Articles tagged with Artificial Intelligence
Symplectic Elements now offers AI-generated summaries for publication abstracts, enhancing public profiles and increasing research visibility. The new functionality supports researchers and institutions in showcasing their research outputs and discoverability.
A new AI-powered tool helps predict traumatic brain injury outcomes based on documented assault scenarios, providing an evidence-based approach to improve investigation accuracy. The model achieved remarkable prediction accuracy for TBI-related injuries, integrating mechanical biophysical data with forensic details.
Researchers developed an AI approach to identify genes contributing to neurodevelopmental disorders like autism spectrum disorder, epilepsy, and developmental delay. The tool enhances gene discovery by predicting additional genes involved in these conditions.
Colorectal cancer is a leading cause of mortality in China due to late-stage diagnosis. Emerging non-invasive diagnostic tests, innovative imaging techniques, and AI applications enhance CRC detection and diagnosis. However, expanding accessibility and promoting public awareness remain key challenges.
A team from the University of Trento combined AI techniques with neuroimaging measurements to analyze how emotions and language structure influence brain activity during interactions. The results show that neural synchrony is associated with emotional content and semantic structure, with implications for understanding human relationships.
PRISm is a form of Pre-Chronic Obstructive Pulmonary Disease (Pre-COPD) characterized by respiratory symptoms and reduced lung function. Imaging assessments, such as computed tomography scans and magnetic resonance imaging, play a crucial role in diagnosing and predicting the prognosis of PRISm.
Researchers at Mizzou have developed a proactive approach using artificial intelligence to address evolving threats against smart grids. The CIBR-Fort system can predict cyberattacks with 91.88% accuracy and defend against them in real-time, enabling scalable security for power grids of the future.
Researchers developed ItpCtrl-AI, a transparent AI framework that reads chest X-rays like a radiologist, providing accurate diagnoses and increasing trust in medical technology. The framework uses a gaze heat map to show the computer where to search for abnormalities and what section of the image requires less attention.
Researchers leveraged a large language model to classify artwork types without pre-prepared training data, achieving high accuracy. This approach enables performance comparable to conventional machine learning methods while reducing human effort and time required for data organization.
Film workers express concerns about AI's impact on wages, jobs, and the artistic process. They argue that AI-generated art lacks authenticity, while some see potential benefits when humans maintain control over creative decisions.
An international research team developed a user-friendly software method called Segment Anything for Microscopy, which can precisely segment images of tissues, cells, and similar structures. The new model improved performance for cell segmentation, enabling researchers to automate tasks that previously took weeks of manual effort.
A new AI model uses electrocardiogram (ECG) analysis to identify female patients at higher risk of heart disease, including cardiovascular disease, future heart failure, and heart attacks. The model shows that women whose ECGs more closely match the typical 'male' pattern are at a significantly higher risk of these conditions.
The book, RE-HUMANIZE, offers actionable frameworks to help business leaders navigate the evolving landscape of digital work. It emphasizes the importance of preserving humanity in organizations, highlighting strategies for a digital division of labor that respects human dignity.
A new AI-powered tool, MELD Graph, has been developed to detect subtle brain abnormalities in children with epilepsy. The tool improves detection rates by 64% compared to human radiologists, reducing delays in diagnosis and treatment. This could lead to faster surgical interventions, improved outcomes, and reduced costs for the NHS.
Ebru Demir aims to study how groups of AI-driven microswimmers move in biological fluids for potential applications in drug delivery, fertility treatments, and other medical fields. Her research combines artificial microswimmers with machine learning to uncover the underlying physics governing their movement.
A new AI model measures how fast the brain ages by analyzing MRI scans, providing a more accurate picture of brain health. The tool closely correlates faster brain aging with increased cognitive decline and dementia risk, offering potential for early biomarkers and personalized treatment.
The ESMO Targeted Anticancer Therapies Congress 2025 features state-of-the-art presentations on new targets, tumour-agnostic drug development, and the role of artificial intelligence in cancer treatment. The congress also highlights recent study results and their potential impact on precision medicine.
Research team develops novel method to exploit frictionless sliding for improved memory performance and energy efficiency. The new technology enables unprecedentedly efficient data read/write operations while consuming significantly less energy.
A new review reveals AI's potential to predict diabetes subtypes, identify high-risk patients, and tailor solutions to individual needs. AI tools can detect early signs of eye damage from diabetes as accurately as specialists, improving accuracy and reducing healthcare costs.
