Articles tagged with Artificial Intelligence
A team of researchers from the University of Groningen developed an AI-based system that can identify individual Holstein cows in a milking station based on their coat pattern. The system achieved a recognition rate of 99.7% and has several advantages, including non-invasiveness, cost-effectiveness, and scalability.
Researchers propose a new model for electricity trade that balances economic interests and considers the stability of economic ties. The model suggests ways to improve cooperation between nations and prioritize transit country interests.
Researchers from Pusan National University have developed an algorithm to restore missing data in event logs, improving restoration accuracy by 10-30% compared to existing algorithms. The high accuracy of the new algorithm ensures its widespread application in industries and potential improvements in AI technologies.
Researchers simulated an attack that falsified mammogram images, fooling both AI breast cancer diagnosis models and human radiologist experts. The study highlights the need to develop ways to make AI models more robust to adversarial attacks, which could lead to incorrect cancer diagnoses.
A new database has been launched to systematically record findings on perovskite semiconductors, featuring over 42,000 individual data sets and analysis tools for interactive exploration. The FAIR principles guide the preparation of the data, enabling easy searching with modern algorithms and artificial intelligence.
Researchers developed an AI system to detect inflammation in ulcerative colitis patients using live colonoscopy videos. The system accurately predicted remission cases with high accuracy, reducing the need for invasive biopsies.
The University of California, Riverside, has been awarded a $980,000 grant from the Department of Energy to develop an AI-driven detector for the future Electron-Ion Collider. The team will use machine learning techniques to optimize detector design and achieve 'co-design,' a new concept in nuclear physics.
A global community of hackers and threat modellers is needed to stress-test the harm potential of new AI products. Companies can harness techniques like red team hacking, audit trails, and bias bounties to prove their integrity and earn public trust. The industry faces a 'crisis of trust' if it doesn't adopt these measures.
Researchers developed AI that extracts hidden equations of motion from observational data, creating models faithful to the laws of physics. This enables physics-based investigations and simulations for ecosystem sustainability, among other applications.
Researchers at MIT and Google Brain developed a system that predicts how changing materials or designs will improve solar cell performance. The new simulator, called differentiable solar cell simulator, provides information on which changes will provide desired improvements, increasing the rate of discovery of new configurations.
Researchers create an artificial intelligence that allows drones to use ocean currents to aid navigation, reducing energy consumption. The AI uses reinforcement learning networks to exploit low-velocity regions in water currents, outperforming even the most efficient swimming strategies found in nature.
Researchers developed an AI-powered system to model disease progression in patients as they age. The model assesses metabolic and cardiovascular biomarkers to calculate health status and disease risks across a patient's lifespan.
Researchers developed an AI program that accurately identified patients at risk of serious illness due to blood infections, with an accuracy rate of 82%. The technology has the potential to serve as an early warning system for doctors, enabling them to rank patients based on their risk level.
A study published in eLife found that rats exhibit efficient coding processes for visual stimuli, similar to those observed in humans. This suggests a universal principle in vision, where the brain adapts to its environment by specializing in the recognition of informative signals, thereby conserving computational resources and energy.
Researchers developed an AI system to predict ICU admission for COVID-19 patients based on over 200 clinical data points. The system achieved greater than 95-per-cent accuracy in predicting ICU need for new cases and identified key factors driving its predictions.
A new machine learning-based algorithm can predict stable material compounds much faster than traditional methods, opening up new avenues for research and discovery. The researchers identified several thousand potential new compounds using the computer, offering a promising breakthrough in materials science.
Researchers at Case Western Reserve University are developing an AI tool to analyze medical images and determine which rectal cancer patients require surgery. By using radiomics and machine learning techniques, the team hopes to identify patients who can avoid invasive surgery and opt for chemotherapy or radiation therapy instead.
A study by the University of Toronto's Rotman School of Management found that predictive analytics can increase revenue by $500,000 to $1 million for manufacturers who invest in IT capital, educate their workforce, and implement high-efficiency manufacturing processes. The research team surveyed over 30,000 manufacturers and found that...
A research team developed an AI framework that analyzes protein interactions to predict effective and low-toxicity cancer drug combinations. The framework, GraphSynergy, outperforms conventional models in identifying synergistic combinations.
