exceeding a computer's available memory. The algorithm divides data into manageable batches to prevent hardware bottlenecks, enabling efficient processing of large-scale applications in various fields.

SourceDOE/Los Alamos National Laboratory·JournalThe Journal of Supercomputing·TypeExperimental study·DateSep 11, 2023

Drug approvals in clinical trials were correlated with the cells/humans discrepancy in gene perturbation effects

A recent study has successfully predicted potential drug outcomes and side effects by analyzing the discrepancy in gene perturbation effects between cells and humans. Researchers used machine learning to forecast drug approvals, improving reliability over conventional methods that only consider chemical properties.

SourcePohang University of Science & Technology (POSTECH)·JournalEBioMedicine·DateSep 8, 2023
Apple Watch Series 11 (GPS, 46mm)

Apple Watch Series 11 (GPS, 46mm) tracks health metrics and safety alerts during long observing sessions, fieldwork, and remote expeditions.

Machine learning contributes to better quantum error correction

Researchers from RIKEN Center for Quantum Computing have used machine learning to perform efficient quantum error correction using an autonomous system that can determine the best corrections despite being approximate. Machine learning plays a crucial role in addressing large-scale quantum computation and optimization challenges.

SourceRIKEN·JournalPhysical Review Letters·TypeComputational simulation/modeling·DateSep 7, 2023

Measuring and Predicting collision cross section (CCS) values for unknown compounds

Researchers developed methods to predict CCS values using machine learning and computer models, offering a faster alternative to experimental determination. The study's findings provide a foundation for measurements using portable ion mobility spectrometers in the future.

SourceAuburn University College of Sciences and Mathematics·JournalJournal of Mass Spectrometry·TypeLiterature review·DateSep 5, 2023
Rigol DP832 Triple-Output Bench Power Supply

Rigol DP832 Triple-Output Bench Power Supply powers sensors, microcontrollers, and test circuits with programmable rails and stable outputs.

Acting fast when an epidemic hits

A team of researchers at the University of Waterloo and Dalhousie University have developed a method for forecasting short-term disease progression using limited data. The Sparsity and Delay Embedding-based Forecasting model, or SPADE4, uses machine learning to predict epidemic progressions with high accuracy.

SourceUniversity of Waterloo·JournalBulletin of Mathematical Biology·DateAug 31, 2023

An ‘introspective’ AI finds diversity improves performance

A new study by North Carolina State University found that artificial intelligence performs better when it chooses diversity over lack of diversity. The AI was able to increase its accuracy up to 10 times more than conventional AI in solving complicated problems.

SourceNorth Carolina State University·JournalScientific Reports·TypeComputational simulation/modeling·DateAug 31, 2023

Better paths yield better AI

Researchers from Bar-Ilan University improved AI classification tasks by choosing the most influential path to the output, rather than learning with deeper networks. This approach can enhance existing architectures and pave the way for improved AI systems without additional layers.

SourceBar-Ilan University·JournalScientific Reports·DateAug 31, 2023

Energy storage in molecules

A team of researchers has discovered a particularly efficient molecular structure for solar energy storage materials, which could lead to more efficient solar energy harvesting. The new molecules were identified by screening over 400,000 molecules with the help of machine learning and quantum computing.

SourceWiley·JournalAngewandte Chemie International Edition·TypeComputational simulation/modeling·DateAug 30, 2023
Creality K1 Max 3D Printer

Creality K1 Max 3D Printer rapidly prototypes brackets, adapters, and fixtures for instruments and classroom demonstrations at large build volume.

Challenge accepted: High-speed AI drone overtakes world-champion drone racers

A team of researchers from the University of Zurich and Intel has developed an AI system called Swift that can beat human champions in drone racing. The autonomous drone achieved the fastest lap, winning multiple races against three world-class champions, but human pilots proved more adaptable to changing conditions.

SourceUniversity of Zurich·JournalNature·TypeExperimental study·DateAug 30, 2023

AI helps ID cancer risk factors

A novel study from the University of South Australia identified 84 features that could signal increased cancer risk in a dataset of 459,169 UK Biobank participants. The study found several biomarkers linked to cancer risk, including urinary microalbumin and high levels of cystatin C.

SourceUniversity of South Australia·JournalEuropean Journal of Clinical Investigation·TypeData/statistical analysis·DateAug 30, 2023

Unveiling global warming’s impact on daily precipitation with deep learning

A deep learning approach has unveiled a significant change in the characteristics of global daily precipitation for the first time. The research found that on more than 50% of all days, there was a clear deviation from natural variability in the daily precipitation pattern since 2015.

