Articles tagged with Artificial Intelligence
Researchers propose a new approach to reduce the tradeoff between overhead and protecting machines against vulnerabilities. The 'Vulnerability-Adaptive Protection Paradigm' applies different protection strategies to different parts of the system, allocating resources more wisely.
A retrospective cohort study found that AI algorithms can identify women at high risk of developing breast cancer 4-6 years before detection. The results suggest using commercial AI algorithms as a pathway to personalized screening approaches, leading to earlier cancer diagnosis.
Researchers at Arizona State University have developed new diagnostic tools using artificial intelligence (AI) to help identify myopic maculopathy, a serious eye condition. The AI-powered systems can analyze retinal images and predict the correct classification of the disease, enabling more accurate treatment recommendations.
A Princeton-led research team has built the first neuron-by-neuron and synapse-by-synapse roadmap through the brain of an adult fruit fly. The map reveals connections within the brain at every scale, enabling researchers to better understand its underlying logic and potentially develop tailored treatments for brain diseases.
The Endocrine Society's inaugural Artificial Intelligence in Healthcare Virtual Summit will explore AI's potential to improve medical care, advance research, and leverage big data. Key sessions will discuss predictive analytics, machine learning algorithms, and natural language processing.
A study by Osaka Metropolitan University found that ChatGPT's diagnostic performance for brain tumors was comparable to that of neuroradiologists, with an accuracy rate of 73%. The model's performance varied depending on the type of clinical report written, with higher accuracy when using reports from neuroradiologist writers.
The U.S. Department of Energy has selected Kate Petersen Mace as the project director for the High Performance Data Facility (HPDF), a first-of-its-kind project providing resources for data-intensive science. Mace will lead the team in developing transformational capabilities to serve the DOE community.
A new method called Clio allows robots to make task-relevant decisions by identifying the parts of a scene that matter. In real experiments, Clio successfully mapped scenes at different levels of granularity based on natural-language prompts and enabled robots to grasp objects of interest.
The ADA Forsyth Institute has received a $6.2 million grant from the NIH to design an AI-driven amalgam replacement for dental restoratives. The new material will feature self-healing and antimicrobial properties, responding to biological signals in each individual patient's mouth.
Researchers developed a method combining AI and thermal cameras to enhance weightlifting training, providing data-driven insights for targeted strategies. The approach enables real-time tracking of muscle activation, strain detection, and temperature changes, ultimately helping athletes optimize performance and safety.
A new Columbia University School of Nursing-led study explores how patients view the use of artificial intelligence (AI) to improve mental health care. The survey found that 49.3% of participants considered AI beneficial for mental health care, but with concerns over incorrect diagnoses and patient autonomy.
The study challenges the idea of creating artificial general intelligence (AGI) with human-level cognition, citing limitations in replicating human cognition. Researchers argue that even under ideal circumstances, it is impossible to achieve AGI due to the complexity of cognitive processes.
A team of researchers aims to improve autonomous vehicle safety by identifying and mitigating vulnerabilities in software and hardware. They plan to use knowledge gained from a $926,737 NSF award to design protection mechanisms that can be applied selectively to ensure safety while maximizing efficiency.
A new AI tool identified drug candidates for over 17,000 diseases, including conditions without treatments, and predicted potential side effects. The model was trained on a broader dataset than current models, enabling it to make more accurate predictions and offering a faster and more cost-effective way to develop therapies.
A recent study published in PNAS Nexus found that widespread adoption of large language models like ChatGPT led to a significant decline in user activity on Stack Overflow. The study highlights the impact of ChatGPT on public knowledge sharing and its implications for AI's future.
A systematic review by PPPL researchers found that most journal articles on machine learning for solving fluid-related PDEs are biased towards machine learning, with negative results underreported. The authors propose rules to make fair comparisons and argue that cultural changes are needed to address systemic problems.
A Kennesaw State University researcher is developing secure AI models that not only protect personal information but also reduce energy use. Her goal is to create a federated learning system that overcomes specific vulnerabilities of current systems, improving data transmission security and confining AI training to individual devices.
Researchers at UT Austin developed AI model EvoRank to design protein-based therapies and vaccines by leveraging nature's evolutionary processes. The model identifies useful mutations in proteins, offering a new approach to biomedical research and biotechnology.
A study from the University of Arkansas System Division of Agriculture has improved food quality computer predictions by using human perception data. The researchers trained a computer model to mimic human adaptation to environmental conditions, resulting in more consistent predictions under different lighting conditions.
A study using machine learning to analyze patents and job task descriptions found that AI is likely to augment rather than replace many jobs. The most impacted occupations included orthodontists, security guards, and air traffic controllers.
