Articles tagged with Artificial Intelligence
Researchers from Tokyo University of Science have designed a tunable physical reservoir device based on dielectric relaxation at an electrode-ionic liquid interface. The system can store and process analog signals, enabling real-time processing of signals in living environments.
A new case study reveals significant differences between human and AI perception in breast-cancer screenings. Researchers found that AI systems consider tiny details in mammograms that are irrelevant to radiologists, highlighting the need for understanding and correcting AI decision-making before trusting it for life-critical medical d...
Researchers at Johns Hopkins Medicine developed an AI training strategy to capture images of mouse brain cells in action, allowing scientists to understand how the brain functions and is affected by disease. The technology combines ultra-small microscopes with AI to enhance image resolution up to 52 frames per second.
A new AI-based method distinguishes between stable and progressive cognitive impairment, enabling accurate diagnosis with an accuracy rate of 85%. This technique overcomes the complexity of subtle structural changes in mild cognitive impairment, contributing to achieving Sustainable Development Goal 3.
Researchers from the University of Cambridge have developed a hybrid, data-driven approach to the Travelling Salesperson Problem that significantly outperforms current methods. The new approach converges to optimal solutions at a faster rate and produces high-quality solutions under restricted computation time.
A new study indicates that artificial intelligence can accurately predict who will develop pancreatic cancer based on pre-diagnostic CT scan images. The AI tool was trained to analyze textural differences in the pancreas and achieved an accuracy rate of 86% in identifying those who would eventually develop the disease.
Researchers at MIT developed an AI method that constrains machine-learning models to suggest molecules with producible chemical structures. The approach guarantees quality and speed, outperforming existing methods in proposing high-quality molecular structures.
Researchers used AI technologies to conclude that male characters are four times more prevalent in literature than female characters. The study's findings also showed that the discrepancy between male and female characters decreases under female authorship.
Researchers developed an AI system using swarm learning to predict cancer from medical images of tissue samples without accessing patient data. The technique improved the detection of genetic changes in colon tumors with high accuracy.
Researchers developed a machine-learning method that allows robots to pick up and place never-before-seen objects in random poses, requiring only 10 human demonstrations. The system uses a neural network specifically designed to reconstruct 3D shapes, enabling the robot to generalize to new object orientations.
A recent study found that an artificial intelligence-based system improved providers' assessments of bladder cancer patients' response to chemotherapy. The AI tool helped doctors from different specialties and experience levels make more accurate diagnoses, with those in academia showing the greatest gains.
Researchers at Michigan State University have designed a learning-enabled safe controller for systems operating in uncertain environments. The new method, which combines control barrier functions and Lyapunov functions, allows the system to quickly learn uncertainties while achieving maximum safe performance.
Researchers developed a new decision-support tool to optimize ship channel dredging and disposal activities, considering factors like navigability condition deterioration and economic values. The algorithm weighs input from local professionals and projects costs with interest and inflation included.
A new deep learning method, PDD-Net, uses 3D deep convolutional neural networks to extract deep metabolic imaging indices from PET scans for differential diagnosis of parkinsonian diseases. The method achieved high sensitivity and specificity rates for Parkinson's disease and other parkinsonian syndromes.
Researchers developed an AI algorithm to model first impressions and accurately predict how people will be perceived based on a photograph of their face. The algorithm's findings align with common intuitions or cultural assumptions, such as people who smile being seen as more trustworthy.
A study published in Gastroenterology found that artificial intelligence reduced the rate of missed precancerous polyps in colorectal cancer screening by twofold compared to standard colonoscopy. The AI detection method identified smaller, flatter polyps and improved false negative rates.
Researchers at Columbia University have developed an algorithm that generates whisper-quiet sounds to block smart devices from spying on users. The system works by predicting the characteristics of spoken language and generating a signal that can disrupt automatic speech recognition models.
A new study by Hiroshima University introduces a novel AI-based technique for estimating site amplification factors from microtremor data. The model demonstrated potential as a predictive tool for characterizing site amplification factors, but notes are needed for further optimization with a larger dataset.
Researchers develop a new AI agent that uses four strategies to solve single-agent stochastic puzzles like Minesweeper, achieving comparable performance to state-of-the-art studies. The approach defines solvability in this context and establishes the boundary between puzzle-solving and game-playing paradigms.
Researchers at UCF create brain-like devices that enable AI to function independently, allowing technology like robots and voice assistants to operate in remote areas or space. The devices use parallelism and in-memory computing, similar to the brain, for AI and unsupervised learning.