SourcePohang University of Science & Technology (POSTECH)·JournalNature·DateAug 30, 2023
Apple AirPods Pro (2nd Generation, USB-C)

Apple AirPods Pro (2nd Generation, USB-C) provide clear calls and strong noise reduction for interviews, conferences, and noisy field environments.

Tracking drivers’ eyes can determine ability to take back control from ‘auto-pilot’ mode

A new method can detect drivers' attention levels from their eye movements, enabling the development of more effective takeover signals. The study found that drivers who are engrossed in on-screen activities take longer to respond to warnings, highlighting a potential safety concern.

SourceUniversity College London·JournalCognitive Research Principles and Implications·TypeExperimental study·DateAug 30, 2023

Neural network helps design brand new proteins

Researchers have developed a novel neural network approach to design brand new proteins with unique arrangements and dynamic functionalities. The method combines attention neural networks with graph neural networks to predict existing protein properties and envision new proteins that nature has not yet devised.

SourceAmerican Institute of Physics·JournalJournal of Applied Physics·DateAug 29, 2023
Apple MacBook Pro 14-inch (M4 Pro)

Apple MacBook Pro 14-inch (M4 Pro) powers local ML workloads, large datasets, and multi-display analysis for field and lab teams.

AI-powered triage platform could aid future viral outbreak response

A new AI-powered triage platform uses machine learning and metabolomics data to predict patient disease severity and length of hospitalization during a viral outbreak. The platform integrates routine clinical data, patient comorbidity information, and untargeted plasma metabolomics data to drive its predictions.

SourceYale University·JournalHuman Genomics·DateAug 29, 2023

How fast does the charge migrate in molecules?

Scientists have successfully measured the speed of molecular charge migration in a carbon-chain molecule, revealing a movement of several angstroms per femtosecond. The study used a two-color high harmonic spectroscopy scheme with machine learning reconstruction to achieve a temporal resolution of 50 as.

SourceSPIE--International Society for Optics and Photonics·JournalAdvanced Photonics·DateAug 25, 2023

Food recognition and logging: New research focuses on local Singaporean food

Researchers at Singapore Management University aim to create a robust machine learning system capable of correctly identifying Singapore's multiracial food. The project focuses on addressing biases in current systems and developing an algorithm that can recognize a wide range of dishes, including those beyond popular online trends.

SourceSingapore Management University·DateAug 25, 2023

AI helps robots manipulate objects with their whole bodies

Researchers at MIT developed a method to simplify the process of whole-body manipulation for robots, enabling them to reason efficiently about moving objects. The technique uses AI and smoothing to reduce the number of decisions required, making it possible for robots to adapt quickly in complex environments.

SourceMassachusetts Institute of Technology·JournalIEEE Transactions on Robotics·DateAug 24, 2023

Sweet corn yield at the mercy of the environment, except for one key factor

A new study by the University of Illinois and USDA-Agricultural Research Service has identified the key factors influencing sweet corn yield. The analysis found that seed source is a significant variable, with processors having a choice over which hybrids to use, and high nighttime temperatures also impact yield.

SourceUniversity of Illinois College of Agricultural, Consumer and Environmental Sciences·JournalPrecision Agriculture·DateAug 24, 2023
Garmin GPSMAP 67i with inReach

Garmin GPSMAP 67i with inReach provides rugged GNSS navigation, satellite messaging, and SOS for backcountry geology and climate field teams.

ChatGPT shows ‘impressive’ accuracy in clinical decision making

A new study found ChatGPT to be nearly 72 percent accurate across all medical specialties and phases of clinical care. It was also 77 percent accurate in making final diagnoses. However, the model struggled with differential diagnosis, which is a crucial aspect of medicine.

SourceMass General Brigham·JournalJournal of Medical Internet Research·TypeComputational simulation/modeling·DateAug 22, 2023

AI can predict certain forms of esophageal and stomach cancer

A new AI tool predicts certain forms of esophageal and stomach cancer at least three years prior to diagnosis. The K-ECAN tool uses basic EHR data to identify high-risk patients, who may benefit from earlier screening and preventative measures.

SourceMichigan Medicine - University of Michigan·JournalGastroenterology·TypeComputational simulation/modeling·DateAug 22, 2023

AI to predict critical care for patients with COVID-19

Researchers developed a deep-learning model to assess CXR images for probable COVID-19 severity. The model achieved an area under the receiver operating characteristic curve of 0.78 when predicting intensive care need within 24 hours.