Researchers from the University of Toronto's Rotman School of Management found that campaign size, social capital, and reward options are top factors in success. Machine learning identified a sweet spot for campaign duration and reward options, with success plateauing after 50 options.
A PSU English professor is using a grant from the National Science Foundation to study one of the world's fastest and largest supercomputers, Aurora. The research aims to answer questions about how supercomputers work, their applications in science and industry, and their impact on the US's position in scientific advancement.
Researchers have identified coupling design methods, composite manufacturing techniques, and future prospects for micro/nanorobots. The review explores three core functions: mobility, controllability, and load capacity, offering insights into designing high-performance MNRs.
Researchers at NJIT's Institute for Space Weather Sciences and Ying Wu College of Computing are developing an AI-powered space weather forecasting system called SolarDM. The system uses synthetic vector magnetograms to provide critical data for predicting solar eruptions, which could offer a three-day forecast horizon.
Researchers are developing AI technology to quantify emotions, improving emotional recognition in fields like healthcare, education, and customer service. This technology can create personalized experiences and enhance comprehension of human emotions, revolutionizing human-computer interactions and mental health assessments.
Scientists used artificial intelligence and molecular dynamics simulations to understand how enzymes fold lasso peptides into a unique structure. They identified key residues important for interaction with the substrate, enabling the design of new cyclase variants that can produce potent lasso peptides.
The integration of artificial intelligence in intratumoral immunotherapy can refine diagnoses, guide interventions, predict treatment responses, and adapt therapeutic strategies. This enables the enhancement of patient outcomes, including improved survival rates and quality of life.
A new AI model called Crystalyze can analyze X-ray crystallography data to determine the structure of powdered crystals. The model was trained on a database of over 150,000 materials and successfully predicted structures for over 100 previously unsolved patterns.
Researchers found that large language models used in home surveillance can make inconsistent decisions about calling the police, even when videos show no crime. Models often disagreed with each other and exhibited inherent biases influenced by neighborhood demographics.
The UC3M-Universia Chair aims to address the challenges of large tech companies' data use and create a new, transparent and fair personal data economy. Researchers will develop models and algorithms linked to AI that are interpretable and unbiased.
Researchers aim to advance training methodologies for superintelligent systems, ensuring they learn from imperfect and evolving data. The project seeks to develop new techniques to improve AI reliability, reduce biases, and increase accuracy.
Two new AI institutes will harness AI to analyze vast amounts of astronomical data, accelerating discoveries and democratizing access to research. Researchers at all career levels will gain access to trustworthy AI tools, enabling them to explore the cosmos with newfound insights.
Researchers analyzed 2 million Google Street View images to explore the utility of digital data in informing public health decision-making. They found that neighborhoods with more crosswalks had lower rates of obesity and diabetes, but no significant link was found between sidewalks and health outcomes.
A new AI-based system has been shown to reduce the risk of unexpected deaths in hospitalized patients by identifying those at high risk of deteriorating health. The system, CHARTWatch, uses real-time alerts and enhanced communication between nurses and physicians to support high-quality care.
CREME, a new AI-powered virtual laboratory, allows scientists to run thousands of virtual experiments with the click of a button to identify key regions of the genome. This breakthrough may lead to discovering new therapeutic targets and giving scientists access to cutting-edge technology without a real laboratory.
Researchers at Purdue University found that autonomous vehicles can interpret and respond to commands from passengers using large language models like ChatGPT. This technology allows the vehicle to personalize its driving to a passenger's satisfaction and take into consideration traffic rules, road conditions, and weather.
A new study by Boston University researchers found that the majority of social media posts from e-cigarette brands left out health warnings, despite a federal requirement to include them. The study used AI to analyze over 2,000 Instagram posts and discovered that only 13% complied with FDA health warning requirements.
Researchers at Peking University developed a dual-IMC scheme to accelerate machine learning and improve energy efficiency. The new computing scheme stores both neural network weights and inputs in memory, reducing data movement and power consumption.
Genethon has developed an innovative gene therapy vector that effectively targets muscle tissue while reducing the risk of liver penetration. The new capsid design uses AI predictive methodology to improve efficacy and safety, paving the way for more effective treatments for neuromuscular diseases.
Researchers at Indian Institute of Science develop a neuromorphic platform that stores and processes data in 16,500 conductance states, cutting energy consumption by a huge margin. This breakthrough could enable complex AI tasks on personal devices, transforming the development of AI tools.
Using AI and the connectome, researchers can now predict individual neuron activity in living brains. The new model predicts neural activity in response to visual input and accurately reproduces over two dozen experimental studies.
