Articles tagged with Software
The BioImage.IO Chatbot uses extensive language models and Retrieval-Augmented Generation (RAG) to provide real-time access to databases and minimize errors. It enables researchers to perform complex image analysis tasks in a simple manner, working directly with microscopes and laboratory equipment.
Researchers at CAMERA have developed an open-source markerless motion capture system using computer vision and deep learning methods. The system estimates joint positions from regular 2D image data, providing unobtrusive analysis of body movements.
NCSA launches Harbor, a fast storage service for global home and software directories, boosting Delta system performance by 400%. Consolidating file systems to VAST namespace improved uptime, load times, and user experience. With Harbor and VAST Data Platform, NCSA achieves scalable and efficient AI infrastructure.
A study published in Radiology found that radiologists and physicians who received local explanations from artificial intelligence (AI) systems performed better and made faster diagnoses than those who received global explanations. The researchers also found that AI advice was trusted more quickly when it provided local explanations.
AnalySwift will develop a composite heater layer for trusses and other infrastructure, enabling the reconfiguration of structural elements in space. The company's software tool will simulate multiphysics modeling and analysis of thermoplastics.
The Digital Olfaction Summit 2024 will present the latest developments in digital olfaction, including portable sensors like Scout3 and NeOse, and wearable devices for real-time scent detection. The event will also feature a unique challenge to digitize scents representing regional cultural essence.
Despite their ability to provide turn-by-turn driving directions in New York City with near-perfect accuracy, generative AI models do not form a coherent internal map of the city. The researchers developed new metrics to test a transformer's world model and found that only one generated a coherent world model for Othello moves.
A research team from Hokkaido University has developed a flexible multimodal wearable sensor patch that can detect arrhythmia, coughs, and falls using edge computing on a smartphone. The sensor patch generates large amounts of data that must be processed to be understood.
The Clinical Genome Resource (ClinGen) has published data on over 2,700 genes curated for clinical relevance to genetic diseases. The consortium has identified 2,420 gene-disease relationships, classified 5,161 unique pathogenic variants and validated 1,557 genes for dosage sensitivity assessments.
A team of scientists and experts led by PNNL has developed a cloud computing approach to democratize access to emerging resources. They demonstrated that cloud computing can provide an agile complement to high-performance computing facilities, enabling complex chemistry workflows to be completed in days instead of months. The initiativ...
Karimian's research will investigate common hardware-based attacks on biometric systems, including spoofing, template, side-channel, and fault-injection attacks. He also aims to develop a hardware-based biometric template protection system that addresses bias in facial recognition software.
Researchers from King's College London have created a new kind of compact circuit that enables robots to receive complex instructions without electricity. This breakthrough could enable the creation of robots with more complex AI-powered software and improve their social awareness and dexterity.
Researchers propose a new approach to reduce the tradeoff between overhead and protecting machines against vulnerabilities. The 'Vulnerability-Adaptive Protection Paradigm' applies different protection strategies to different parts of the system, allocating resources more wisely.
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 team of researchers aims to improve autonomous vehicle safety by identifying and mitigating vulnerabilities in software and hardware. They plan to use knowledge gained from a $926,737 NSF award to design protection mechanisms that can be applied selectively to ensure safety while maximizing efficiency.
A new course launched with funding from the UK Space Agency to address the growing skills gap in software, data, and AI for the UK space sector. The Securing the future of space: Space Software and Data/AI CPD programme will equip mid-career professionals with expertise in AI and data-science.
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.
Researchers at USC developed an approach that matches polysomnography using a single-lead echocardiogram, allowing anyone to create their own low-cost, DIY sleep-tracking device. The software significantly outperformed other EEG-less models and assesses sleep stages at the highest level.
A study found that large language models, despite accuracy in medical exams, fail to consistently request necessary examinations and often deviate from treatment guidelines. In comparison to human doctors, AI diagnoses achieved lower accuracy rates, highlighting concerns about their suitability for everyday clinical practice.
A large multicenter study has identified 34 new genetic diseases using genetic diagnostics, including a novel AI-powered analysis tool called GestaltMatcher. The study analyzed the genetic data of 1,577 patients and found changes in 370 different genes, with 425 children diagnosed with rare diseases.
