Articles tagged with Software
Researchers developed an advanced survey system combining AR glasses with a camera and AI to objectively assess leafminer damage in the field. The DeepLab-Leafminer model achieved superior segmentation performance, resulting in high diagnosis accuracy rates.
The £250 million investment will create an Advanced Marine Technology Hub at the University of Plymouth, leveraging its expertise in autonomous marine systems, maritime cyber security, and renewable energy. This initiative aims to boost the city's economy and enhance UK's national resilience.
Researchers from Carnegie Mellon University found six million fake stars on GitHub, used to boost repository reputation and steal user data. The use of fake stars muddies the waters, making it challenging to differentiate between legitimate and malicious repositories.
Researchers at Seoul National University of Science & Technology developed LWMalloc, a lightweight and high-performance dynamic memory allocator for resource-constrained environments. The new allocator outperforms ptmalloc by achieving up to 53% faster execution time and 23% lower memory usage.
A new login system called Client-Side Encrypted Access Logging (CSAL) detects online account compromise without exposing personal devices to invasive tracking. The system verifies whether a login came from a user's own device, addressing a flaw in how major platforms log account access.
Experts from across industries and disciplines gathered to assess the current state of cybersecurity through a multidisciplinary lens. The workshop explored emerging technologies and the intersection of technology and policy, highlighting the need for a unified ecosystem to address persistent challenges.
The $2.5 million DRIFT program aims to close critical talent gaps and safeguard connected vehicles by providing specialized online and in-person training. Worcester Polytechnic Institute will lead the university’s DRIFT program, offering tuition-free modules and real-world training to upskill engineers and professionals.
Researchers at the University of Graz and the University of California, San Diego have developed a novel method to determine omega positions of lipids in complex biological samples. This breakthrough enables the study of biological mechanisms in unprecedented detail, particularly for inflammation-related diseases.
This book provides a beginner-friendly resource on the impact and evolution of decentralized networks, highlighting their applications in healthcare, supply chains, agriculture, climate monitoring, and education. The authors emphasize sustainability, data security, and ethical tech adoption.
The team aims to deliver AI power directly to devices, improving resilience and speed in constrained environments. By processing data step-by-step across a network of devices, they can create a safe and adaptable system that can withstand attacks and extreme conditions.
Researchers use AI to solve differential equations, such as Schrodinger's equation, for large-scale systems, improving efficiency and accuracy in fields like drug discovery and material design.
A research team at Vienna University of Technology has discovered a previously undiscovered Android security vulnerability that allows fraudulent apps to take control of mobile phones. Users may be tricked into performing unwanted actions, such as granting certain rights or deleting data.
The new journal aims to accelerate knowledge dissemination in AI by prioritizing theoretical breakthroughs, practical applications, and societal implications. It features short peer-reviewed contributions and opinion pieces to facilitate swift engagement with contemporary AI issues.
Researchers developed an AI-powered microscope system to measure soil fungi presence and quantity, providing insights into soil health and fertility. The low-cost optical microscopy with machine learning technology can be used by farmers and land managers worldwide.
FANDANGO, a new open-source fuzzing tool, employs an iterative procedure modeled on biological evolution to produce high-quality test inputs that cover both semantics and syntax. The tool enables complete control over test inputs, allowing testers to specify input characteristics and explore specific parts of the program.
The Association for Computing Machinery (ACM) has announced a new open-access journal, TAISAP, focusing on AI security and privacy. The journal aims to develop methods for assessing the security of AI models, systems, and environments, including adversarial attacks, privacy concerns, and cybersecurity applications.
A Cochrane review found that virtual reality (VR) can help stroke survivors regain arm movement and increase therapy time. VR may also improve balance and reduce activity limitations, but effects on mobility and quality of life are uncertain.
Researchers at Texas A&M University found that websites use browser fingerprinting to track people across browser sessions and sites. Even users who opt out of tracking under privacy laws may still be silently tracked through fingerprinting.