Researchers developed a new zero-shot AI pipeline that leverages open-source foundation models like Segment Anything Model (SAM) and Grounding DINO to improve accuracy in automated image segmentation for remote sensing. The pipeline achieves outstanding segmentation results, reaching up to 99% accuracy, and operates in a zero-shot manner.
Researchers developed a frailty index using electronic health record data from over 500,000 patients, identifying those at high risk of adverse health outcomes. The tool classifies patients as robust, pre-frail, frail or very frail based on age-related health deficits.
Researchers identified recent advancements in bioinformatics foundation models, enhancing understanding of molecular landscapes and providing practical foundations for innovation in molecular biology. The models are versatile and essential tools for various downstream tasks, including genomics and drug discovery.
A recent study reveals substantial differences in fear levels towards AI replacement of jobs across cultures, with India, Saudi Arabia, and the US reporting highest fear levels. The study highlights occupation-specific fears, with judges consistently ranked as most feared and journalists as least feared.
Text-to-image technology demonstrates great potential in urban and rural planning design, offering fresh perspectives and tools for innovation. Experimental results show advantages in design process optimization, image generation efficiency, and complex scene modeling.
A new framework for understanding complex systems has been introduced by a groundbreaking study led by Professor Ginestra Bianconi from Queen Mary University of London. The study establishes the field of higher-order topological dynamics and reveals how hidden geometry shapes brain activity, climate patterns, and artificial intelligence.
An international team of researchers has created a detailed map of individual cells in the adult lung, including those affected by chronic lung disease. The AI-driven finding shows that some lung tissue in patients with idiopathic pulmonary fibrosis (IPF) exhibits signs of the disease before significant structural changes occur.
Researchers found that large language models use a semantic hub mechanism to process diverse data, integrating information from various modalities. They demonstrated that models can change their outputs by intervening with text in the dominant language, even when processing other languages.
Researchers developed a machine learning model that predicts the presence of animal feeding operations with high accuracy, filling a data gap crucial for managing their environmental impacts. The model uses predictors such as surface temperature and phosphorus levels to identify locations without relying on aerial images.
Researchers at Worcester Polytechnic Institute are developing a lightweight, flexible robotic arm that enables wheelchair users to safely grasp and carry objects out of reach. The project builds on origami-inspired designs and novel fabrication methods for modules made of lightweight plastics, 3D printed components, and sensors.
A new study from the University of Surrey emphasizes the need for transparency and trustworthiness in AI models. The research proposes a comprehensive framework known as SAGE to ensure that AI explanations are contextually relevant to end-users.
Thatchaphol Saranurak and Andrew Owens have been awarded Sloan Research Fellowships for their innovative work on graph networks and machine perception systems. Their research aims to create more efficient algorithms for computing dynamic systems, such as social networks and traffic patterns.
A new study forecasts Australia's road traffic fatalities to rise to 998 by 2030 and 715 by 2050, with older drivers and male motorcyclists at the greatest risk
A new study from the University of South Australia found that most people trust AI in situations where the stakes are low, such as music suggestions. However, those with poor statistical literacy or little familiarity with AI were just as likely to trust algorithms for trivial choices as they were for critical decisions. The study also...
Validaitor offers a unique platform for AI governance, risk management, and automated testing, reducing certification costs by up to 80%. KIT's investment supports the development of trustworthy AI solutions, combining expertise in cybersecurity and energy sectors.
A study reveals that 65.8% of adults have low trust in their healthcare system's use of artificial intelligence, and 57.7% fear AI-related harm. Hospitals should increase or improve their communications with patients about AI tools to build trust.
INSEAD experts Tim Gordon and Theos Evgeniou explore the dual races of AI-driven economic growth and global leadership in a free webinar. They examine risks of market bubbles and discuss strategic implications for businesses and policymakers.
The INSEAD webinar delves into the challenges and opportunities of deploying multi-agent AI systems in large-scale enterprise environments. Experts will discuss balancing automation with strategic control and the potential for companies to operate without human involvement.
A team of researchers developed a smart jacket with environmental sensors, heat-generating yarns, and AI to monitor and regulate temperature. The jacket provides immediate temperature readings and color-changing yarns to indicate potential overheating.
Researchers have designed a compact, high-efficiency flow battery test system that requires an order of magnitude less starting material while delivering results comparable to standard lab-scale systems. The mini flow cell design is geared towards rapid screening and development of new battery materials, reducing the time and resources...
Researchers at PNNL developed a mini flow battery test system that requires less starting material while delivering comparable performance to standard lab-scale systems. This innovation reduces time and resources needed for testing new battery materials, accelerating the discovery of grid energy storage technology.
