Articles tagged with Algorithms
The SDC-DeepLabv3+ algorithm achieved a mean pixel accuracy of 95.84% and mean intersection over union of 96.87%, reducing background interference and enhancing filament visibility. The method shows potential for improved harvesting robot performance and precise filament harvesting.
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.
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 NTNU have developed a way to reconstruct 3D models of the colon using single images taken by capsule endoscopy cameras. These models can aid in detecting abnormalities and signs of disease, enabling specialists to make diagnoses faster.
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.
Researchers at Bar-Ilan University have discovered a new scaling law that governs how artificial neural networks handle an increasing number of categories for identification. This law reveals how the identification error rate increases with the number of required recognizable objects, impacting AI latency and efficiency.
Researchers developed two clinical ageing clocks, PCAge and LinAge, that use blood tests, a urine test, and a health questionnaire to estimate future mortality risk. These clocks show significant predictive efficacy in characterising individual future ageing trajectories.
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.
The University of Texas at Arlington has awarded over $130,000 to support new research projects through its Research Enhancement Program grants. The funding is intended to provide seed money for researchers to initiate creative endeavors and make a positive impact on society.
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.
Researchers developed a reliable iris recognition method by applying statistical limits to the spatial domain zero crossing technique, reducing errors to 0.022%. The algorithm uses a neural network to recognize unique features of each person's iris, achieving over 99.78% accuracy.
Researchers from Mass General Brigham created an algorithm to generate personalized DBS treatment plans based on four major PD symptoms. The algorithm improved patients' symptoms in four of five cases, demonstrating its potential to improve treatment beyond standard-of-care approaches.
A new study from Chalmers University of Technology shows that AI-controlled charging stations can offer personalized prices to electric vehicle users, minimizing both price and waiting time. However, the researchers highlight the importance of addressing ethical issues related to data exploitation by motorists.
Researchers at Texas A&M University have developed a more accurate method for tracking reservoir evaporation rates, accounting for factors not considered by current methods. The new algorithm reveals a clear geographic distribution and strong seasonality of evaporation throughout Texas.
Researchers Dr. Samson Zhou and Dr. David P. Woodruff aim to create secure algorithms for big data models using mathematical connections and cryptography ideas. They focus on streaming models, which process data in real-time, and address challenges such as randomness and different types of attacks.
Researchers have developed a system combining bio-inspired cameras with AI to quickly detect obstacles around cars, using less computational power. The hybrid system detects objects up to one hundred times faster than current systems while reducing data transmission and processing needs.
A study found that thumbnails on a popular video-sharing platform used by children contained attention-capturing designs with violent and stereotyped themes. The researchers aim to understand how children respond to such thumbnail designs and their impact on the quality of consumed content.
A new algorithm called adaptive intersection maximization (AIM) removes high-frequency noise from super-resolution optical microscope data in real time, achieving sub-nanometer precision. This allows scientists to study chemical and biological systems far more easily and precisely than before.
A breakthrough in trauma care has nearly quadrupled the 'golden hour' for treating large animals with internal bleeding during emergency ground and air transport. Researchers used a closed-loop, autonomous intervention system to resuscitate pigs with traumatic injuries, extending their survival time by several hours.
The team aims to create a system that can deliver items without human contact, using cables, knots, and multiple robots. They will focus on scaling up the transport of small objects like a basketball and solar panel.
A new computer algorithm has been developed to enhance the management of invasive species globally, optimizing resource allocation and reducing costs. The innovative tool is adaptable to various population dynamical models and treatment methods, improving the effectiveness of environmental conservation efforts.
Researchers have developed an AI algorithm that can track protein clumping under the microscope in real-time, revolutionizing the study of neurodegenerative disorders. The tool helps identify key characteristics of clumped proteins, which can lead to new therapies.
Engineers developed a material that mimics human bone for orthopedic femur restoration, providing optimized support and protection from external forces. This innovative approach uses machine learning, optimization, and 3D printing to create a fully controllable computational framework.
