Articles tagged with Artificial Intelligence
Researchers developed an AI model that addresses uncertainties in renewable energy generation and electric vehicle demand, making power grids more reliable. The model uses multi-fidelity graph neural networks to optimize solutions within seconds, improving grid performance even under unpredictable conditions.
A new AI tool called PIONEER has been developed to predict protein-protein interaction mutations in hundreds of diseases, including dozens of cancers. The tool allows researchers to navigate the interactome for over 10,500 diseases and identify potential drug targets.
Researchers have developed a reconfigurable three-dimensional integrated photonic processor specifically designed to tackle the subset sum problem, a classic NP-complete challenge. The processor operates by allowing photons in a light beam to explore all possible paths simultaneously, providing answers in parallel and demonstrating hig...
Using Clinical Design Support Systems (CDSS) can help make maternity services safer for pregnant women, with a meta-analysis of 35 studies showing a 1.69 times higher odds of improved outcomes. The findings support the use of AI and related software tools to improve pregnancy care.
A new study finds that AI-powered models exhibit similar levels of accuracy as ophthalmologists in identifying infectious keratitis, a leading cause of corneal blindness worldwide. The AI models displayed a sensitivity and specificity of 89.2% and 93.2%, respectively, matching the diagnostic accuracy of human experts.
Artificial intelligence is creating a new way of thinking with System 0, an external cognitive process that enhances human abilities. This system relies on AI's capabilities to process information and provide suggestions, but humans must interpret and assign meaning to the results.
A new study by Monash University researchers highlights essential factors for adapting Generative AI (GenAI) to support human learning in all levels of education and workplaces. The key considerations include understanding how to use GenAI to enhance human learning while fostering critical thinking and self-reflection skills.
A new AI-based system, BELA, accurately assesses IVF embryo quality by analyzing time-lapse video images and maternal age. The system generates a predictive score for euploidy or aneuploidy, offering an objective measure of embryo quality.
A new system dubbed SonicSense allows robots to interpret the world through acoustic vibrations, giving them a richer ability to 'feel' and understand objects. The system, featuring a robotic hand with contact microphones, can identify materials, shapes, and recognize objects in complex environments.
A pilot study found that AI tools can accurately process hospital quality measures, achieving 90% agreement with manual reporting. This can lead to more efficient and reliable approaches to healthcare reporting, especially for complex measures like severe sepsis and septic shock.
A systematic review of randomized clinical trials found that AI-assisted colonoscopies increased overall detection of colonic polyps and adenomas, with a small increase in procedure time. Researchers also found no clear differences in benefit for detecting adenomas across different AI systems.
A team of scientists and experts led by PNNL has developed a cloud computing approach to democratize access to emerging resources. They demonstrated that cloud computing can provide an agile complement to high-performance computing facilities, enabling complex chemistry workflows to be completed in days instead of months. The initiativ...
A team of researchers has developed an AI-powered system to provide evidence-based caregiver training information and support to individuals with Alzheimer's and related dementia. The system is designed to be personalized and accessible, using validated resources and tools to address the unique needs of caregivers.
Penn Engineering researchers found that certain features of AI-governed robots have security vulnerabilities, putting safety at risk. The 'jailbreak' rate of OpenAI's ChatGPT was 100% in just days, bypassing safety guardrails and allowing manipulation or hacking.
A recent poll found that 74% of people over 50 would not trust health information generated by artificial intelligence. Only 32% of older adults reported it's very easy to find something accurate online. Health systems, academic institutions, and government agencies can use the results to improve health information accessibility.
Researchers at UVA's School of Engineering and Applied Science have developed an AI-driven intelligent video analyzer capable of detecting human actions with unprecedented precision and intelligence. The system, called SMAST, promises to transform industries such as surveillance, healthcare, and autonomous driving.
A new project, 'Crowd-Assisted Human-AI Teaming with Explanations,' aims to develop an interactive AI system that leverages the collective strengths of human crowd workers and machine learning models. The researchers will use crowdsourcing platforms to recruit experts and non-experts to perform tasks, making the system more robust and ...