Computer scientists and mathematicians have used artificial intelligence to help prove or suggest new mathematical theorems in complex fields. The breakthrough uses DeepMind's AI processes to explore conjectures in mathematics, leading to a completely new theorem in knot theory.
Researchers used machine learning to identify patterns in knot theory and representation theory, suggesting new connections that mathematicians were able to prove. This collaboration demonstrates the potential of AI as a tool for guiding intuition in mathematical research.
The University of Texas at Arlington has received a $1.5 million grant from the US Department of Education to support domestic doctoral students specializing in Internet-of-Things study and research. The project aims to increase diversity among computer science researchers, with a focus on women and minorities.
A Japanese study found that a robot's physical texture, such as softness or elasticity, affects perceptions of its personality. The researchers used six humanoid robots with varying arm textures and asked participants to touch and evaluate them.
A novel AI algorithm developed at Mayo Clinic can predict long-term patient survival after cardiac surgery using a single-lead EKG. The study found a clear correlation between long-term mortality and a positive AI ECG screen for reduced left ventricular ejection fraction among patients without apparent severe cardiomyopathy.
Researchers developed transformational machine learning (TML) to learn from multiple problems and improve performance while learning. TML out-performs current machine learning methods for drug design, accelerating the identification and production of new drugs.
Researchers at the University of Gothenburg have successfully combined a memory function with a calculation function in the same component, enabling more efficient technologies like mobile phones and self-driving cars. The discovery opens the way for brain-like computers that can perform tasks effectively and energy efficiently.
A study using GDPR-compliant mobile phone data found significant decreases in household mixing during the first two lockdowns, but increases during the third, coinciding with the vaccine rollout.
Researchers have developed a new AI technique, MuSIC, which combines microscopy, biochemistry techniques and artificial intelligence to reveal approximately 70 components contained within a human kidney cell line, half of which had never been seen before.
A team of scientists from GIST developed an AI-based approach to analyze and extract user behavior data, estimating the optimal demand response management for each household. The study showcases how AI can improve electricity consumption, leading to lower prices and a smaller carbon footprint.
Researchers developed an AI method to correct speed of sound aberrations in photoacoustic images, resulting in improved image quality and resolution. The technique reduced streak artifacts by up to 5% and increased signal-to-noise ratio by about 25 decibels.
A study using Google Trends and Wikipedia search volume found that public interest in earthquakes is dependent on the income level of the affected country. Earthquakes in developing countries receive less international attention than those in developed countries, with interest often dwindling within a week. However, interest persists f...
Fred Martin, a UMass Lowell computer scientist, is being recognized for developing an educational framework that introduces robotics and AI to K-12 students. His work has guided the development of primary and secondary AI education initiatives worldwide.
A new AI model has been developed to classify colorectal polyps, demonstrating accuracy and sensitivity at a level comparable to practicing pathologists. The model was tested in a clinical trial involving 15 pathologists, showing significant improvements in accuracy compared to traditional methods.
A new study by USC researchers uses GANs to generate synthetic neurological data that can be fed into machine-learning algorithms to improve BCI usability. This approach improved BCI training speed by up to 20 times and enabled rapid adaptation to new subjects.
Machine learning enables better understanding of climate-induced hazards, predicting floods and landslides with high accuracy. The technology combines diverse data sources to assess risk extent, considering both triggering hazards and socio-economic vulnerability.
Research reveals AI recommendation tools can lead to a 'information cocoon' effect, where customers see only what they want to see, negatively impacting purchasing decisions. This phenomenon is particularly concerning in e-commerce, highlighting the need for consumers to take independent purchasing decisions.
A research team found that combining human and AI predictions yields more accurate results, especially in atypical cases with unknown factors. Human analysis can fill gaps in big data, leading to better collective predictions.
A new AI application called DeepMReye uses MRI signals to read eye movements and infer thoughts, memories, and goals. It can also diagnose brain diseases by analyzing characteristic eye movement patterns.
Researchers from Okayama University developed an AI-powered image classifier to simplify and speed up the task of image analysis in cell biology. The system achieved high detection accuracy for mitotic cells in plant species, demonstrating its potential for non-experts to use.
Researchers have developed a new approach to studying prostate cancer, allowing them to track the behavior of individual cancer cells from birth to organ spread. The technique uses whole-organ imaging and artificial intelligence to create a 3D reconstruction of the organ at single-cell resolution.