A UCF researcher is developing algorithms to track space objects and predict their orbits, which will also aid in maritime domain awareness. The computational framework will enable spacecraft to operate autonomously without intervention from Earth.
Researchers developed a multimodal algorithm for improved sarcasm detection, examining multiple aspects of audio recordings for increased accuracy. The approach combines sentiment analysis using text and emotion recognition using audio for a comprehensive analysis.
Researchers used AI to detect localized versus advanced cancer stages in oropharyngeal squamous cell carcinoma patients. The study suggests improved patient care and clinical decision-making through AI-assisted health record extraction.
A new approach uses neural networks to automatically determine polynomial coefficients for digital pre-distortion (DPD) in RF-PAs, reducing hardware complexity and power efficiency. This method can correct non-linearities and support emerging standards without extensive real-time processing.
Researchers created a digital twin model that predicts and controls complex systems, achieving higher accuracy than traditional methods. The algorithm is compact, energy-efficient, and easy to implement, making it suitable for self-driving vehicles and other dynamic systems.
Researchers developed a new AI algorithm called Maximum Diffusion Reinforcement Learning (MaxDiff RL) to improve robot reliability. The algorithm enables robots to learn complex skills more efficiently by encouraging exploration of their environments.
Researchers designed a new AI model that accurately predicts treatment outcomes for stroke prevention in people with heart disease. The model, called CURE, was trained on a massive dataset of de-identified patient information and fine-tuned to focus on specific health conditions and treatments.
Researchers at Aalto University have created a method to manipulate objects with wind, allowing for controlled movement in different directions. The technique uses an airflow field to move objects along desired trajectories, with potential applications in robotics and complex processing tasks.
The American Heart Association has funded four new grants to evaluate the use of race in predicting heart disease risk and develop unbiased clinical algorithms. The research projects will test various risk models to remove racial bias from care decisions, improving patient outcomes.
Researchers developed an algorithm that uses stochastic differential equations to identify key data points in noisy data, improving early warning signal accuracy. The approach can be applied to various domains, including ecology and mental health, and has been validated through simulations.
Researchers from Drexel University have developed a machine-learning algorithm that can extract and recognize digital fingerprints of AI-generated video, including Stable Video Diffusion, Video-Crafter, and Cog-Video. The algorithm can be trained on just a few examples of new AI generators to detect them.
A Concordia PhD candidate argues that tech companies' opaque algorithms for storing and sharing personal content raise questions about selection and representation. An Apple update blocking Holocaust-themed photos in the iPhone Photos app's Memories sparked a debate among users, with some expressing annoyance at being told what to see.
A new framework mitigates bias in machine classification by evaluating under different fairness metrics and inferring specific bias terms from data. The framework substantially reduces bias in classification outcomes while preserving accuracy across seven datasets and 21 classifiers.
A team of researchers at MIT has developed a new method to model the irrational behavior of humans, which can be used to predict their future actions. By analyzing an agent's previous decisions, the technique infers its computational constraints and adapts to human collaborators' weaknesses.
Researchers at Bar-Ilan University developed a new AI confidence measure that distinguishes between high- and low-confidence decision making in deep learning architectures. This breakthrough enables the creation of safer and more reliable autonomous vehicles by prioritizing human intervention when confidence levels are lower.
The project, AI STORIES, aims to understand how artificial intelligence creates new narratives and challenges dominant American narratives. The research will test the hypothesis that AI-generated responses mimic sci-fi stories where AI gains human emotions.
A new machine-learning approach outperforms human testers in generating diverse prompts that trigger a wider range of undesirable responses from chatbots. The technique provides a faster and more effective way to ensure the safety of large language models.
A new study by Carey Morewedge and colleagues found that people are more likely to recognize bias in algorithmic decisions than their own. This is because algorithms can codify and amplify human bias, but also reveal structural biases in society. The research suggests ways to increase awareness of biases and correct them.
Recent advancements in AI and IoT have improved earthquake prediction by identifying patterns in historical seismic data. However, limitations such as computational complexity, data quality, and interpretability remain, requiring a comprehensive approach to integrate diverse datasets.
