Articles tagged with Artificial Intelligence
Researchers developed an AI algorithm that can assess climate change tipping points, predicting rapid or irreversible change in systems. The new approach can detect features of tipping points common to various complex systems, including ecology, epidemiology, and markets.
Researchers developed a feature selection algorithm that uses boosting to select relevant features from high-dimensional data sets. The algorithm outperforms other methods in terms of accuracy and number of features used, making it more scalable and explainable.
Researchers at WVU aim to characterize autism patients' behaviors using behavior-tracking technology. They plan to use artificial intelligence to identify traits associated with ASD, which could lead to more accurate diagnoses and personalized interventions. The study also has the potential to improve early detection in young children.
Rutgers researchers have found that learning can be mimicked in synthetic matter, which could lead to new algorithms for artificial intelligence. The study involved changing the environment of nickel oxide material and observing its response.
A collaborative research between Owkin and Cleveland Clinic has developed an AI model that predicts liver cancer recurrence following liver transplantation. The model outperformed traditional scoring systems and showed promise for improving patient outcomes.
Researchers have developed an AI-powered platform that allows scientists to grow virtual tumors and optimize nanoparticle designs using artificial intelligence. The new EVONANO platform has the potential to improve targeted cancer treatments, enabling personalized therapies for individual patients.
Cong Wang aims to develop a two-fingered robot that can perform everyday tasks with precision manipulation, using artificial intelligence and crowdsourcing. The robot will be taught by human volunteers through the Amazon Mechanical Turk system, with the goal of creating a physically intelligent being.
The University of Huddersfield's AI Skills Bootcamp will provide learners with personalized learning and employment plans, alongside Artificial Intelligence and transferable skills. The 16-week program aims to support learners from across the UK in developing independent skills and addressing current barriers to digital skills employment.
A new study published in Clinical Gastroenterology and Hepatology found that computer-aided detection can improve colonoscopy quality by reducing the miss rate, with a relative reduction of nearly a third when used in conjunction with standard-of-care colonoscopy. The study suggests that artificial intelligence may be an important tool...
Scientists at Aarhus University are working on a nano-sized brain-inspired computer that can harvest its own energy, making it the smallest and most efficient AI system yet. The project aims to reduce power consumption by 12 orders of magnitude compared to modern supercomputers.
Researchers at Osaka University used machine learning to analyze locomotion data from diverse species, revealing common features associated with dopamine deficiency. The study found that worms, mice, and humans exhibit similar movement disorders when lacking dopamine, despite their evolutionary differences.
The article highlights the need for financial and technological support to enable effective interprofessional teams in primary care. The authors suggest training community members to serve their communities and exploring how diversity impacts patient care outcomes. They also advocate for innovative payment models that allow primary car...
Researchers found that AI and non-AI tools can improve the effectiveness, efficiency, and experience of care in pre-visit planning. However, few technologies have been independently evaluated, suggesting a need for rigorous evaluation to harness their full potential.
A new AI-powered training program aims to improve the skills of safety-critical professionals by generating scenarios based on past occurrences. The program uses reinforcement learning to increase learning and generate explanations for its decisions.
The Ariel Machine Learning Data Challenge has announced its winners, ML Analytics and TU Dortmund University, who developed highly accurate solutions for observing exoplanet atmospheres despite instrument noise. The winning teams will receive a cash prize of €500 and present their research at various conferences.
Researchers developed an AI tool using data from hospitals across four continents to predict oxygen needs of hospital Covid patients anywhere in the world. The study achieved high-quality predictions with a sensitivity of 95% and specificity of over 88%, demonstrating the transformative power of federated learning in healthcare.
A study by Purdue University and collaborators has found a way to demonstrate habituation and sensitization in nickel oxide, a quantum material that mimics the sea slug's most essential intelligence features. This discovery could lead to building hardware-based AI with improved efficiency and reduced energy consumption.
A new study from Northwestern University finds that exploring diverse styles before exploiting a narrow area can lead to a career's greatest hits. Dashun Wang and his team analyzed data from over 2,128 artists, including Jackson Pollock, and found a consistent association between the 'exploration-exploitation' pattern and hot streaks.
The Center for Research on Programmable Plant Systems (CROPPS) aims to create systems that enable plants to communicate their hidden biology to sensors, optimizing growth and the local environment. This will lead to breakthrough discoveries, new educational opportunities, and transformative management of crops.
