Articles tagged with Artificial Intelligence
A team of scientists discovered two types of neurons in fruit flies and mice that enable them to identify distinct smells. With experience, these animals can learn to differentiate between very similar odors, a process that could improve machine-learning models and AI systems.
A new project will monitor how changing environmental conditions shape viral outbreaks in wild rodent populations to identify hotspots with high potential for spillover into people. The team will use metaviromics and AI to analyze data from wild rodents in the UK and Eastern Uganda.
Researchers developed an AI model to optimize network allocation, saving bandwidth and reducing computational cost. The model can be adapted for various scenarios, including drone battery conservation and remote surgery.
Researchers used AI to identify 2 promising antigens as candidates for a gonorrhea vaccine, which accurately predicted reduction of bacterial populations. The antigens were tested in lab and animal models, showing efficacy in killing bacteria and decreasing bacterial burden.
A team of researchers from POSTECH successfully engineered a dual metalens capable of switching between different imaging modes using a single lens. This innovation enables fast mode-switching and acquisition of high-resolution images for applications such as bio-imaging and cellular reactions.
The DGIST research team developed an image translation model that can reduce biases in data despite the lack of information on underlying factors. The model achieved superior performance compared to existing methods on various biased datasets, including those with texture biases.
A new project aims to help robots assess risks and make autonomous decisions. The research focuses on quantifying ambiguity in robot perception to improve safety and efficiency.
Researchers developed an AI-powered method to measure urban decay using street view images, identifying object classes like potholes and graffiti. The model showed promise in detecting urban decline in cities like San Francisco and Mexico City, with potential applications for informing urban policy and planning.
Researchers developed a method combining sensor data with machine-learning algorithm to identify flaws in 3D-printed parts. The framework allows for statistically verified quality control, reducing the need for human involvement in manufacturing inspection.
Scientists at Nagoya University developed a new gastric acid inhibitor with a binding affinity nearly 10 times higher than existing drugs. The AI-driven approach led to the creation of compound DQ-18, which exhibits stronger binding to the gastric proton pump.
Researchers argue that AI systems can be designed to follow human law, suggesting a more integrated approach to regulation. The study proposes training AI agents in legal frameworks and using large language models to monitor and shape their behavior.
Researchers at Osaka University have developed a novel platform that combines nanopore technology with artificial intelligence to detect different coronavirus variants quickly. The platform was tested on 241 saliva samples and detected the Omicron variant 100% of the time.
A research group led by Professor Kaspar Althoefer has been awarded a €10m ERC Synergy grant to develop a revolutionary new system for screening and treating colorectal cancer. The system, which combines medical robotics, artificial intelligence, and minimally invasive surgery, aims to improve patient outcomes and quality of life.
A new study published in eClinicalMedicine suggests that ECG-AI can flag some risks years sooner than current risk calculator equations by identifying signs of coronary artery disease, such as calcification and blockages. The technology has the potential to save more lives by identifying people who do not know they have coronary disease.
A study shows pigeons tackle complex problems using associative learning and error correction, similar to AI models. Researchers used an AI model to replicate the pigeons' behavior, finding strong evidence for the similarities between pigeon and AI learning mechanisms.
A new study analyzes Twitter discussions on deepfakes related to the Russian invasion, highlighting negative reactions and positive sentiments towards deepfakes. The researchers found that some users' distrust in real videos increased after exposure to deepfakes.
A new study suggests an artificial intelligence tool can detect distress in hospital workers' conversations with therapists during the pandemic. The tool analyzed digitalized session transcripts to identify common phrases tied to mental illness using natural language processing.
A new AI-powered tool, Salmon Vision, enables real-time monitoring of salmon populations in British Columbia and beyond, addressing data-poor fisheries and climate-smart management. The technology has shown promising accuracy in identifying salmon species and yields mean average precision rates of up to 90% for key fish species.
Researchers develop integrated photonic-electronic hardware capable of processing three-dimensional (3D) data, doubling parallelism for AI tasks and significantly boosting energy efficiency. The new chip can process 100 electrocardiogram signals simultaneously with high accuracy, outperforming electronic processors.
AI medical devices can improve diagnosis and treatment, but their accuracy and limitations must be carefully considered. Developers must ensure transparency about AI's performance and limitations to avoid harming patients and exacerbating health inequities.
