Research using machine learning to solve scientific problems. Covers AI quality control, sea-surface temperature estimation, label-free cell analysis, and cyber defense.
Machine learning helps researchers discover how bacterial populations adapt to environmental diversity by analyzing growth curves. The analysis reveals distinct decision-making components for lag, growth, and saturation phases, protecting the population from extinction.
Researchers created IGLUE to score ML efficiency in 20 languages, addressing cultural bias and practical implications. The tool aims to improve solutions for visually impaired and reduce performance dropouts outside English-speaking contexts.
Researchers at UMaine have developed a novel AI-based method for monitoring soil moisture in forests, using wireless sensor networks and machine learning to optimize energy efficiency. This approach could enable more efficient tracking of forest health, reducing costs and increasing reliability.
Researchers developed a new machine-learning method to understand force chains in jammed granular solids. The graph neural network approach can predict the position of force chains with high accuracy, even for complex systems and varying conditions.
Researchers at Drexel University have developed a computer model that uses machine learning algorithms to analyze the genetic sequence of the COVID-19 virus and predict the severity of new variants. The model provides an early warning system for public health officials, allowing them to prepare accordingly.
A large retrospective study found that visceral fat area from fully automated and normalized abdominal CT analysis predicts subsequent myocardial infarction or stroke in Black and White patients. The study suggests that body composition analysis using machine learning could be widely adopted to add prognostic utility to clinical practice.
A Brazilian research team has developed a novel method to sort specialty and standard coffee beans using multispectral imaging and machine learning. The technique, which does not require roasting or human intervention, uses images of the beans at different wavelengths to distinguish between quality levels.
A new method for generating realistic images in driving simulations uses machine learning to improve visual fidelity. This enables better testing of driverless cars and study of driver distraction, ultimately enhancing safety and interaction between humans and AI on the road.
A team of Japanese researchers used reinforcement learning to study fluid mixing during laminar flow, achieving exponentially fast mixing without prior knowledge. The method also enabled effective transfer learning, reducing training time for new mixing problems, and has potential applications across various industries.
Researchers at Arizona State University have developed a machine learning model to predict melting temperatures for any compound. The model enables faster and more accurate calculations of melting points, which is critical for designing high-performance materials in various industries.
Rice University's ROBE Array algorithm slashes the size of DLRM memory structures, allowing training on 100 megabytes of memory and a single GPU. The method matches state-of-the-art DLRM training methods with improved inference efficiency.
A*STAR scientists have developed VarNet, an AI-based method that identifies cancer mutations in tumor samples with high accuracy. This breakthrough allows for personalized treatment strategies and better understanding of cancer.
Researchers at the University of Oldenburg and Fraunhofer IWES collaborate on a new project to develop more accurate wind flow simulations using artificial intelligence. The goal is to reduce computing times and enhance precision, ultimately accelerating innovation in wind turbine design.
ORNL researchers have won seven 2022 R&D 100 Awards for their advancements in materials science, machine learning, and energy storage. DuAlumin-3D, a high-strength aluminum alloy, and Gremlin, an AI system to identify weaknesses in machine learning models, are among the winning technologies.
A team of Brazilian researchers has developed a novel technique using light and artificial intelligence to identify the maturity stages of soybean seeds. The method utilizes chlorophyll fluorescence and machine learning algorithms to classify commercial seeds with high accuracy. This innovation avoids destroying seeds, which are then c...
A study reveals that over 50% of mammal food web links have disappeared due to animal declines, leading to a collapse of global ecosystems. Restoring extinct species to their historic ranges holds great potential to reverse these declines and restore food web complexity.
The special report outlines 12 suboptimal practices in data handling that can predispose machine learning systems to bias. The report presents strategies to mitigate these biases, including careful planning, multidisciplinary teams, and creating heterogeneous training datasets.
Researchers used satellite imagery and machine learning to pinpoint high-priority areas for deforestation action, reducing the target area by 160,000 km². The study reveals that only 37% of the last three years' deforestation rate was covered by official monitoring in the 11 municipalities.
Researchers developed a machine learning algorithm that can predict how different driving patterns affect battery performance, improving safety and reliability. The algorithm uses non-invasive probing to provide a holistic view of battery health, suggesting routes and driving patterns that minimize degradation and charging times.
Researchers at Washington University in St. Louis are evaluating the potential of AI to improve health outcomes and doctor well-being. Chenyang Lu's team has developed novel methods using deep learning to predict physician burnout and surgical outcomes, transforming clinical data into accurate predictions.
