Articles tagged with Algorithms
A new algorithm proposes measuring quadriceps muscle mass for more accurate sarcopenia diagnosis, potentially leading to earlier detection and better treatment options. Ultrasound imaging is recommended as a cost-effective and practical solution for diagnosing sarcopenia in clinical settings.
A new large language model, 'llm-jp-3-172b-instruct3', has been released with approximately 172 billion parameters, trained from scratch using 2.1 trillion tokens of data. This model surpasses GPT-3.5 performance on benchmarks such as 'llm-jp-eval' and 'llm-leaderboard'.
The Association for Computing Machinery (ACM) has named 55 Fellows for their transformative contributions to computing science and technology. The inductees represent a diverse range of fields, including cybersecurity, artificial intelligence, human-computer interaction, machine learning, and programming languages.
Anil Jain and Michael I. Jordan received the BBVA Foundation Award in Information and Communication Technologies for their pioneering work on machine learning, enabling transformative technologies like biometrics and artificial intelligence. Their research has unlocked applications of far-reaching impact on society.
A new 6D pose dataset has been introduced, providing high-quality RGB and depth images with annotated 6D pose data. This dataset achieves state-of-the-art accuracy rates of 97.05% and 98.09% for robotic grasping and automation applications.
Researchers from Southern Methodist University and University of Michigan found A-B testing limitations that affect user response to ads, leading to misinterpreted data. The study highlights the importance of recognizing these limitations to make informed marketing decisions.
Researchers from Singapore, Japan and US developed an advanced swarm navigation algorithm for cyborg insects that prevents them from getting stuck in challenging terrain. The new algorithm represents a significant advance in swarm robotics and could pave the way for applications in disaster relief and search-and-rescue missions.
Researchers at MIT have developed Boltz-1, an open-source AI model that achieves state-of-the-art performance in predicting biomolecular structures. The model surpasses AlphaFold3, which is limited to academic research and commercial use, by incorporating new algorithms and improving prediction efficiency.
The authors introduce advanced methodologies for integrating maintenance strategies and structural health monitoring to extend infrastructure service life. Topics include data-driven decision-making, multi-objective optimization, cost-benefit analysis, and the role of data analytics in managing uncertainties.
A study of 9,000 US-based participants reveals that they prioritize efficiency over fairness when choosing between human and algorithmic decision-makers. Notably, Republicans prefer humans more than Democrats, yet most claim fairness is a top priority.
Physicists at the University of Michigan have developed an algorithm that enables materials to learn and adapt, mimicking brain-like behaviors. This breakthrough has implications for the development of advanced materials with self-tuning properties.
A new monitoring system uses 'virtual sensing' to accurately estimate CO₂ and NOx emissions based on driving behavior. The system provides personalized environmental impact assessments, empowering drivers to manage their emissions.
A team of Caltech researchers has developed an algorithm called Spectral Expansion Tree Search (SETS) that enables autonomous robots to determine the best movements to make as they navigate the real world. SETS uses control theory and linear algebra to find natural motions that use a robotic platform's capabilities to its fullest extent.
Researchers develop a simple fix to an existing technique, enabling the generation of sharp, high-quality 3D shapes that rival top model-generated 2D images. The new approach improves upon previous methods by avoiding costly retraining and complex postprocessing.
Researchers from the University of South Australia have developed a celestial navigation system that uses visual data from stars to provide an alternative means of nighttime navigation in environments where GPS is unavailable or unreliable. The system has been tested on a fixed-wing drone and demonstrated accurate positioning within fo...
Dr. Sebastian Stich aims to create more efficient and adaptable machine learning models using collaborative learning approaches. The goal is to reduce computational power demands and costs, making it accessible to smaller players in fields like medicine.
This editorial introduces persistence landscapes as a mathematical method to identify and correct biases in medical imaging. Persistence landscapes offer a way to reduce random noise while preserving important details, making it easier for clinicians to focus on meaningful image parts.
A new meteorology estimation method developed at Osaka Metropolitan University improves the accuracy of building energy simulations by considering interdependent factors such as temperature, solar radiation, and humidity. The generated data was found to be almost identical to the original dataset, proving its accuracy.
Researchers at MIT have introduced a new algorithm that strategically selects the best tasks for training an AI agent, resulting in improved performance and reduced training costs. The technique outperforms existing methods by five to 50 times, making it more efficient and effective.