A global team of scientists emphasizes the need for collaboration between experts in AI, medicine, ethics, and beyond to develop fair models. They argue that focusing on equity rather than complete equality is a more reasonable approach, considering factors like race, gender, and patient preferences.
Researchers at MIT found that similarity-focused generative AI models falter when tasked with designing new products, highlighting the need to prioritize innovation in engineering tasks. By adjusting training objectives and metrics, AI can be an effective 'co-pilot' for engineers, enabling faster creation of innovative products.
A new AI algorithm developed by Cedars-Sinai can detect atrial fibrillation in people without symptoms, improving stroke prevention. The algorithm was trained on over a million electrocardiogram readings and accurately predicted cases of atrial fibrillation within 31 days.
Researchers used deep learning to identify dihydroartemisinin as a potential osteoporosis treatment that maintains mesenchymal stem cell stemness and produces more osteoblasts. The study found that administering DHA extract for six weeks significantly reduced bone loss in mice with induced osteoporosis.
Researchers from KTU and partners propose a gamified learning approach to acquire knowledge in programming. The method creates a personalised learning process using AI or tutors to monitor progress and adapt goals accordingly.
A new study by Klick Labs reveals that AI technology can screen for Type 2 diabetes using six to 10 seconds of a person's voice, with high accuracy rates. The research used acoustic features to analyze recordings from over 18,000 participants and identified significant vocal variations between individuals with and without the condition.
The American College of Surgeons (ACS) Clinical Congress 2023 offers media credentials to cover groundbreaking research, connect with surgeon experts, and learn about the latest trends in surgery. Key topics include artificial intelligence, COVID-19's impact on cancer care, and pediatric trauma.
A new AI tool provides fully automated, easy-to-use evaluation of brain tumors using amino acid PET scans. The deep learning-based segmentation algorithm assesses treatment response with quality comparable to that of an experienced physician.
The High Performance Data Facility Hub will provide researchers with unprecedented data management resources, accelerating scientific discovery through seamless access to large and complex datasets. The hub will be led by Jefferson Lab and partner with Lawrence Berkeley National Laboratory.
Researchers from Mindgard and Lancaster University exposed vulnerabilities in major Large Language Models (LLMs) that can be copied for as little as $50. This 'model leeching' attack allows attackers to gain insights into how LLMs work, enabling them to launch targeted attacks with an increased success rate.
Northwestern University engineers developed a nanoelectronic device that can perform accurate machine-learning classification tasks in real time with reduced power consumption. The device can be deployed directly in wearable electronics for real-time detection and data processing, enabling more rapid intervention for health emergencies.
A new AI software has achieved a 100% detection rate for melanoma, significantly improving skin cancer detection accuracy. The software correctly identified 99.5% of all skin cancers and 92.5% of pre-cancerous lesions, with potential to reduce face-to-face consultations and enhance dermatology triage.
The Digital Twin Brain platform combines intricate brain atlases and dynamic neural models to simulate human brain functions. This innovative approach holds promise for advancing artificial general intelligence and precision mental healthcare.
Researchers developed an AI-based method to estimate BMD from plain X-ray images using a hierarchical learning framework. The approach showed high performance and reliability in estimating BMD, with correlation coefficients of 0.88 and 0.92 compared to DXA and QCT.
The author estimates that AI-related electricity consumption could increase by 85-134 TWh annually by 2027, comparable to the annual electricity consumption of countries like the Netherlands and Sweden. The growth highlights the need for mindful AI adoption to minimize energy-intensive applications.
Researchers developed AI tools to analyze speech patterns in people with schizophrenia and found that these patterns can be distinguished from those of healthy individuals. The study uses an AI language model trained on internet text to represent the meaning of words, and it was able to predict the words generated by control participan...
The study developed a highly accurate AI model for fully automated cancer detection, including small and difficult-to-detect tumors. The model could detect visually imperceptible cancer from normal-appearing pancreases substantially early before clinical diagnosis, with a median of 438 days.
A new generative model named scPoli enables multi-scale representations of cells and samples, facilitating the integration of high-quality large-scale datasets for novel biological insights and disease understanding. This model accelerates atlas building and usage, ultimately accelerating disease understanding and therapy development.
A new AI tool developed by Brazilian researchers can detect potentially cancerous lung nodules in CT reports, missing a crucial early diagnosis. The NLP tool achieved an accuracy rate of 97% in identifying suspicious nodules.