A study found that trainee teachers who received AI-generated feedback improved their diagnostic reasoning, identifying potential learning difficulties in pupils more accurately. The AI system analyzed the trainees' work and provided clear, adaptive feedback.
Scientists develop models that complement simulations using reinforcement learning and numerical methods to predict climate change, turbulent flows, and morphogenesis. This approach enables faster and more energy-efficient predictions, solving complex problems in engineering and climate applications.
An AI model developed by researchers identified a subset of individuals with a 25-fold risk of developing pancreatic cancer within three to 36 months. The model used sequence of medical diagnoses from patient records to predict risk, which was validated in two independent datasets.
Researchers have gained unprecedented insights into the heart's dynamic ultrastructure using high-resolution electron microscopy. This knowledge is crucial for developing new therapeutic concepts for heart attacks and cardiac arrhythmias.
Researchers used AI to analyze videos of over 2,500 ASL signs and found that challenging signs are made closer to the signer's face, making them easier for perceivers to recognize. This suggests that ASL has evolved to be more recognizable, improving communication.
The UPV study uses AI to investigate subphenotypes in line with clinical characteristics, helping clinicians assess patients and plan resource allocation. The team develops predictive models for early mortality prediction and severity assessment, offering robust and reliable AI in data quality issues.
The UNC Charlotte team developed a universal AI algorithm called AutoClass to clean noisy single-cell RNA sequencing (scRNA-Seq) data. The algorithm effectively removes noise and enhances downstream analysis in multiple aspects, demonstrating its robustness and scalability.
Researchers have developed a new method called Shared Interest that enables users to aggregate, sort, and rank individual explanations of a machine-learning model's reasoning. This technique uses quantifiable metrics to compare how well the model's reasoning matches human thinking, helping to uncover concerning trends in decision-making.
A new e-nose prototype, NOS.E, can distinguish between six whiskies by brand names, regions, and styles in under four minutes, with 100% accuracy for region detection and 96.15% for brand name identification. The technology has applications beyond whisky, including counterfeiting detection in perfume and wine.
Researchers at the University of Bristol created a 3D-printed artificial fingertip that produces nerve signals similar to those from human tactile nerves. The innovation could improve robot dexterity and prosthetic hand performance by giving them an in-built sense of touch.
A study using AI-powered robot scientist Eve analyzed over 12,000 research papers on breast cancer cell biology and found that less than one third of the results were reproducible. The researchers found that significant evidence for repeatability was found in 43 papers, while 22 papers showed replicable results under different conditions.
Researchers at Carnegie Mellon University developed AI-enhanced museum exhibits that increased learning and engagement for elementary school-aged children. The intelligent exhibits featured a virtual assistant, NoRilla, which interacted with visitors, asking questions and guiding them through scientific challenges.
Researchers at MIT developed a framework for robotic manipulation systems that can perform complex tasks using a two-stage learning process. This allows robots to learn abstract ideas about manipulating deformable objects, such as pizza dough, and execute skills to complete tasks.
Researchers integrated biological signals with gold-standard machine learning methods to create emotionally intelligent speech dialog systems. The study found that combining language information with biological signal information improved the AI's performance, making it comparable to human-like emotional recognition.
Researchers at Yale University developed an AI-based model that can diagnose multiple heart rhythm and conduction disorders using electrocardiogram images, regardless of format or layout. The tool has been validated through multiple international data sources with high accuracy for clinical diagnosis from ECGs.
A machine-learning algorithm detected potential signs of colorectal cancer in high-risk patients who missed routine screenings. The algorithm identified patients as high-risk by analyzing age, gender, and recent CBC results, and subsequent screenings showed significant findings in 70% of the flagged group.
A research team from Universidad Complutense de Madrid developed a machine learning-based tool to predict areas with best access to potable groundwater in Africa. The tool achieved a success rate of close to 90% in initial trials, particularly in Mali and Chad.
Researchers at MIT created a process called DualFair that can remove bias from data used to train machine-learning models. The method tackles both label bias and selection bias, significantly reducing discrimination in loan predictions while maintaining high accuracy.
Researchers used AI to detect dialects in zebra finch songs, showing they play a key role in mate choice. Females prefer males who sing the same dialect as their parents, indicating cultural trait importance over physical appearance.
