Articles tagged with Artificial Intelligence
The University of Tennessee is working with several institutions to address health disparities research and enhance AI performance. The projects aim to train participants in using high-performance computing, cloud-based AI applications, and open data tools in medical research and healthcare delivery.
Simpler, physics-based models can generate more accurate predictions than state-of-the-art deep-learning models for certain climate scenarios. However, simple models are more accurate when estimating regional surface temperatures, while deep-learning approaches excel at local rainfall estimation.
Surya is a visual AI model trained on massive amounts of solar data, leveraging NASA's deep scientific expertise in cutting-edge AI models. The system aims to determine the Sun's magnetic field generation and structure, as well as its impact on the heliosphere and geospace.
A new Mayo Clinic AI tool, UNISOM, has shown promising results in identifying early signs of clonal hematopoiesis of indeterminate potential (CHIP), a condition that raises the risk of leukemia and heart disease. The tool helps detect CHIP-related mutations in standard genetic datasets, opening new avenues for research and discovery.
A new deep-learning model calculates urban heat stress per square meter in the future, considering geodata and weather forecasts. The model simulates a range of climate scenarios, including increased heat stress due to rising greenhouse gas emissions.
The project aims to develop personalized technologies that promote lifelong learning in various educational settings. It will guide the creation of IR systems that can effectively support users with complex information needs and foster information literacy.
A new login system called Client-Side Encrypted Access Logging (CSAL) detects online account compromise without exposing personal devices to invasive tracking. The system verifies whether a login came from a user's own device, addressing a flaw in how major platforms log account access.
A new study offers a powerful AI-assisted method for uncovering exactly how TB drugs kill the bacteria, which could lead to smarter treatment combinations. The approach uncovers molecular details of drug interactions and can predict their impact from images alone.
Researchers at North Carolina State University unveiled Rainbow, a self-driving laboratory that autonomously discovers high-performance quantum dots. The system combines advanced robotics and AI to conduct up to 1,000 experiments per day, accelerating materials discovery.
Researchers developed Vesalius to interpret complex data on cancer cell interactions, leading to potential discoveries in treating hard-to-treat cancers. The tool analyzes whole tissue architecture to identify predictive biomarkers and inform treatment options based on individual disease types.
A new AI-driven framework uses a custom-built catalysis knowledge graph and LLMs to recommend relay catalysis pathways. The system successfully found existing and suggested new pathways for several target molecules, demonstrating its potential to improve efficiency and selectivity in chemical reactions.
Researchers at Uppsala University developed an AI model that can accurately predict battery ageing, leading to longer life and enhanced safety for electric vehicle batteries. The model reduces the need for sensitive vehicle data and provides a detailed picture of chemical processes inside batteries.
The inaugural AI in Agriculture Symposium will bring together experts from academia and industry to discuss the latest research and real-world applications for agriculture. The symposium will feature a roundtable discussion on multidisciplinary collaborations in agriculture.
Researchers at Uppsala University have developed an AI system that can detect subtle tissue changes indicative of prostate cancer, missing it from human pathologists. The study found the AI detected cancers in over 80% of cases where pathologists missed them.
A new reporting checklist introduces key methodological details to improve reproducibility and transparency in AI-based automated image analysis. The guidelines will support clear communication of methods and reduce cognitive bias, promoting the translation of AI tools into routine pathology workflows.
A new study by the University of Surrey found that AI technologies can give hotels, restaurants, and cruise lines a competitive edge while improving environmental and social impact. The research calls for targeted staff training, industry-wide partnerships, and government-backed incentives to speed up AI adoption.
Chung-Ang University researchers develop innovative soft robots using paper electrodes and liquid crystal elastomers, achieving directional crawling through asymmetric bending. The robots utilize temperature-responsive materials and simple electroless plating patterning, enabling efficient and cost-effective fabrication.
A new study reveals that ambient documentation technologies, such as AI-driven scribes, led to significant reductions in physician burnout and improvements in well-being. The findings showed a 21.2% absolute reduction in burnout prevalence at Mass General Brigham and a 30.7% absolute increase in documentation-related wellbeing at Emory...
A new computational framework has been developed to optimize cellular self-organization, allowing scientists to understand and control how cells grow and interact. The framework uses machine learning tools to extract rules that guide cell behavior, enabling the creation of artificial organs and potential treatments for cancer.
A new AI-assisted model combines MRI, biochemical, and clinical information to predict worsening knee osteoarthritis with high accuracy. The model showed improved accuracy in predicting worsening pain and joint space narrowing, suggesting its potential to enhance care.