Researchers developed a new method to study rock engravings, integrating technological and visual analysis to uncover the cultural significance of engravings in Timna Park. The approach provides comprehensive insights into the production processes and cultural context of ancient engraving practices.
A recent study investigates the trust and involvement of Cameroonian software developers in open-source projects, highlighting cultural biases and infrastructural limitations as major barriers. The research aims to enhance understanding of trust mechanisms within these communities, focusing on African developers' unique challenges.
A team of researchers developed EMOKINE software to measure the objective kinematic features of movements that express emotions. The software provides movement parameters from data sets at the touch of a button, allowing scientists to analyze emotional expression and intentions.
A new study identifies six best practices for addressing non-functional requirements (NFRs) to ensure software security and performance. The research highlights the importance of NFRs in determining software quality and success, and how developers discuss and manage these requirements.
The WVU researchers developed a non-invasive, at-home sleep apnea detection device that uses artificial intelligence technology to measure oxygen levels in the blood. Early detection can help prevent worsening of underlying comorbid conditions and reduce healthcare costs, according to Dr. Sunil Sharma.
Researchers developed a symbolic model checking approach to verify quantum circuits, addressing the gap between model-checking quantum programs and quantum circuits. They used Maude programming language to formally specify and verify quantum circuits, confirming their correctness and paving the way for error-free quantum computing.
The University of Bonn has developed an AI software that can simulate the growth of field crops using drone photos. This allows farmers to estimate parameters such as leaf area or yield with high accuracy, and even predict the outcome of certain interventions. The software also focuses on polycultures, which can boost yields by reducin...
A recent study published in Anesthesia & Analgesia found that clinical decision support software can prevent up to 95% of medication errors in the operating room. The software provides evidence-based information to clinicians at the point-of-care to enhance decision-making and prevent errors.
Research from Texas McCombs finds that developers who multihome their software attract more users to the original product, improving its performance and standing out in the market. The study also shows that multihoming can lead to a 5.3% increase in average monthly usage for similar products.
Researchers from Mainz University and the University of Chile are developing a new technique called Gradual Abstract Interpretation to improve program analysis methods and detect security vulnerabilities in WebAssembly. They aim to identify and address security vulnerabilities while eliminating redundant protective measures.
Two new Parnas Fellows, Prof. Hongyu Zhang and Prof. Daniela Damian, will share their expertise with researchers at Lero, enabling collaboration and knowledge sharing. The fellowship programme has brought world-class software researchers to Ireland to share their experience and expertise.
Researchers developed CT-Derived Functional Imaging, a software program that calculates lung volume changes and blood mass without contrast dye. The technology has improved diagnoses for up to 30% of patients who couldn't tolerate contrast dye, and also benefits all patients with lung issues such as COPD and cancer.
Konstantinos Mamouras, assistant professor of computer science at Rice University, has been awarded a $547,555 NSF CAREER Award to decentralize IoT applications and relieve network congestion. He aims to introduce novel programming techniques that enable efficient and reliable IoT development.
A new tool called VFCFinder analyzes open-source software updates to pinpoint specific code sections being modified to address security vulnerabilities. This helps programmers determine which updates are necessary without unnecessary changes.
A study reviewed 100 US institutions with National Center of Academic Excellence in Cybersecurity designations, finding significant variation in program types, credits, and learning outcomes. The research aims to improve industry-readiness and graduate employability by highlighting areas for improvement in cybersecurity education.
Researchers created GraSSRep and rhea, tools that outperform current methods for handling repeats and structural variants in metagenomic data. These methods use self-supervised learning and graph neural networks to analyze microbiome data, offering new insights into biological processes and potential applications in antibiotic resistance.
A new AI method developed by Swedish researchers can identify toxic substances based on their chemical structure, potentially replacing animal testing. The method has been shown to be more accurate and broadly applicable than existing computational tools, offering a promising alternative for environmental research and authorities.
A study by Washington State University found ChatGPT's generative AI system provided inconsistent heart risk assessments for patients with chest pain. The AI failed to match traditional methods used by physicians and returned different results for the same patient data, highlighting its limitations in high-stakes clinical situations.
A computer vision researcher has developed privacy software for surveillance videos that obscures identifiable information such as faces and clothing in real-time. The software, funded by the National Science Foundation's Accelerating Research Translation program, aims to balance surveillance needs with privacy concerns.