Researchers identified 166 prognostic biomarkers from long non-coding RNAs, with one biomarker, HOXA10-AS, showing high effectiveness in categorizing gliomas as low- or high-risk. The study provides potential therapeutic targets and insights into cancer biology.
George Mason University researchers Zhi Tian and Yue Wang are securing $125,000 in funding from the Virginia Innovation Partnership Authority to develop an artificial intelligence-based solution for multi-access edge computing. The project aims to enhance network security and improve efficiency of collaborative machine learning.
Researchers at Lancaster University examine the use of AI in the food sector, highlighting the need for trusted data collaboration to reduce waste and increase sustainability. They also warn about potential ethical issues and unexpected consequences of new technology.
Researchers at Rice University are creating a 3D-printed smart helmet with embedded sensors to protect soldiers' brains against kinetic or directed-energy effects. The program aims to modernize standard-issue military helmets by incorporating advances in materials, image processing, artificial intelligence, and energy storage.
Researchers have developed a new method that uses deep neural networks to predict extreme heat waves with unprecedented accuracy, up to two weeks before they occur. This breakthrough has significant implications for risk management, planning, and warning systems, which will greatly improve public safety and support public policies.
The review found that datasets lack images and information about patients with darker skin, which may lead to inaccurate diagnoses. The research highlights the need for better representation of diverse skin tones in training AI models.
A systematic review of AI studies on mechanical ventilation found that many were testing early technology, but more work is needed for transparency and bias avoidance. The review recommends improving data availability and reporting standards to facilitate the translation of AI into improved patient care.
Researchers trained a GAN to generate novel refractory high-entropy alloys with specific properties, surpassing human intuition and guesswork in material design. The model produces alloy compositions in milliseconds, offering a promising tool for determining suitable materials.
Researchers created novel frog models to replicate polycystic kidney disease, allowing for real-time observation of disease processes. AI analysis enabled rapid assessment of disease in the tiny animals.
Researchers used reinforcement learning to control a small particle moving in a double-well system, achieving accurate control despite noisy measurements. The method shows promise for future applications in quantum technologies and AI.
A new machine learning-based algorithm has been developed to identify adolescents who have experienced suicidal thoughts and behavior. The algorithm, applied to a large dataset of survey responses from over 179,000 high school students in Utah, shows high accuracy in predicting individual adolescents at risk.
A new study explores the problem of shortcuts in a popular machine learning method and proposes a solution that can prevent shortcuts by forcing the model to use more data. By removing simpler characteristics and asking the model to solve the task two ways, researchers reduce the tendency for shortcut solutions and boost performance.
Researchers at University of Missouri and University of Chicago develop an artificial material that can respond to its environment, make decisions, and perform actions not directed by humans. The material uses a computer chip to control information processing and convert energy into mechanical energy.
Scientists have developed a software that adds missing sugar components to protein models created with AlphaFold, enabling more accurate structural predictions. This breakthrough has the potential to revolutionize workflows in biology, allowing scientists to understand proteins and their mutations faster than ever.
A new algorithm has been developed to train spiking neural networks, mimicking the human brain's structure and function. This approach enables these powerful, fast, and energy-efficient systems to solve complex tasks like image classification with high precision.
A new visual analytics tool, Sibyl, was developed to help child welfare specialists understand machine learning predictions. The tool uses bar graphs to show how specific factors of a case contribute to the predicted risk that a child will be removed from their home within two years.
A new study by Georgia Institute of Technology researchers found that automation and AI may have a uniformly positive impact on worker well-being, but only partially. The results show that workers facing automation risk experience less stress but worse health and minimal job satisfaction. Notably, high-risk occupations like receptionis...
A new study maps out risk factors associated with misleading information and proposes practical ways to manage them in the business world. The research aims to bridge the divide between academic research and real-world practice of cyber risk management.
Researchers at Tohoku University developed a smart chair with pressure sensors that detect workers' movements to predict low back pain progression. By analyzing small body motions, they identified a common motif that can be used to forecast worsening LBP throughout the day.
Researchers use physical reservoir computing to teach robots to think like humans by simulating brain signals. The system enables goal-directed behavior without additional learning, highlighting a potential breakthrough in AI development.