Post-Acute Sequelae of COVID-19 research aims to track long-term health symptoms in survivors. A $3.7 million grant will support the development of self-supervised deep learning technologies to recognize post-COVID lung progression phenotypes.
Researchers at the University of Texas at Austin developed an AI algorithm that accurately predicted 14 earthquakes within about 200 miles of their location and strength, with only one false warning. The system detected statistical bumps in real-time seismic data and paired them with previous earthquakes to make predictions.
A new generative AI model enhances clinical accuracy and textual quality of chest radiograph reports, surpassing traditional methods like teleradiology. Its implementation could enable timely alerts for life-threatening conditions, aiding imaging interpretation and documentation.
Researchers at BYU and Duke University found that AI can improve conversation quality and promote civil dialogue in online interactions. By using AI-generated rephrasings of users' messages, participants exhibited greater willingness to listen to opposing viewpoints and reported higher conversation quality.
Researchers developed a novel approach to predict therapeutic targets for aging and age-related diseases. They trained a domain-specific BioGPT model on biomedical literature, which improved its performance in identifying prospective targets.
Researchers at Argonne National Laboratory have developed an autonomous microscopy technique that uses AI to selectively target points of interest for scanning, speeding up the experimental process and allowing for greater efficiency in facilities with limited beam time. This innovative approach has the potential to accelerate scientif...
A coordinated network of space lasers could prevent collisions with manned and unmanned space assets by nudging debris off potential collision courses. The artificial intelligence-powered lasers can maneuver and work together to respond rapidly to debris of any size.
Researchers discovered that monk parakeets possess a unique tone of voice, known as a voice print, similar to humans. This finding raises the possibility that other vocally flexible species may also have a voice print.
Researchers found that humans can inherit AI biases after interacting with a biased system, leading to a permanent negative impact on human decisions. This effect was observed in three experiments, where participants who were aided by a biased AI system continued to replicate its bias even when unaided.
Researchers from the University of Tokyo have developed an AI-powered drone system that analyzes young plants to predict their expected growth characteristics. By identifying optimal harvest times, farmers can reduce waste and improve their income by up to 20.4%, while also benefiting consumers and the environment.
Researchers from SUTD successfully applied reinforcement learning to a video game problem, creating complex movement designs that outperformed top human players. The study's findings have the potential to impact robotics and automation, ushering in a new era of movement design.
Researchers discovered that users' prior beliefs about an AI chatbot's motives significantly impact their interactions with the agent. Priming users to believe certain things about the AI's empathy, neutrality, or manipulation influences their perception of its trustworthiness and effectiveness.
A study of 33 physicians across 17 specialties found that chatbots provided largely accurate information to diverse medical queries. However, the chatbots had important limitations that require further research and model development.
A new AI method leverages causal relationships in genome regulation to efficiently identify optimal genetic perturbations for cellular reprogramming. The technique reduces experimental costs by prioritizing the most informative interventions, leading to faster convergence and more effective results.
Researchers found that participants preferred 60-70 options from ChatGPT, citing high perceived accuracy and increased intent to purchase. This contradicts traditional choice overload theories, highlighting the impact of personalized recommendations on consumer decision-making.
GlowTrack, a non-invasive movement tracking method using fluorescent dye markers, improves the capture of diverse movements in laboratories. This technique enables easier comparison of movement data between studies, increasing scientific discovery and advancing fields like biology, robotics, and medicine.
The University of Trento coordinates a European research network, Elias, aiming to establish Europe as a leader in AI research. The project focuses on developing new computational systems and models for sustainable innovation, social cohesion, and reliable AI.
Researchers developed MonoXiver, a new method to help AI extract 3D information from 2D images, making cameras more useful tools for emerging technologies. The method significantly improves accuracy when used in conjunction with existing techniques, such as MonoCon.
Researchers identified potential therapeutic targets for Alzheimer's disease and other conditions using a new approach combining AI-driven target identification with protein phase separation analysis. The study provides insights into the role of protein phase separation in human disease and its potential as a therapeutic target.
Researchers at the University of Zurich developed PlantServation, a method that enables scientists to observe plants with great precision using AI and machine learning. The technique allows for the analysis of millions of images taken from various weather conditions, providing insights into how plants respond to environmental factors.
The UW team's system uses self-deploying microphones to divide rooms into speech zones and track the positions of individual speakers. The robots disperse as far from each other as possible, allowing for greater sound control and isolating specific areas or separating simultaneous conversations.