A team of researchers developed a method to annotate biopsy image data with eye-tracking devices, reducing the burden on pathologists. The resulting AI model achieved an accuracy of 96.3% and surpassed human pathologists' performance in diagnosing skin lesions.
The 12th Heidelberg Laureate Forum brings together 200 young mathematicians and computer scientists with 29 distinguished laureates to exchange ideas and discuss pressing issues in their fields. The event features a diverse range of lectures, talks, and panel discussions.
A novel AI model developed by the Dresden research team simultaneously detects multiple genetic alterations directly from routinely stained histological colon cancer tissue sections. The model recognized shared visual patterns rather than independently identifying individual genetic alterations.
Researchers from the University of Bath and University of Hong Kong found that additive advice bias is common in conversations, social media, and AI chatbots. This bias can leave people feeling more overwhelmed than helped, with well-intentioned tips piling on extra tasks.
Experts argue that large language models require symbolic representation to excel in complex tasks, citing examples like the Pirahá people and Leibniz's calculus notation. The proposed approach, known as neuro-symbolic synthesis, combines statistical intuition with human-designed symbol systems for efficient reasoning.
The study combines decision making and machine learning to improve robot learning for water analysis. The Random Forest Classifier achieved an accuracy of 69% which improved to 73% after applying Synthetic Minority Over-sampling Technique (SMOTE) and tuning hyperparameters. The robotic system can detect, analyze, and distinguish drinki...
The new book, Monster Transformation, argues that employees are key to overcoming transformational hurdles. By uncovering unique competencies and empowering them, organizations can break through challenges and succeed in a rapidly evolving space. The book offers a story-driven approach to meeting the needs of the current technological ...
Researchers develop a novel deep learning-enabled method for high-speed, high-precision 3D surface measurements. The technique uses frequency-domain multiplexing and achieves speeds 16 times faster than the sensor's native frame rate.
Researchers develop AI-based model for structural analysis of antibodies, offering precision in less time. The S2ALM model integrates sequence and structure, predicting missing information with high accuracy.
A new study by UC Davis researchers reveals that popular GenAI browser assistants collect and share sensitive data without users' knowledge. The study highlights the need for stronger safeguards and transparency to protect user privacy online.
A new AI hybrid reading strategy for screening mammography reduces radiologist workload by 38% while maintaining comparable cancer detection and recall rates. The strategy incorporates uncertainty quantification, allowing AI to provide certainty estimates for predictions.
The grant aims to support novel applications of data visualization technology that benefit various stakeholders in the research ecosystem. Successful applicants will receive up to £25,000 for their innovative tech ideas.
Researchers have discovered a new material that matches or exceeds the performance of commercial iridium-based materials, but at a fraction of the cost. The breakthrough was achieved using a powerful new tool called a megalibrary, which rapidly screened vast combinations of metals to find a suitable alternative.
OEC allows satellites to process data directly, reducing latency and bandwidth constraints. However, research faces challenges due to limited energy storage, heat dissipation, and launch costs.
The new model can predict how well any given molecule will dissolve in an organic solvent, helping chemists choose the right solvent for reactions. The researchers trained two models on a comprehensive dataset and found that their predictions were two to three times more accurate than the previous best model.
A University of Washington study compared AI developers with climate advocates, revealing divergent values and perceptions on topics like ethics. Climate activists saw limited use cases for AI, focusing on automating tasks and connecting communities with nature, while developers had a broader view of the technology's potential impact.
A new study suggests that adopting AI in high-stakes settings like hospitals and airplanes requires evaluating algorithms and human decision-making simultaneously. The study found that accurate AI predictions improved participant performance by 50-60%, but inaccurate predictions led to a 100% degradation in proper decision making.
MIT researchers have developed a method to reveal the inner workings of protein language models, which can accurately predict proteins suitable for drug or vaccine targets. By analyzing sparse representations of proteins, they identified key features that drive these predictions.
A $5 million NSF grant is powering AI innovations in Pegasus, a widely used workflow management network. Researchers aim to develop intelligent workflow management tools that adapt to evolving user needs and dynamic resource conditions.
Researchers used machine-learning models to design nanoparticles that can deliver RNA to cells more efficiently. The approach accelerated the identification of optimal ingredient mixtures in lipid nanoparticles, leading to better delivery vehicles for RNA vaccines and mRNA therapies. This could dramatically speed up the development of ...
