Articles tagged with Artificial Intelligence
Researchers found that AI models that analyze medical images can predict patient demographics with high accuracy but struggle to diagnose patients from diverse backgrounds. The models use demographic shortcuts, leading to incorrect results for women, Black people, and other groups.
A newly developed deep learning algorithm has outperformed existing methods in predicting osteoporosis risk, potentially leading to earlier diagnoses and better outcomes. The model identified key factors such as weight, age, and grip strength as significant contributors to osteoporosis risk.
Researchers developed an AI model that accurately predicts metal yield strength by combining physical theory with machine learning. The model outperforms traditional methods, which often rely on extensive experimentation.
Researchers at U of T have developed a deep-learning model called PepFlow that can predict the full range of conformations for peptides, which are shorter than proteins but perform similar biological functions. The model combines machine learning and physics to capture precise and accurate conformations within minutes.
Researchers found that people are more likely to accuse others of lying when AI makes an accusation, highlighting the need for caution in implementing similar technologies. The study suggests that over-reliance on AI lie-detection tools may lead to careless accusations and reinforce biases.
A study found that large language models (LLMs) like ChatGPT underperform state-of-the-art detectors but can explain their analysis in plain language. LLMs' semantic knowledge makes them well-suited for detecting deepfakes, providing a common sense understanding of reality.
A new study from the University of Copenhagen reveals that AI has helped detect significantly more cases of breast cancer and reduce radiologist workloads. The AI system has been used to analyze tens of thousands of X-rays every year, resulting in a 12% increase in detected cases, including more small tumours of one centimetre or less.
AlphaFold's groundbreaking ability to predict protein structures is set to transform predictive medicine, enabling the development of personalized vaccines and adaptive clinical trials. However, the review also highlights crucial challenges and ethical considerations surrounding AI integration with clinical data.
The special issue explores challenges and opportunities in managing synthetic genomics risks, introducing a common global baseline for nucleic acid synthesis screening. Review articles provide insights into enhancing gene synthesis security and biosecurity practices of synthetic DNA providers.
Researchers found that AI-generated submissions went undetected in a UK university's examinations system, earning higher grades than real students' answers. The study suggests that AI tools could potentially allow students to cheat and achieve better grades than their peers.
A recent study published in PLOS ONE found that AI-generated exam answers were undetectable in 94% of cases, outperforming human submissions. The University of Reading's blind test challenged educators to detect AI-generated content, highlighting the need for global education sector policies and guidance on AI use.
Researchers at Boston University developed an AI model that analyzes speech patterns to predict the likelihood of Alzheimer's disease in patients with mild cognitive impairment. The model achieved an accuracy rate of 78.5% and could potentially revolutionize dementia screening, making it more accessible and efficient.
A new AI model has been developed to improve clinical trial recruitment for eye disease, specifically Geographic Atrophy. The system identified almost twice as many candidates and with higher precision compared to conventional approaches, showing promise for overcoming a major obstacle in GA clinical trials.
Researchers investigated the efficiency of modern neural network-based generative models, comparing them to traditional sampling techniques. The study found that modern diffusion-based methods may face challenges due to a first-order phase transition, but also exhibit superior efficiency in certain cases.
Researchers found that humans distinguish between voices based on emotional cues, with happy voices being perceived as more human-like. However, the brain's response differs, with AI voices eliciting stronger responses in error detection and attention regulation areas.
A new study found that animals use a wide range of strategies to accomplish tasks, many of which are just as effective as the optimal solution but require less brain power. The research provides a theoretical framework for understanding these 'good enough' strategies and their potential applications in animal behavior.
A new model developed by Flatiron Institute researchers proposes that individual neurons exert more control over their surroundings, which could be replicated in artificial neural networks. This updated model treats neurons as tiny 'controllers' and may lead to better AI performance and efficiency.
A new study developed an AI-based approach, DiffPALM, to predict protein interactions with high accuracy, outperforming traditional methods. This advancement has significant implications for drug development and disease treatment, and the researchers have made it freely available for further research.
Researchers found ChatGPT consistently ranks resumes with disability-related honors and credentials lower than the same resumes without those honors. However, when trained to prioritize disability justice and DEI principles, the system improved its rankings for most disabilities, except for autism and depression.
Scientists at UVA and Toyota Research Institute create language representations of driving behavior to enable robots to associate words with environmental interactions. This allows cars to provide guidance and adjust speed in challenging situations, improving safety and usability.