A machine learning model developed by Canadian and Slovenian researchers accurately predicted fall risk in lower limb amputees, achieving up to 80% accuracy. This breakthrough has significant implications for the development of smartphone-based fall detection systems.
NTU Singapore has launched the Algorand Centre of Excellence at NTU (ACE@NTU), a new research and education centre focused on developing and advancing blockchain technologies. The centre aims to become the nexus for blockchain education and research in Singapore and the region.
A proof-of-concept study developed three machine learning models to predict posttreatment recurrence in early-stage hepatocellular carcinoma patients. The models achieved high accuracy using imaging data alone, while combining clinical data did not significantly improve performance.
A team of researchers from Osaka University developed an AI algorithm to predict the risk of mortality for trauma patients. They analyzed a large dataset of patient information and blood markers to identify critical factors that guide treatment strategies more precisely.
Engineers developed a machine learning algorithm that can detect and correct wide variety of errors in real time, learning from other machines' experiences. The algorithm enables 'driverless' printers to work for multiple parts, materials, and printing conditions.
A new University of Illinois project aims to improve undergraduate students' ability to estimate their knowledge using artificial intelligence methods. The researchers will utilize machine learning to anticipate student performance and provide personalized feedback to enhance studying strategies.
Researchers used artificial intelligence to demonstrate the correlation between cytoskeleton organisation and nuclear position in eukaryotic cells. The study successfully predicted the presence and location of nuclei in over 8,000 cells with high accuracy, transforming the way scientists approach complex biological systems.
A new method, XTEC, uses machine learning to analyze large volumes of X-ray data, revealing previously hidden structural changes in materials. This accelerates materials discoveries and unlocks new properties of temperature-sensitive devices.
Researchers developed a Flashover Prediction Neural Network (FlashNet) model to forecast deadly fire events, beating other AI-based tools with up to 92.1% accuracy across various building floorplans. The model's performance improved when given real-world data, highlighting its potential for saving firefighter lives.
MIT researchers developed a method to create 3D-printed materials with tunable mechanical properties and embedded sensors, enabling real-time feedback on movement and interaction. The sensing structures use air-filled channels that deform when moved or squeezed, providing accurate feedback for robotics and wearable devices.
Researchers used natural language processing and machine learning to analyze nearly 35,500 death records, identifying the most common substances involved in overdose deaths. The system reduced data processing time by months, allowing for more rapid public health responses and interventions.
Two OU research groups received nearly $2 million in funding to develop new surveillance methods and predict the next avian influenza pandemic. The projects focus on integrating data from multiple sources to detect early signals of disease spread.
Researchers from Aarhus University are developing a new approach to turbulence modelling using physics-constrained machine learning to accurately simulate complex turbulent systems. The goal is to reduce computational costs while maintaining accuracy, enabling more efficient designs and predictions in various fields.
Researchers successfully taught microrobots to swim via deep reinforcement learning, allowing them to adapt to changing conditions and perform complex maneuvers. The AI-powered swimmers can navigate toward any target location on their own, showcasing their robust performance in fluid flows and uncontrolled environments.
Physicists have created a way to simulate quantum entanglement between interacting particles using neural networks and fictitious 'ghost' electrons. This approach enables accurate predictions of molecule behavior, which could lead to breakthroughs in pharmaceutical development and material design.
A new study used artificial intelligence to create the largest global map of insect diversity, highlighting areas with high ant biodiversity and potential conservation priorities. The researchers also found that only a low percentage of these areas are protected.
A new study used satellite data to determine the effect of fuel regulations on sulfur pollution from cargo ships. The research team found significant changes in pollution after regulations went into effect, and their data can contribute to understanding how pollutants interact with clouds and affect global temperatures.
Researchers at MIT have developed a machine-learning system that uses computer vision to monitor the 3D printing process and correct errors in real-time. The system successfully printed objects more accurately than other 3D printing controllers, enabling engineers to incorporate novel materials into their prints with ease.
A team of Chan Zuckerberg Biohub scientists developed a deep-learning method, dubbed
A new study introduces a novel epigenetic predictor, PCBrainAge, that captures aging heterogeneity across multiple brain regions. The tool demonstrates stronger associations with AD dementia and pathologic AD compared to existing age predictors.