Researchers developed a robust, deep neural network model to analyze automobile traffic impacts of construction zones. The model estimates hourly traffic volumes without adjustment factors, helping transportation agencies plan for efficient work zone operations.
Researchers at Nanyang Technological University and Tan Tock Seng Hospital have developed an AI-powered system to diagnose glaucoma from stereo fundus images, achieving an accuracy of 97% in diagnosing the condition. The automated method could potentially be used in less developed areas where patients lack access to ophthalmologists.
A study using machine-learning models trained on over 1 million companies reveals that AI can accurately predict the success of startups. The tool, developed by researchers, has the potential to help investors make informed decisions and avoid significant losses.
Researchers developed a new AI algorithm called 'basis profile curve identification' to simplify comparisons between effects of electrical stimulation on the brain. The algorithm may help understand which brain regions interact with each other, guiding placement of electrodes for treating network brain diseases.
A new algorithm, Phe2vec, accurately identified patients with certain diseases, outperforming traditional methods in classifying diagnoses. The study suggests that this automation will facilitate further research in clinical informatics.
Researchers at Technical University of Munich have developed a new machine learning algorithm that can analyze complex markets and their equilibrium strategies. This breakthrough has potential applications in auction theory, wireless spectrum auctions, and more.
A review of 23 studies found AI systems were less accurate than humans and radiologists in detecting breast cancer. The quality of methods used was poor, and the applicability to European or UK breast cancer screening programmes was low.
Researchers developed an AI tool that can quickly and accurately identify suspicious proteins in the body by analyzing their movements. The method, known as diffusional fingerprinting, uses machine learning algorithms to predict protein behavior with over 90% accuracy.
A study found that Airbnb's Smart Pricing algorithm narrowed the racial revenue gap, but only for Black hosts who adopted it. The algorithm increased monthly occupancy and overall revenue for Black hosts by nearly 9% and $13.92 a night.
A new research project, FLOCKD, will allow smart digital units to autonomously share information with nearby units, enabling faster learning and more intelligent system behavior. The goal is to achieve synergetic problem-solving and improve overall performance.
Researchers developed a model to predict the risk of death and unplanned cardiac hospitalization among patients awaiting cardiac surgery. The tool, based on an ethnically diverse group of 62,375 patients, identifies factors such as gender, urban residency, and cardiac symptoms that increase the risk of adverse events.
Researchers developed scArches to compare single-cell genomics data with existing references, enabling accurate diagnosis of diseases like COVID-19. The algorithm uses transfer learning to preserve privacy and democratize the usage of single-cell reference atlases.
Scientists created a reliable true random number generator using atomically thin two-dimensional films, overcoming long-term stability issues and power consumption concerns. The innovation uses memristors to produce fluctuating electronic signals with an exceptionally high degree of randomness.
A new AI tool called IceNet has been developed to predict Arctic sea ice conditions with high accuracy. The system is almost 95% accurate in forecasting sea ice presence two months ahead, addressing the challenge of predicting Arctic sea ice forecasts for decades.
Researchers at UCLA have developed a computational technique powered by artificial intelligence that transforms images of tissue previously stained with H&E into new ones with added special stains. The process takes less than one minute per tissue sample, significantly improving diagnoses in medical conditions such as organ transpl...
Student researchers at the University of Cincinnati developed artificial intelligence to train robots to work together to move a couch around obstacles and through a narrow door. The robots successfully completed the task 95% of the time in simulations, with nearly equal success without re-training.
The robotic white cane system combines depth data with a 2D floor plan map to reduce pose estimation errors. It features a novel 'robotic roller tip' interface that allows for automatic mode-switching, making it easier for visually impaired users to navigate.
A North Carolina State University panel of experts assesses AV deployment risks and benefits, predicting substantial benefits if well-regulated. The study's findings suggest regulations could limit urban use of AVs and commercial fleet ownership, reducing risk and increasing benefits.
Drones are not the only vehicles at the forefront of automating deliveries; researchers have developed a control strategy for ships and partnered tugs to navigate environmental disturbances. The multi-layer, multi-agent control scheme increases efficiency in the shipping process while reducing human error.
Researchers from University of Notre Dame discovered that behavioral inertia can be beneficial in service center operations, particularly when agents are experts or handling difficult calls. The study suggests striking a balance between automated routing systems and agent discretion to maximize efficiency and effectiveness.
A recent study suggests that personal carbon allowances (PCAs) may be a feasible solution to reduce emissions and promote sustainable lifestyles. The researchers propose a market-based approach to provide individuals with incentives and options to link their actions with global carbon reduction goals.