The 34th International Joint Conference on Artificial Intelligence (IJCAI) will take place in Montreal, Canada, from August 16 to 22, 2025. The conference aims to showcase the frontiers of artificial intelligence research and applications, with a focus on AI's impact on society.
Researchers developed an AI framework to map interactions between content and algorithms on digital platforms, reducing the spread of misinformation. The system would allow users and platform operators to pinpoint sources of potential misinformation and promote diverse information sources.
Isabel Angelo will refine and expand machine learning-driven pipelines for detecting exoplanets, focusing on subtle or unconventional candidates. Her work aims to uncover rare or unexpected planetary systems using cutting-edge AI and astrophysical modeling.
Researchers create digital twin facility management system for relocatable modular buildings, improving asset management and decision making. The DT-FMS enhances the lifecycle management of RMBs, minimizing waste and maximizing value through reuse and reconfiguration.
University of Houston researchers are developing an AI-powered dashboard for Florida food pantries, aiming to streamline stakeholder collaboration and distribute resources to families in need. The tool will enable emergency coordinators to respond quickly to spikes in demand, prioritizing the needs of vulnerable populations.
A recent study found that school-based online surveillance companies are extensively monitoring students' digital behavior beyond school hours, often using AI with little human oversight. The research team identified 14 companies marketing such services, citing concerns about privacy, equity, and oversight.
Researchers at Radboud University Medical Center found that AI detects breast cancer on mammograms more frequently than radiologists. The study analyzed 42,000 breast scans and showed that one radiologist working with AI detects more tumors than two radiologists alone.
Experts from across industries and disciplines gathered to assess the current state of cybersecurity through a multidisciplinary lens. The workshop explored emerging technologies and the intersection of technology and policy, highlighting the need for a unified ecosystem to address persistent challenges.
The study reveals that East and West coasts, Great Lakes and Gulf regions face the highest risk of weather-induced blackouts. The nationwide Power System Vulnerability Index (PSVI) tool identifies areas at increased risk of power outages, enabling policymakers to prioritize preparation for long and frequent power outages.
Researchers designed over 36 million compounds using generative AI algorithms and computationally screened them for antimicrobial properties. The top candidates show promise against Neisseria gonorrhoeae and Staphylococcus aureus (MRSA) by novel mechanisms that disrupt bacterial cell membranes.
Researchers developed a novel approach called R3DG that analyzes representations at varying granularities to capture nuanced emotional fluctuations and reduce computational complexity. This framework demonstrates superior performance in multiple multimodal tasks, including sentiment analysis, emotion recognition, and humor detection.
A team at Osaka Metropolitan University used AI to analyze video footage of calves, detecting consistent temperature changes in their eyes and noses. The method enables non-invasive monitoring and improves the accuracy of body temperature assessments.
Researchers have developed a new AI approach called HEAT-ML that accelerates calculations of magnetic shadows in fusion vessels, enabling faster design and operation. This breakthrough could lead to significant improvements in fusion power generation and potentially limitless clean energy.
Researchers at King's College London found that AI chatbots can be exploited to reveal up to 12.5 times more personal information from users. The study used three types of malicious AIs to encourage disclosure of private info, with reciprocal strategies proving the most effective.
Researchers leverage machine learning to accelerate solid-state battery development, overcoming material interactions and interface instability. AI-powered strategies optimize battery management systems and decode ion transport for improved energy storage.
Researchers have developed an AI system that can recognize the early warning stages of laryngeal cancer from voice recordings. By analyzing variations in tone, pitch, and volume, the AI can distinguish between voices with benign vocal fold lesions and those with cancer. The study's findings offer a promising breakthrough for non-invasi...
Researchers at the University of Pennsylvania used AI to identify previously unknown compounds in Archaea that could fuel the development of next-generation antibiotics. The study, published in Nature Microbiology, found that 93% of the identified archaeasins demonstrated antimicrobial activity against drug-resistant bacteria.
A research team developed a new method to precisely edit DNA by combining genetic engineering with artificial intelligence. The technique enables accurate modeling of human diseases and lays the groundwork for next-generation gene therapies.
Researchers evaluated over 1,500 AI algorithms for detecting breast cancers on mammography images, achieving median rates of 98.7% specificity and 27.6% sensitivity. Combining top-performing algorithms resulted in sensitivity boosts to 60.7% and 67.8%, comparable to average screening radiologists.
Catal-GPT streamlines catalyst formulation generation and optimizes data-driven industrial catalysis. The AI-powered platform achieves high accuracy in knowledge extraction from scientific literature and generates experimental protocols.