TopoFormer uses a transformer model trained on tens of thousands of protein-drug interactions to recreate 3D structures as one-dimensional information that current models can understand. This enables more accurate predictions of new drug interactions and potentially reduces development time and costs.
A new system named SQUID, a computational tool created by Cold Spring Harbor Laboratory scientists, helps interpret how AI models analyze the genome. It reduces background noise and leads to more accurate predictions about genetic mutations.
Research suggests that large-language models could play a role in managing the energy grid, particularly in emergency response, crew assignments, and wildfire preparedness. However, significant challenges remain, including data availability, safety guardrails, and reliability, which must be addressed to ensure safe deployment.
Researchers at Cold Spring Harbor Laboratory designed a new way for AI algorithms to move and process data more efficiently, inspired by the human brain. This design allows individual AI neurons to receive feedback and adjust on the fly, processing data in real-time.
Deep learning enhances STS diagnosis and treatment by automating contouring for radiation therapy and predicting treatment responses. The review highlights key areas where deep learning is making an impact, including data acquisition and processing, algorithm development, clinical applications, and pathological diagnosis.
A team of researchers created an advanced method for automatic microfossil detection and analysis using AI. The method has shown great potential in utilizing AI to analyze vast amounts of microfossil data, potentially helping geologists better utilize wellbore samples.
A Finnish study found that teaching AI basics to 4th and 7th graders improved their understanding of the technology. The students designed and created AI apps, which helped them develop conceptual understanding and critical thinking skills. The program also explored the impact and ethics of AI on children's daily lives.
A recent study proposes a roadmap for integrating edge AI into farming practices to improve efficiency, quality and safety of agricultural production. This technology enables devices to make smarter decisions faster without connecting to the cloud or off-site datacenters.
A study by Nanyang Technological University found that eight in 10 gastroenterologists in the Asia-Pacific region accept and trust AI-powered tools for diagnosing colorectal polyps. The study also highlights the need for more research into what influences doctors' acceptance of AI in their medical practice.
Researchers at Mass General Brigham developed a generative AI process that screens patients for clinical trial eligibility with high accuracy and reduced cost. The process, called RECTIFIER, was compared to traditional screening methods and found to be more accurate and cost-effective, with an estimated cost of $0.11 per patient.
Leading academics recommend extending Sustainable Development Goals to 2050, addressing climate and biodiversity targets, and incorporating AI impact, community input, and inclusive consultations. They also suggest reforming global finance architecture and framing goals as missions with clear targets.
A new AI model developed by Surrey researchers and Stanford University can accurately identify objects in complex scene sketches, even from non-artists. The model achieved an 85% accuracy rate, outperforming previous approaches that relied on labelled pixels.
Researchers developed a technique called Multi-View Attentive Contextualization (MvACon) to improve AI's ability to map 3D spaces using 2D images from multiple cameras. MvACon significantly improved the performance of vision transformers in locating objects and detecting speed and orientation.
Researchers at UC San Diego School of Medicine are developing an AI model to predict opioid addiction in high-risk patients. The model uses generative artificial intelligence to analyze genomic, social determinants of health, clinical, procedural, and demographic data to identify patients at greatest risk.
Researchers developed an AI-powered method to train robotic exoskeletons, enabling users to save energy while walking, running, and climbing stairs. The new approach allows for rapid development of exoskeleton controllers without lengthy human-involved experiments, offering promise for aiding individuals with mobility challenges.
A research team at Pohang University of Science & Technology has developed a new type of hafnia-based ferroelectric memory device that can store 16 levels of data per unit transistor. The device operates at low voltages, high speeds and exhibits stable characteristics.
Researchers from Shinshu University have created a novel composite material with exceptional capabilities for motion and physiological sensing. The new sensor design showed significant performance and stability improvements, enabling practical use in wearable applications.
The Goethe SDG Contest recognized three award-winning start-up teams: HOPES Energy, MySympto, and CERES FieldCheck. These innovative projects leverage AI and sustainable products to address pressing global challenges, including energy storage, healthcare efficiency, and environmental conservation.
A sweeping review reveals how integrating AI technologies can improve the reliability, predictability, and efficiency of solar power generation. Researchers explored maximum power point tracking, power forecasting, and fault detection in PV systems.
The article explores how AI can be applied to the electric power and energy industry, demonstrating its potential as a valuable technology for asset management. Machine learning techniques are showcased as a solution to improve efficient and sustainable energy networks.