Researchers propose a hybrid data driven framework combining VMD, ISSA, and MKSVR to enhance battery SOH estimation and RUL prediction. The approach achieves accurate predictions with high stability.
Researchers from the University of Washington created an AI algorithm to analyze infant poses using limited training data. By leveraging generative AI, they were able to produce high-quality results, enabling parents to monitor their babies' daily activities and detect potential health issues early.
Researchers have developed a new open-source algorithm called Conditional Variational Diffusion Model (CVDM) that improves the quality of images by reconstructing them from randomness. The CVDM is computationally less expensive than established diffusion models and can be easily adapted for various applications.
A new MIT-derived algorithm corrects coarse climate model predictions by 'nudging' them toward more realistic patterns, leading to more accurate forecasts of extreme weather events. The approach uses machine learning and dynamical systems theory to improve the resolution of large-scale climate models.
A recent study published in JAMA found that Black patients are less likely to receive a heart transplant than white patients, with odds of acceptance being higher for white candidates. The study also revealed that the intersection of race and gender often worsens access for Black women.
Researchers have proposed an innovative quantum algorithm that effectively solves combinatorial optimization problems with constraints in a short time. The pVSQA algorithm uses a quantum device to generate a variational quantum state and transform infeasible solutions into feasible ones, achieving near-optimal performance.
A new algorithm combines deep learning and transfer learning to retrieve advanced geosynchronous radiation imager (AGRI) aerosol optical depth with high accuracy. The approach facilitates feature selection and offers applicability to other multispectral sensors.
Researchers at Klick Labs developed an algorithm to detect deepfakes with 80% accuracy by analyzing speech pause patterns, offering a solution to the growing problem of AI-generated content. The study's findings suggest that vocal biomarkers can distinguish between real and fake voices, providing a novel approach to flagging deepfakes.
A recent study analyzed data from multiple social media platforms over three decades, finding that toxic interactions are a persistent aspect of online discussions. The study suggests user resilience to negativity and highlights the importance of understanding human behavior in digital environments.
A recent study integrates domain knowledge into data-driven machine learning models for well logging reservoir parameter prediction. The model, PINN, uses petrophysics constraints to guide training and improve accuracy, especially in cases with small sample sizes.
Researchers developed a new training tool to help AI programs account for human dishonesty, especially in mortgage and insurance applications. The modified AI was better able to detect inaccurate information from users.
A review published in Intelligent Computing outlines the strengths of automatic approaches to designing metaheuristics, which can lead to more successful outcomes and reduce redundant, metaphor-based algorithms. The authors encourage research that relies on automatic design, utilizing modular software frameworks and configuration tools.
Researchers at Bar-Ilan University discovered that each filter recognizes small clusters of images, with sharpened recognition as layers progress. This breakthrough can improve AI performance by reducing latency and memory usage while maintaining accuracy.
A 20-year analysis found that calcium and vitamin D supplements reduced cancer mortality by 7%, but increased cardiovascular disease mortality by 6% in postmenopausal women. The study suggested that cancer incidence depends on pre-supplementation status, while CVD mortality is higher among supplement users.
Researchers aim to address LVAD shortcomings, reducing blood damage and clotting risk through innovative designs and coatings. A novel flexible stented blood inlet and slippery hydrophilic coatings will be used to prevent flow stasis and clot formation.
Researchers found counterexamples to ADOPT's termination and optimality properties, potentially leading to suboptimal solutions or failure to terminate. They proposed a modified version that corrects these issues, ensuring the algorithm's termination and optimality.
Researchers developed a deep learning algorithm to remove probe effects from AFM images, enabling the resolution of material features smaller than the probe's tip. This breakthrough allows for accurate three-dimensional surface profiles, crucial for nanoelectronics development and scientific studies.
A study compared traditional logistic regression models and machine learning algorithms to predict the best surgical technique for patients with submucosal tumors. The traditional regression approach was found to outperform ML algorithms, with morphology ranking as the highest contributor to prediction accuracy.