A team of researchers developed a new technique combining methods to simulate molecules, achieving accuracy and efficiency on the Frontier exascale supercomputer. They broke records with simulations of over one million electrons and scaled their algorithm to an EFlop/s processing quintillion calculations per second.
Researchers developed a machine-learning tool that provides accurate predictions for flood-prone areas, using historical data and weather-based predictors. The model can predict short-term river discharge with high accuracy, giving real-time data on water movement through the river.
A new approach using topological data analysis (TDA) enhances the reliability and reduces bias in AI systems used for medical diagnosis in radiology. TDA captures intricate features and provides a holistic view of medical images, leading to more accurate diagnoses and equitable patient care.
A new study reveals that an AI algorithm can accurately detect early-stage metabolic-associated steatotic liver disease (MASLD) in patients who meet the criteria, leaving 83% undiagnosed. This highlights the need for improved screening and diagnosis methods to prevent progression to advanced liver disease.
A WVU research partnership with the DEA aims to improve fast and accurate identification of psychoactive substances like fentanyl. The Expert Algorithm for Substance Identification (EASI) will enable labs using different instruments to share data on chemical profiles, helping to identify drugs like fentanyl.
Researchers at Graz University of Technology have developed a digital monitoring system to prevent costly mistakes in concreting processes. The system uses sensors and algorithms to measure and analyze various parameters, providing real-time warnings for potential issues, and eliminating the need for rework.
HemaChrome's machine learning-based technology enables instant and noninvasive measurement of blood hemoglobin levels from digital photos, facilitating point-of-care diagnostic tests. The collaboration with Global Health Labs aims to address anemia diagnosis gaps in low- and middle-income countries.
The study emphasizes the need for a coherent approach to understanding A.I. threats, recognizing the intricate interplay between technology and society. Experts propose involving laypeople and experts in risk assessment processes, as well as promoting social resilience to ensure better decision-making.
Researchers at Lehigh University are using advanced algorithms and cross-domain data to help cities predict human movement patterns, enabling better planning and preparedness for events and emergencies. The model will account for variations in data streams from different sources, such as cell towers, GPS, and financial transactions.
Researchers found that X/Twitter's algorithm presents users with milder and less polarizing information than chronological timeline news. However, this has implications for the use of these platforms to find trustworthy news, as users question its credibility even when coming from legitimate sources.
Professor Ruth Britto and her international team will develop new algorithmic methods with applications in mathematics, particle physics, and gravity. They aim to tackle longstanding computational bottlenecks and push the boundaries of numerous areas of theoretical physics.
Researchers have summarized advanced field weakening (FW) control strategies for permanent magnet synchronous motors (PMSMs), including offline calculation methods, online computational methods, and model predictive control (MPC)-related methods. The studies highlight the importance of balancing computational difficulty with control ro...
A team of MIT engineers developed an algorithm to identify causal links in complex systems, taking data from various sources and analyzing interactions between variables. The method generates a causality map linking variables with likely cause-and-effect relationships, including synergistic and redundant links.
The team developed an exascale climate emulator with enhanced resolution without increasing data storage needs. The emulator offers a remarkable resolution of 3.5 kilometers, replicating local conditions on a timescale from days to hours.
A Cornell University research team found that strategically placing a mix of medium-speed and fast-charging stations in urban areas increases driver usage and improves investor profitability by 50-100%. The team used Bayesian optimization to analyze data from Atlanta, taking into account factors like traffic and road characteristics.
A new training algorithm called ternarized gradient BNN (TGBNN) enables learning capabilities for binarized neural networks (BNNs) on IoT edge devices. The proposed MRAM-based CiM architecture achieves faster convergence and matching accuracy with regular BNNs.
Researchers developed a machine learning model to predict dielectric function of materials, facilitating novel dielectric material development. The model speeds up calculations by using chemical bonds between atoms and achieving accuracy close to first-principle calculations.
The GALAD algorithm combines AFP, AFP-L3, and PIVKA-II for HCC detection. Combining GAAD, GALAD, or PIVKA-II with ultrasound improves diagnostic efficiency compared to recommended strategies.
Researchers have developed Rastermap, a visualization tool that enables scientists to uncover activity patterns in thousands of neurons. The tool sorts neuronal activity into clusters based on similarity and maps them onto a graphical representation, allowing for the identification of patterns that can be further tested in the lab.
A UVA professor has developed a new computational algorithm to find tightly connected clusters, or triangle-dense subgraphs, within large networks. This breakthrough can help uncover suspicious activity in fraud detection and identify community dynamics on social media with greater precision.