A $3.9 million grant from the National Institutes of Health supports a study on wearable sleep trackers and AI in predicting blood biomarkers of Alzheimer's disease in at-risk individuals. The research aims to create an 'early warning system' for flagging individuals with a genetic predisposition to Alzheimer's.
Researchers at Klick Labs developed an AI technique using vocal biomarkers to predict chronic high blood pressure with up to 84% accuracy. The study used machine learning to analyze hundreds of indiscernible vocal biomarkers, including pitch variability and speech energy distribution patterns.
The study reveals that local field potential events play a crucial role in processing information, even without external stimuli. The findings offer new avenues for research, diagnosis, and treatment of brain diseases, as well as the development of AI inspired by neuroscience.
A new AI model generates detailed images of cancer tissue that imitate what its staining would look like, reducing the need for resource-intensive lab analyses. The VirtualMultiplexer uses contrastive unpaired translation to create accurate virtual pictures of diagnostic tissue colorations.
Advanced endoscopy combined with AI and digital pathology offers a deeper understanding of inflammatory bowel diseases (IBD). This leads to more accurate diagnoses and improved patient outcomes.
Researchers used Google AI tool to map proteins' configurations and their ability to resist pressure changes, offering insights into protein design and life on other planets. The findings shed light on deep ocean life and could lead to new targets for structural and biophysical studies.
Researchers at Cornell University found that integrating AI into environmental control systems can reduce energy consumption in indoor agriculture by up to 25%. By optimizing lighting and climate regulation, AI helps create an energy-efficient solution for optimal plant growth, carbon dioxide levels, and ventilation requirements.
Researchers developed an AI model to detect lung disease in premature babies by analyzing their breathing patterns while sleeping. The Long Short-Term Memory (LSTM) model achieved 96% accuracy in classifying flow values as belonging to a patient with BPD or not, enabling early diagnosis and treatment.
A study found that ChatGPT performed better than trainee doctors in assessing complex cases of respiratory disease in areas such as cystic fibrosis and asthma. The chatbot's responses were also scored higher for being human-like, while Google's Bard and Microsoft's Bing performed similarly to or worse than trainees.
A deep-learning algorithm developed by astronomer David Harvey can untangle the complex signals of self-interacting dark matter and AGN feedback in galaxy cluster images. The Inception model achieved an accuracy of 80% under ideal conditions, showcasing its potential for analyzing vast amounts of space data.
Researchers at the Florida Museum of Natural History are studying bagworms' unique life cycle and their potential to inform understanding of modern climate change. They'll also analyze fossils from ancient mammal communities affected by rapid warming, as well as use AI to model future disease outbreaks.
A new AI tool called CAR-E is being developed to provide personalized coaching conversations for medical students and residents, encouraging reflective practice and enhancing their skills. The web-based tool will use a coaching approach to prompt students to think back on their clinical encounters and knowledge gaps.
Researchers Maria Eichlseder and Fariba Karimi will study keyless encryption and AI's impact on online social networks to promote fair algorithms. Their projects aim to address open problems in cryptographic systems and quantify intersectional inequality.
Researchers at McGill University developed AI-guided feedback systems that outperformed human instructors in teaching neurosurgical skills. The study found that expert instruction alone led to poorer surgical learning outcomes, highlighting the potential of AI to enhance learner surgical skills acquisition.
Researchers will investigate the psychological influence of online communications developed with artificial intelligence, including misinformation and radicalizing messages. The team aims to develop a holistic model of multi-level belief resonance that can counter foreign influence on campaigns and radicalization.
A team at NUS Yong Loo Lin School of Medicine leveraged an artificial intelligence-derived platform, CURATE.AI, to guide treatment for a patient with Waldenström macroglobulinemia, a rare blood disorder. The trial demonstrated substantial improvement in red blood cell levels and minimised side effects.
A Mass General Brigham-led study found that a large language model improves the accuracy of immune-related adverse event detection, identifying additional cases not picked up by manual adjudication. The model demonstrated excellent specificity and sensitivity, opening up opportunities for collaboration among institutions.
A machine-learning algorithm called xFakeSci has been developed to detect AI-generated scientific articles, with a success rate of nearly 94%. The tool analyzes word patterns and bigrams to distinguish between real and fake papers, highlighting the need for comprehensive detection methods as AIs become increasingly sophisticated.
A study at the European Society of Cardiology Congress found that an AI-enabled digital stethoscope helped doctors identify twice as many cases of pregnancy-related heart failure compared to a control group. The tool was 12 times more likely to flag heart pump weakness, leading to better diagnosis and potentially life-saving treatment.