Researchers from Aarhus and Berlin have developed an algorithm that can predict how complex molecules will bind to the surface of catalysts. This is achieved through a machine-learning approach inspired by 3D Tetris, allowing computers to quickly identify promising catalysts.
MIT researchers have developed a new type of programmable resistor that enables analog deep learning, which promises faster computation with reduced energy usage. The device can process complex AI tasks like image recognition and natural language processing, paving the way for integration into commercial computing hardware.
Researchers developed a machine learning method to predict material structure, overcoming a key bottleneck in materials science. The approach accurately predicts the structure of materials with five times the efficiency of current methods, paving the way for advances in battery technology and photovoltaics.
The new AI system uses associative learning to detect similarities in datasets, reducing processing time and computational cost. By leveraging optical parallel processing and light signals, the system can identify patterns and associations more efficiently than conventional machine learning algorithms.
A team of researchers at Osaka University has created a machine learning system that can virtually remove buildings from a live view, streaming in real-time on a mobile device. This technology can help accelerate the process of urban renewal based on community agreement, reducing conflicts and delays.
A recent study by Renmin University of China found that a good media reputation consistently reduces the risk of termination for administrative agencies. The research analyzed over 4.95 million articles published between 1949 and 2019 in the People's Daily, an official newspaper of the Chinese Communist Party Central Committee.
Researchers from Georgia State University developed an AI model that can analyze large amounts of brain imaging data to identify novel patterns linked to mental health conditions. The model was trained on datasets of over 10,000 individuals and showed promise in predicting Alzheimer's disease, schizophrenia, and autism risk.
A new AI system developed by researchers at Johns Hopkins University has been shown to detect sepsis more accurately and quickly than current methods, potentially saving thousands of lives. The system uses computational simulation and modeling to analyze patient data and identify early warning signs of sepsis.
Researchers developed a new machine learning method called MotifBoost that can predict infections based on limited T-cell receptor data. By focusing on short sequences of amino acids in the receptors, the approach achieved more accurate results with smaller datasets, shedding light on the human immune system's recognition of germs.
A new study uses machine learning models to predict cancer patients' responses to immunotherapy based on their gut microbiome features. The research identifies common gut bacterial taxa associated with responders versus non-responders, providing a potential tool for distinguishing and predicting immunotherapy responders.
A new clinical model predicts hospital mortality and major adverse kidney events in critically ill patients with acute kidney injury. The proposed model exhibits good performance for outcome prediction, enabling timely interventions to promote kidney recovery.
Researchers at Max Planck Institute for Intelligent Systems created a robot dog named Morti that can walk smoothly within an hour. The robot uses a Bayesian optimization algorithm to learn from sensor data and adapts its virtual spinal cord, allowing it to optimize its walking pattern and minimize stumbling.
A study by Carnegie Mellon University researchers found that algorithmic transparency can have positive effects for firms, allowing them to motivate agents to improve valuable features. However, transparency may not always be beneficial for agents, as it can lead to a loss of predictive power and disadvantage high-type agents.
Researchers used human heart muscle cells and machine learning to predict arrhythmias in patients, achieving over 90% accuracy. The study lays the foundation for safer and more effective medicines by generating patient risk profiles and drug toxicity testing.
Developed a dataset of over 2,000 clinically relevant questions written by medical experts to train AI models. The model asked high-quality and authentic questions over 60% of the time, compared to real questions from medical experts.
A new study from the University of California - Davis Health suggests machine learning can identify handgun purchasers at high risk of firearm suicide. The algorithm used predictive factors such as handgun categories, caliber size, and previous gun purchases to forecast the likelihood of firearm suicide.
A new AI technology called in silico FOCUS analyzes cell images to predict therapeutic effect of drugs for neurodegenerative disorders like Kennedy disease. The technology has 100% accuracy and can analyze several hundred thousand cells in just a few minutes.
Researchers at Boston University developed an AI-powered computational model that can detect cognitive impairment from audio recordings of neuropsychological tests. The model was trained on over 1,000 individuals and accurately distinguished between healthy individuals and those with dementia.
Researchers from North Carolina State University have developed a new approach to federated learning that allows them to develop accurate AI models more quickly and accurately. By reformating updates sent to the centralized server, they can resolve the heterogeneity problem in data, improving model performance.
A team of researchers at Max-Planck-Gesellschaft developed METIS, a modular software system for optimizing biological systems using machine learning. The tool allows users to optimize their already discovered or synthesized biological systems and can be used with different lab equipment.