A study by RIFS researcher Silke Niehoff analyzed DAX company sustainability reports and found that most prioritize customer demands and efficiency over environmental concerns. However, a few companies are using digitalization to promote sustainable development and serve as role models.
A Bayes Business School study found that supply chain professionals overestimate technology benefits and underestimate needs, leading to disappointment. The study offers a list of goals, constraints, and benefits to help managers better calibrate expectations.
Researchers developed an AI-driven image analysis pipeline that identified novel cellular hallmarks of Parkinson's disease from images of over a million skin cells. The platform can distinguish between patient cells and healthy controls, revealing new signatures for potential therapeutic targets.
Researchers developed a novel approach to diagnose, monitor, and predict the course of myocarditis using CMR parameters and AI. The goal is to provide personalized counseling for athletes and optimize treatment options.
Scientists from Cardiff University have developed a new artificial intelligence method to automate the extraction of information from large collections of museum specimens. The 'image segmentation' method can accurately locate and bound different visual regions on images, allowing for faster and more efficient digitization processes.
Researchers developed an AI-based computer algorithm that accurately predicted heart health risks based on voice recordings alone, identifying a high biomarker score associated with increased CAD-related events. The study suggests voice technology could be a powerful screening tool in remote healthcare delivery and telehealth.
The Human Brain Project (HBP) has brought together neuroscientists from different disciplines to work collaboratively on common goals. The HBP researchers outline their scientific approach and illustrate the potential of EBRAINS infrastructure for neuroscience research.
Researchers developed an AI algorithm that can measure coronary plaque buildup in five seconds, predicting heart attack risk within five years. The tool was trained on images from 921 people and matched results with invasive tests considered highly accurate.
Researchers have developed a new forecasting approach using machine learning and anonymized datasets from Facebook that significantly outperforms conventional models for projecting COVID trends at the county level. The model captures shifting trends in numbers reflecting lockdowns, waning immunity, or masking policies.
A study found that telemedicine and community screening for diabetic retinopathy are highly cost-effective in rural and urban China. The results suggest that adopting telemedicine screening programs at the national primary care level is economically reasonable.
A pilot study suggests that an artificial intelligence system called CRANE can help cardiac experts diagnose rejection and estimate its severity more accurately. This could lead to faster diagnosis and treatment, as well as reduced variability in expert agreement, ultimately improving heart transplant outcomes.
Researchers used a contrast pattern mining algorithm on publicly available data from 16,000 participants in the T1D Exchange Clinic Registry. The study found individuals with an immediate family history of Type 1 diabetes were more frequently diagnosed with hypertension and other co-occurring conditions.
A new machine learning study analyzed 10 years of weather data to identify three major categories of weather patterns and their effects on thunderstorms. The study aims to isolate the impact of aerosols, tiny particles suspended in the atmosphere, on storm severity.
A new AI method accurately estimates timetable robustness within milliseconds, enabling efficient optimization. This improves balance between passenger needs and economic conditions.
Researchers from the University of Cambridge and Oslo identify a century-old mathematical paradox as the Achilles' heel of modern AI. The paradox limits the existence of stable and accurate neural networks, making many AI systems untrustworthy in high-risk areas.
Researchers created BirdBot, a robotic leg inspired by the ostrich's anatomy, which achieves energy efficiency through a mechanical coupling of muscles and tendons. The robot leg requires fewer motors than other machines, making it suitable for large size applications.
Mayo Clinic researchers used AI to predict antidepressant outcomes in children and adolescents with major depressive disorder. They identified six depressive symptoms and assessed them using the Children's Depression Rating Scale-Revised to predict treatment outcomes.
Scientists developed an AI approach to model and map the Earth's natural features in greater detail and accuracy. The new system can recognise intricate features and aspects of the terrain far beyond traditional methods, generating enhanced-quality environmental maps.
The European Lung Cancer Congress 2022 focused on the latest advancements in lung cancer treatment, including personalized strategies for better patient care. The congress also explored emerging therapies and molecular sub-types to enhance precision medicine.
Researchers at NC State University have developed a 'self-driving lab' that uses artificial intelligence and fluidic systems to advance our understanding of metal halide perovskite nanocrystals. The technology can autonomously dope MHP nanocrystals, adding manganese atoms on demand, allowing for faster control over properties.
Researchers reexamined hundreds of experiments on neural activity and consciousness, finding that experiment parameters determine results. The study used artificial intelligence to predict which theory would be supported by each experiment with 80% success.