Cornell University researchers used facial recognition AI to develop an imaging robot called BlackBird that scans grape leaf samples automatically, reducing manual assessment time from six months to one day. The technology has the potential to save farmers billions of dollars by detecting disease early and reducing fungicide usage.
A single-center retrospective study found that AI-CAD reduced recall rates and improved accuracy compared to digital mammography (DM) and DBT. The study showed lower recall rates and higher accuracy for DM with AI-CAD, indicating a practical addition to lowering false-positive findings.
Researchers have created an AI software that uses Minecraft to test its ability to plan for future events and solve complex tasks. The software, developed by Penn State researchers, aims to advance artificial intelligence in areas such as robotics, logistics management, and drone flight.
Researchers developed an image-based detection system using artificial intelligence models to diagnose COVID-19 from chest X-rays. The model accurately differentiated between COVID-19, pneumonia, and healthy patients, showing great promise for precision medicine.
Researchers at MIT have created an algorithm that enables drones to navigate complex obstacle courses at high speeds without crashing. The new approach combines simulations with real-world experiments, allowing drones to adapt to challenging aerodynamics and find the fastest routes.
A joint research team from POSTECH and KIMS developed a faster and more accurate microstructure imaging technique using deep learning. The technique enhanced the resolution of existing microstructure images up to 4, 8, or 16 times, reducing imaging time by up to 256x compared to conventional SEM systems.
Scientists at CiTIUS have developed a new fast support vector classifier (FSVC) that significantly improves data classification using Machine Learning techniques. The FSVC is much faster and operates with less memory than traditional approaches, making it suitable for large-scale classification problems.
Researchers have created an artificial neuron that uses ions instead of electrons for information transmission, achieving a similar energy efficiency as the human brain. The device's ion channels and clusters replicate those found in neurons, allowing for the emission of action potentials and transmission of information.
Researchers at OIST Graduate University develop robots capable of conducting complex experiments and analyzing data. The 'Nobel Turing Challenge' achieves significant advancements in scientific discovery by leveraging AI-driven robotics.
Researchers at KAIST have developed a brain-inspired highly scalable neuromorphic hardware by co-integrating single transistor neurons and synapses. This innovation dramatically reduces hardware cost and accelerates the commercialization of neuromorphic hardware, enabling its application in mobile and IoT devices.
Researchers developed an AI-powered tool to identify and recommend jobs based on underlying skill sets, increasing the chances of success in job transitions. The system can also respond to changes in job demand and provide precise skills needed to transition to a new occupation.
A team of computer scientists has developed an assembly selection process that balances representation and fairness in citizens' assemblies. By using a machine learning-based algorithm, the researchers ensure that all volunteers have an equal chance of being chosen, regardless of demographic quotas or education level.
A team of researchers found that when people use mental abstractions, the brain area that signals valuable information becomes highly active. This discovery could lead to new advances in basic research, education, rehabilitation, and artificial intelligence.
A new app called selfBACK has been developed to help people deal with back pain in a better way. The app uses artificial intelligence and draws on other people's experiences with back pain to provide tailored advice and feedback.
Researchers at UIC have received a $725,000 grant to develop an AI system that can help protect US Navy divers from waterborne bacteria, parasites, and other harmful pathogens. The system aims to provide real-time information on water conditions, allowing divers to make informed decisions about their mission.
Researchers develop hands-on labs to educate high school students about AI and cybersecurity ethics issues, aiming to increase empathy for vulnerable populations. The project uses functional near-infrared spectroscopy to assess the impact of these labs on brain regions associated with empathy.
The Institute for Learning-enabled Optimization at Scale (TILOS) will explore the interplay between artificial intelligence and optimization to develop methods that can change real-world practice. Foundational research will drive important applications in chip design, robotics, and communication networks.
The University of Washington is leading a new NSF institute focused on using artificial intelligence to understand dynamic systems, which describe chaotic situations where conditions are constantly shifting and hard to predict. The institute aims to integrate fundamental AI theory with applications in critical technological areas.
The UMass Amherst AI-EDGE institute will focus on designing wireless edge networks that are efficient, reliable, and secure. The goal is to solve long-standing distributed AI challenges by analyzing and managing vast amounts of data in real-time.
The institute will develop predictive digital twins of individual crop plants and entire farm fields, integrating real-time data from sensors to optimize crop growth. By leveraging expertise in plant sciences, engineering, and technology, AIIRA aims to accelerate agricultural productivity and sustainability.