Researchers at North Carolina State University have developed an AI-powered method to train robotic exoskeletons to autonomously assist users in various movements, reducing energy consumption by up to 24.3% for able-bodied individuals and 15.4% for those with mobility impairments.
Scientists developed an AI-powered system to track tiny devices that monitor markers of disease in the gut. The system includes a wearable coil and ingestible pill with optical gas-sensing membranes, pinpointing device location and measuring gases like ammonia. Future improvements aim to make the device smaller and more power-efficient.
A new computer vision technique developed by MIT engineers significantly speeds up the characterization of newly synthesized electronic materials. The technique automatically analyzes images of printed semiconducting samples and quickly estimates two key electronic properties: band gap and stability.
Generative AI has both positive and negative effects on social equality, impacting work, education, healthcare, information, and misinformation. Policymakers are urged to implement policies such as tax code changes, data unions, and anti-misinformation campaigns to ensure the technology is used to increase equality
Researchers found that advertising on misinformation websites is pervasive among companies across several industries and amplifies the financing of misinformation. Consumers also face substantial backlash when ads appear on such websites, switching away from companies whose products are advertised on misinformation outlets.
Researchers developed HypOp, a framework using unsupervised learning and hypergraph neural networks to solve combinatorial optimization problems significantly faster. The framework can also tackle certain problems that prior methods cannot effectively solve.
The Omega tool enables rapid analysis of complex biological images through natural language conversations, prioritizing ease of use and democratizing bioimage analysis. By leveraging large language models, scientists can process and analyze images without extensive programming skills.
A new study reveals that ChatGPT's automated content moderation filters can flag nearly 20% of its own generated scripts for content violations, including half of PG-rated shows. The research raises questions about the efficacy of using AI as a tool in scriptwriting and its potential impact on artistic expression.
A new study analyzed over 14,600 scientific publications funded by more than $4 billion in NIH grants, revealing key research topics such as clinical trials, vaccine distribution, and virology. The findings suggest that half of the funding went to five states: North Carolina, Washington, New York, California, and Massachusetts.
Researchers at Osaka Metropolitan University developed a machine learning-based deicer that offers higher performance while minimizing environmental harm. The new mixture of propylene glycol and sodium formate solution shows improved ice penetration capacity, reducing the need for substance use.
Researchers developed an AI-driven liquid biopsy to identify lung cancer through DNA fragment patterns in the blood, demonstrating a high negative predictive value of 99.8%. The test could quadruple lung cancer detection rates and prevent thousands of deaths if implemented nationwide.
Researchers are using a hyper-diverse group of herbs called bellflowers to understand relationships between species, origins, and human activity. The project combines genetic data, archaeological records, and computer modeling to create a playbook for answering similar questions in other regions.
A recent NTU Singapore study found that eight in ten gastroenterologists accept and trust the use of AI-powered tools in diagnosing and assessing colorectal polyps. The study, which surveyed 165 doctors in the Asia-Pacific region, also found that more experienced gastroenterologists perceived a lower risk of AI tools.
A Carnegie Mellon University study finds that people with autism are using AI chatbots for workplace advice, but raises questions about the quality of the advice and the need for inclusivity. The research highlights the importance of involving individuals with autism in the development of technology to address their specific needs.
Researchers in Italy have successfully monitored invasive stink bugs using drones and AI, reducing disruption and improving data capture. The system achieved a 97% detection accuracy, enabling precise forecasting models for integrated pest management strategies.
A new AI-driven tool can accurately diagnose Lewy body dementia by analyzing changes in vocal emotional expressions. The study found that individuals with Lewy body dementia exhibited more negative and calmer emotional expressions compared to those with Alzheimer's disease and healthy controls.
A new open-source platform called CheckMate allows users to interact with and evaluate the performance of large language models (LLMs) like ChatGPT. Researchers found that while LLMs can be helpful, they also make mistakes and provide incorrect information.
A study published in Radiology found that AI significantly improved breast cancer detection and reduced false-positive findings. The AI system detected more cancers while lowering the rate of unnecessary recalls, reducing radiologist workload by 33.4%.
A new AI model developed by researchers at the University of Jyvåskilö can predict and respond to human emotions, improving user experience. The model simulates cognitive evaluation processes to assess emotional responses to events, enabling computers to preemptively predict and mitigate negative emotions.
Global greenhouse cultivation has increased rapidly, with Asia accounting for 60.4% of global coverage. The practice provides opportunities for local food security and poverty alleviation, but raises environmental concerns such as water pollution and energy consumption.