Researchers at the University of Copenhagen's Quantum for Life Centre have developed a new mathematical recipe to make quantum simulators more scalable and efficient. This breakthrough could speed up the development of new medicines from years to months by predicting how molecules behave in the human body before laboratory trials.
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.
A new vehicle allocation strategy for dockless bike-sharing systems at night can improve the balance of urban transportation and reduce traffic congestion. The approach uses a three-way classification method and behavioral decision theory to forecast demand and optimize resource allocation, reducing waste and enhancing system efficiency.
A team of researchers from UMass Amherst debunks the idea that Facebook's algorithms successfully filtered out untrustworthy news during the 2020 election. The study found that temporary changes to the algorithm were not accounted for, leading to misperceptions about the platform's reliability.
Researchers found that large language models used in home surveillance can make inconsistent decisions about calling the police, even when videos show no crime. Models often disagreed with each other and exhibited inherent biases influenced by neighborhood demographics.
Researchers at Klick Labs developed an AI technique using vocal biomarkers to predict chronic high blood pressure with up to 84% accuracy. The study used machine learning to analyze hundreds of indiscernible vocal biomarkers, including pitch variability and speech energy distribution patterns.
A breakthrough technology allows for touchless infrared imaging to monitor changes in pupil size and gaze direction behind closed eyes. This innovation can help identify wakefulness, awareness, and pain in sleep, anesthesia, and intensive care, enabling more accurate clinical decision-making.
Researchers Maria Eichlseder and Fariba Karimi will study keyless encryption and AI's impact on online social networks to promote fair algorithms. Their projects aim to address open problems in cryptographic systems and quantify intersectional inequality.
A new algorithm, inspired by the nervous system's matchmaker, pairs drivers with riders in a way that maximizes everyone's happiness. The algorithm creates near-optimal pairings while preserving privacy, making it suitable for everyday applications.
Researchers questioned the Cascadia subduction zone's earthquake record, finding that turbidite layers showed no better correlation than random chance. The study suggests a need for further research on turbidite layers and their connection to past earthquakes.
Researchers at Boston University created an AI tool that can determine the cause of dementia using commonly collected patient data, boosting doctor accuracy by 26%. The algorithm identifies 10 types of dementia, including vascular and frontotemporal dementia, to help doctors manage patients more effectively.
A recent study found that approximately half of FDA-approved AI medical devices are not trained on real patient data, sparking concerns about device accuracy. The researchers analyzed 500+ medical AI devices and discovered that many lacked clinical validation data, which is essential for ensuring the credibility of these technologies.
The researchers will develop new algorithms to identify clusters within large datasets, enabling better community detection. They plan to test the method in various applications, including single-cell genomics and scientometrics.
A new AI-based digital platform has been developed to analyze tissue sections from lung cancer patients, making diagnosis faster and more accurate. The platform uses algorithms that enable fully automated analysis of digitized tissue samples, allowing for personalized therapy based on molecularly specific genetic changes.
Researchers at Washington State University developed an AI algorithm that optimizes 3D printing settings, reducing time and cost for engineers. The algorithm improved the accuracy and quality of printed models, particularly for complex biomedical devices like kidneys and prostates.
A new algorithm developed at Washington State University improves safety and efficiency in robots working with humans by accounting for human carelessness. The tool has shown a maximum improvement of 80% in safety and 38% in efficiency compared to existing methods, and the researchers plan to test it in real-world settings.
A computer algorithm has achieved a 98% accuracy in predicting different diseases by analyzing the color of the human tongue. The proposed imaging system can diagnose various health conditions, including diabetes, stroke, and COVID-19, using a simple and affordable method.
Researchers have discovered a non-memory-based mechanism for animals to cache and retrieve food, challenging long-held beliefs about animal cognition. The proposed mechanism uses neural networks similar to hash functions, allowing for efficient storage and retrieval of cache locations.
Researchers develop an unsupervised deep learning-based method to reconstruct particle distribution in Tomographic PIV, achieving superior performance over traditional methods. The new technique demonstrates potential for practical applications in high-density particle fields and high-velocity flow fields.
A new study led by CU Boulder computer scientist Theodora Chaspari found that AI algorithms can be confused by natural variations in speech patterns between different genders and races. This can lead to underdiagnosis or misdiagnosis of mental health concerns like depression.
Researchers have introduced a new AI calibration method called Thermometer, which enables efficient calibration of large language models for various tasks. This technique leverages temperature scaling to adjust a model's confidence and can generalize to new tasks without requiring additional labeled data.