The NUS Institute for Functional Intelligent Materials is hosting the AI4X 2025 conference to explore how AI is driving breakthroughs across various natural sciences. Scientists, industry leaders, and innovators will share their knowledge on applying AI to Natural Science and Finance.
Researchers have created a novel self-healing electronic skin that repairs itself in seconds, surpassing existing technologies by up to 80%. This technology integrates artificial intelligence and offers real-time fatigue detection and muscle strength assessment with remarkable precision.
Lydia Kavraki was elected to the National Academy of Engineering for her groundbreaking contributions to robotics, biomedicine, and artificial intelligence. Her work has revolutionized motion-planning algorithms and enabled robots to collaborate with humans safely.
Relativity Networks develops patent-pending HCF cable that transmits data nearly 50% faster than conventional glass fiber, expanding data center geographical optionality. UCF's College of Optics and Photonics supports the innovation through industry partnerships and research collaborations.
The University of Oulu's 6G research programme explores AI-based applications and services for mobile networks. The recently published paper focuses on artificial intelligence methods to provide communication links and offer AI-based services between devices, base stations, massive data centres, and cloud services.
Researchers at the University of Michigan are developing AI-powered mobile clinics to improve access to healthcare in rural areas. The clinics will be equipped with an AI agent that guides medical generalists through unfamiliar diagnoses and procedures, reducing costs and improving patient outcomes.
Researchers at the University of Konstanz developed an AI system to speed up nanoparticle measurements, reducing time from hours to minutes. The system, based on Meta's open source AI technology, can accurately count complex particles and measure individual particles with high precision.
A new study from the University of Surrey explores the transformative potential of Metaverse technologies in manufacturing. The integration of advanced technologies like AR and digital twins aims to re-empower humans by making them an essential part of the manufacturing equation.
The initiative focuses on promoting conscious design processes to create quieter products, buildings and transportation systems to reduce noise pollution. By adopting a systems-thinking approach, it will address the root causes of noise and its impacts on people, environment and economy.
Discounted hotel rates available at select hotels near the Anaheim Convention Center. The Global Physics Summit will feature nearly 14,000 individual presentations on new research in various fields.
MIT researchers have developed a new approach to assess predictions with a spatial dimension, leading to more accurate forecasts in spatial prediction tasks. The new method provides better validations than classical methods, especially in cases where assumptions about data independence break down.
A groundbreaking study analyzed data from over 78,000 cancer patients to identify nearly 800 genetic changes impacting survival outcomes. The research also discovered genes significantly associated with survival in various cancers, such as breast, ovarian, skin, and gastrointestinal cancers.
Researchers developed Torque Clustering, an unsupervised learning method that efficiently uncovers patterns in vast datasets without human guidance. The algorithm outperforms traditional methods, offering a potential paradigm shift for robotics and autonomous systems.
Research finds people's skepticism towards artificial moral advisors (AMAs) stems from their perceived lack of human experience and genuine understanding. AMAs are seen as less trustworthy than human advisors when making utilitarian decisions, highlighting a need to align AI capabilities with human values.
A new machine learning model, NAS-WD, has improved the accuracy of detecting 'woody breast' in chicken meat to 95%, allowing for better quality assurance and customer confidence. The model uses hyperspectral imaging to analyze complex data from images, enabling more accurate detection than traditional methods.
Researchers have proposed a new fault-tolerant framework for distributed deep learning model training that minimizes overhead and improves efficiency. By utilizing idle system resources during training, the framework effectively coordinates tasks with fault-tolerance functions.
A £1 million grant-funded project aims to advance production of next-generation, paper-based packaging for liquids. Researchers will develop novel coating processes, mechanistic modelling, computer vision, and AI to create 'dry' spray coatings that are food-safe, degradable, and environmentally friendly.
The OmicsFootPrint tool uses AI to convert complex biological data into circular images, helping researchers visualize disease patterns and identify personalized therapies. The tool demonstrated high accuracy in distinguishing between different cancer types and has potential for studying neurological disorders.
A new AI-based tool can translate a person's thoughts into continuous text without requiring language comprehension, and it can be trained in under an hour. The system was developed by adapting a previous brain decoder to a new person using short, silent videos.
A recent study emphasizes the urgent need to address bias in generative AI systems, which can distort outcomes and erode public trust. The research suggests that developing and deploying ethical, explainable AI is crucial to ensure fairness and transparency in critical decision-making areas.