SourceSPIE--International Society for Optics and Photonics·JournalJournal of Medical Imaging·DateAug 21, 2023

New “bandit” algorithm uses light for better bets

Researchers developed a modified bandit Q-learning algorithm that aims to learn optimal Q values for every state-action pair, balancing exploitation and exploration. The scheme relies on photonic systems to enhance learning quality, accelerating parallel learning through conflict-free decision-making.

SourceIntelligent Computing·JournalIntelligent Computing·DateAug 21, 2023
GQ GMC-500Plus Geiger Counter

GQ GMC-500Plus Geiger Counter logs beta, gamma, and X-ray levels for environmental monitoring, training labs, and safety demonstrations.

Using big data on livestock farms could improve antimicrobial resistance surveillance

A new study reveals that using big data and machine learning can improve antimicrobial resistance surveillance in livestock production. The research found correlations between environmental variables, microbial communities, and antimicrobial resistance, suggesting multiple routes for improving surveillance.

SourceUniversity of Nottingham·JournalNature Food·TypeData/statistical analysis·DateAug 18, 2023

For a new generation of antibiotics, scientists are bringing extinct molecules back to life – and discovering the hidden genetics of immunity along the way

Researchers at the University of Pennsylvania School of Engineering and Applied Science have discovered dozens of small protein sequences with antibiotic qualities in extinct organisms like Neanderthals and Denisovans. They then synthesized these molecules using artificial intelligence and tested their efficacy against pathogens.

SourceUniversity of Pennsylvania School of Engineering and Applied Science·JournalCell Host & Microbe·DateAug 16, 2023

Studying the theoretical limit of learned source coding

A team led by Dr. Zixiang Xiong at Texas A&M University aims to understand the fundamental limits of learned source coding, a machine learning-based data compression method. They hope to develop more powerful compression methods for efficient use of wireless communication and less energy consumption by mobile devices.

SourceTexas A&M University·DateAug 16, 2023

Google Trends data can improve predictions of football players’ market value

Researchers developed a novel method using Google Trends to assess player popularity and demonstrated its improvement in predicting market value. The method involves calculating six indicators of popularity that can be compared among players, improving accuracy when incorporated with other factors.

SourcePLOS·JournalPLOS ONE·TypeComputational simulation/modeling·DateAug 16, 2023
DJI Air 3 (RC-N2)

DJI Air 3 (RC-N2) captures 4K mapping passes and environmental surveys with dual cameras, long flight time, and omnidirectional obstacle sensing.

AI models are powerful, but are they biologically plausible?

Researchers propose a hypothesis that astrocytes, non-neuronal cells in the brain, can perform core computation as transformers, providing insights into human brain function and machine learning success. This discovery could spark future neuroscience research and help explain transformer performance across complex tasks.

SourceMassachusetts Institute of Technology·JournalProceedings of the National Academy of Sciences·DateAug 15, 2023

Can AI help hospitals spot patients in need of extra non-medical assistance?

A new study shows that a rule-based natural language processing tool successfully identified patients with unstable access to transportation, food insecurity, social isolation, financial problems, and signs of abuse or exploitation. The tool performed better than deep learning algorithms in identifying these social determinants of health.

SourceMichigan Medicine - University of Michigan·JournalHealth Services Research·TypeData/statistical analysis·DateAug 14, 2023

Artificial intelligence designs advanced materials

Scientists at Max-Planck-Institut für Eisenforschung developed a machine learning model that enhances predictive accuracy in alloy design, uncovering new corrosion-resistant compositions. The model combines numerical and textual data, enabling the identification of optimal alloy formulas.

SourceMax-Planck-Gesellschaft·JournalScience Advances·DateAug 11, 2023
Anker Laptop Power Bank 25,000mAh (Triple 100W USB-C)

Anker Laptop Power Bank 25,000mAh (Triple 100W USB-C) keeps Macs, tablets, and meters powered during extended observing runs and remote surveys.

How sure is sure? Incorporating human error into machine learning

A team of researchers from the University of Cambridge developed a way to incorporate human error into machine learning systems, improving their performance in handling uncertain feedback. However, they found that even with uncertainty accounted for, hybrid systems still perform worse than standalone machine learning models.

SourceUniversity of Cambridge·DateAug 9, 2023