Researchers develop Knowledge-enhanced Bottlenecks (KnoBo) method to emulate human physicians' education, resulting in more accurate and interpretable AI models for medical image recognition. KnoBo-based models outperform existing best-in-class models on accuracy and robustness, especially in handling confounded data.
The FDA will continue to play a central role in regulating AI technologies that improve health outcomes. The agency emphasizes the need for rigorous oversight of these transformative tools, crucial for protecting patients and clinicians.
Researchers at Rice University develop OpenSafe.AI, a system that leverages responsible AI and hazard models to provide timely insights for emergency response organizations and communities before, during, and after tropical cyclones and coastal storm events. The goal is to enable better preparation and navigation for severe weather.
Researchers at the University of Pennsylvania have developed a new consensus complementarity control (C3) algorithm that allows robots to react to complex physical contact in real-time. The algorithm enables robots to control the motion of sliding objects, a challenging task previously thought to be impossible for autonomous robots.
Researchers at Penn Engineering and PSOM will develop AI systems to predict treatment response in breast cancer, heart attacks, and sepsis. The goal is to support clinicians with accurate and transparent predictions, leading to better health outcomes for patients.
Researchers at Indiana University are developing next-generation ophthalmoscopes to spot early warning signs of diseases like Alzheimer's, diabetes, and heart disease with a simple eye scan. The technology uses machine learning and AI to reduce diagnosis time from days to minutes.
WorldScribe, a new software, uses generative AI to provide real-time text and audio descriptions of surroundings for people who are blind or have low vision. The tool can adjust the level of detail based on user commands or camera frame time.
Researchers have developed AI-enabled detection software that can accurately detect natural debris, litter, or waste blocking culverts. The system can be integrated to existing CCTV systems to provide proactive flood defense, improving safety for response teams.
A study from the University of Surrey found that people with a preference for sweets are at a higher risk of developing depression, diabetes, and suffering a stroke. The researchers used artificial intelligence to group 180,000 volunteers into three profiles: health-conscious, omnivore, and sweet tooth.
The two-year study aims to explore biases in AI systems and develop a 'human-in-the-loop' framework for quality data discovery. It will investigate how humans can be involved as labelers, prompters, and validators to improve data sets and user interfaces.
Researchers argue that AI's impact on public health depends on its development and deployment, warning of potential biases, lack of transparency, and exacerbation of existing harm. However, the authors also highlight AI's potential to improve healthcare systems, access to care, and provide essential services.
Ziyu Yao is creating a language model-powered virtual mathematics classroom to support collaborative learning and promote more equitable education for middle school students from under-resourced communities. The platform aims to provide effective mathematics education and explore the opportunities and risks of Generative AI techniques.
Recent advances in Brain Network Models (BNMs) have improved simulations of brain activities, understanding neuropathological mechanisms, and predicting disease progression. BNMs integrate structural and functional connectivity data to analyze abnormal network dynamics.
Researchers have used AI to analyze digital images of pathology slides and identified risk factors for aggressive brain tumors that differ between men and women. These findings could lead to more individualized care and improved treatment outcomes for glioblastoma patients.
Researchers created SmartCADD, an AI-powered virtual tool combining quantum mechanics and Computer Assisted Drug Design techniques. The tool speeds up the screening of chemical compounds, significantly reducing drug discovery timelines and identifying promising HIV drug candidates.
Researchers at George Mason University are developing an AI-powered system to predict snow water equivalent (SWE) forecasts, utilizing graph neural network-based models and physics-based constraints. The project aims to create more accurate and reliable SWE forecasts by capturing detailed snow accumulation and melt processes.
A recent study explores the potential of AI in ophthalmology to detect elevated HbA1c levels, a marker for high blood sugar and cardiovascular disease. The research highlights the importance of developing trustworthy AI models and addressing challenges in clinical adoption.
The CityUHK team develops a new federated learning technology integrated with research knowledge graphs and large language models to digitally transform STI services. This will create a comprehensive, domain-specific knowledge base and provide intelligent assistant services for researchers.
Researchers used AI to repurpose FDA-approved drugs for chronic pain treatment. The LISA-CPI framework identified compounds that can bind to specific pain receptors and modulate signaling effects. Studies are underway to validate these compounds in the lab, offering a promising approach to advanced pain management.
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.