Using AI software called SLEAP, scientists at Salk Institute are designing climate-saving plants with optimized root systems that can store more carbon. This approach enables researchers to analyze plant features and connect desirable traits to targetable genes, accelerating the development of carbon-capturing plants.
A Wayne State University researcher is working to transform code review tools and workflows to address participants' challenges in understanding and communicating code changes. The goal is to produce high-quality feedback using empirical methods, machine learning, and natural language techniques.
A study found that GPT-4 matched the performance of radiologists in detecting errors in radiology reports, with an accuracy rate of 82.7%. The use of GPT-4 resulted in lower mean correction cost per report than the most cost-efficient radiologist.
The digital twin of a railway wireless network uses scenario modeling, radio wave propagation characterization and integrated operation platforms to improve safety and efficiency. The study introduces key technologies such as ray tracing and AI-based super-resolution to achieve accurate deterministic modeling of wireless channels.
A new study introduces a high-performance rail inspection system using YOLOv8 for fast and accurate defect detection. The system achieved up to 281.06 FPS on desktop systems and 200.26 FPS on edge computing platforms, increasing processing speeds while maintaining high accuracy levels.
Researchers at Kennedy Krieger Institute and Johns Hopkins Medicine developed a new method for analyzing walking and gait using free software and cellphone videos. This approach is more accessible and quicker than current state-of-the-art methods, enabling clinicians to assess patients' walking abilities more conveniently.
Researchers developed Umwelt software that allows blind and low-vision users to build customized data representations without an initial visual chart. The system incorporates three modalities: visualization, textual description, and sonification.
Researchers at University of Missouri are developing software that allows drones to fly independently, perceiving and interacting with their environment while achieving specific goals. This technology has the potential to assist in mapping and monitoring applications, such as 3D or 4D advanced imagery for disaster response.
A four-month department-wide EHR optimization project led to improved usability and reduced administrative burdens. The study demonstrates that successful EHR workflow optimization is possible at the departmental level through ongoing collaboration between EHR users and IT colleagues.
Researchers developed a new tool to improve the accuracy of electronic devices that measure plant leaf color to assess health. The software uses polarization to account for variations in light and reduce errors caused by glare.
A new Dartmouth study reports on a unique case of prosopometamorphopsia (PMO), a rare condition that distorts facial features. The researchers used computer software to visualize the patient's real-time perception of face distortions, providing accurate and photorealistic visualizations for the first time.
A new measure called “outdoor days” describes the number of days per year that outdoor temperatures are neither too hot nor too cold for people to go about normal outdoor activities. This measure reveals significant global disparities, with the North gaining more outdoor days and the South losing them due to rising temperatures.
The selected research project aims to develop a lightweight edge AI-based technology for jointly exploiting wireless communications and sensing in smart factories. It will enable high-quality wireless communications even under challenging situations.
Communications of the ACM has been revamped as a web-first, open-access publication, enabling rapid article publication and enhanced reader experience. The new model aims to increase engagement with the broader computer science community, expand author reach, and showcase cutting-edge ideas and research.
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.
A new study by Zachary Kowaleski found that RegTech investments can have operational benefits for large broker-dealers, including improvements in customer relations and employee monitoring. However, small companies were more negatively affected, with profits dropping by an average of over 10 times the apparent savings.
Scientists have created an algorithm to design synthetic DNA segments that indicate the state of cells in real-time. This tool will be used to screen for anti-cancer or viral infection drugs, as well as improve gene and cell-based immunotherapies.
Incheon National University researchers developed a web 3.0 streaming architecture that reduces delay, improves user experience, and ensures transparency and fairness for real-time services. The proposed system uses Inter-Planetary file system (IPFS) to enable blockchain-based peer-to-peer data storage and caching.
A new camera system records natural animal-view videos with high accuracy, enabling scientists to study animal behavior and navigation. The system uses four color channels, including UV light, to produce accurate video of how animals perceive colors.
Researchers have designed a new, affordable system to study neural interactions and compute using living neurons. The open-source MiV system boasts over 500 electrodes, offering improved control and precision in measuring neural processes.
Quantum Research Sciences has developed a quantum computer software that achieves 28% improved accuracy over classical computers in predicting optimal inventory levels. The software will be used by the US Air Force to manage its supply chain, reducing costs associated with excess or inadequate inventory.