Researchers develop annotation-free avian population estimation approach using multimodal perception model, achieving high accuracy without explicit object localization. The method is tested on the Wetland-Bird-Count dataset, outperforming existing weakly supervised and unsupervised methods.
A new deep learning model, ENDNet, significantly enhances subgraph matching accuracy by identifying and neutralizing extra nodes that interfere with the matching process. This improves performance in pattern recognition tasks across various fields, including drug discovery and natural language processing.
The Mass Query Language (MassQL) tool empowers scientists to uncover previously unknown pollutants in massive chemical datasets. It has identified toxic compounds hidden in plain sight, including organophosphate esters and chemicals from breaking down over time.
Proof scores use term rewriting to verify system properties, striking a balance between automation and human effort. Despite limitations, the technique has been successfully applied to various systems and protocols, with potential for critical applications in safety-critical systems.
This year's ACM awards recognize groundbreaking innovations in autonomous systems, cryptography, and software for parallel computers. Peter Stone receives the Allen Newell Award for contributions to AI, while William Gropp and his team receive the Software System Award for developing MPICH.
A Dartmouth team's AI model recognized Navajo with near-perfect accuracy, identifying related languages such as Apache and Native Alaskan languages. The study suggests that this technology could be a bridge to including smaller languages in online translation services.
Eurocrypt 2025 will bring together leading cryptographic researchers and experts for a four-day conference in Madrid, featuring pre-conference workshops and over 650 participants. IMDEA Software Institute is the main organizer of this event, alongside other top-tier institutions.
Computer scientists at the University of Bath reprogrammed a Roomba to perform four new tasks, showcasing the untapped potential of domestic robots. The researchers identified over 100 ways to tap into the latent potential of robotic devices, proposing functions such as playing with pets, watering plants, and delivering breakfast in bed.
MSU is developing a computer program called MOSAIC to create holistic biological profiles from skeletal remains, making the investigative process clearer and more efficient. The project aims to leverage relationships between various structures to provide estimates without biasing results by focusing on individual components.
MIT researchers have developed a new data-driven method that eliminates redundant computations in complex logistical problems. The approach uses machine learning to predict which operations should be recomputed and reduces the solve time for problems like scheduling trains, hospital staff, and factory tasks.
Researchers at Osaka Metropolitan University developed an autonomous driving algorithm for robots to navigate raised cultivation beds, utilizing lidar point cloud data. The system enables precise movement and accuracy in both virtual and actual environments, promising to expand tasks beyond harvesting to monitoring and pruning.
A University of Florida researcher has developed a groundbreaking AI tool called VisionMD that analyzes videos of patients with Parkinson's disease and other movement disorders. The tool provides valuable information about how the disease is progressing and responding to medications, improving patient care and advancing clinical research.
A collaborative research team has developed a novel mixed reality (MR) technology that uses real-world doors as natural transition points. The system allows users to select a door within their MR interface and seamlessly transition into a virtual space, creating an unprecedented sense of immersion.
Researchers introduce an innovative approach using dynamic topic modeling to analyze annual and quarterly reports, uncovering hidden risk factors. The novel method creates tradable indices with a cost-effective alternative to traditional index construction.
The FLUID robot, developed by Hokkaido University researchers, automates the co-precipitation of cobalt and nickel to create binary materials with precision. The open-source system uses a 3D printer and off-the-shelf electronics, making it customizable and cost-effective for researchers worldwide.
Researchers will use sensors and software to predict AM part lifespan, enabling cost savings and extending part life. The project aims to improve Darwin software to provide detailed insights into manufacturing processes.
A new study published in PLOS Digital Health found that older drivers with GPS navigation systems tend to drive more frequently, suggesting these tools help maintain driving mobility. The research reveals that using GPS can alleviate spatial orientation difficulties and support older adults' independence on the roads.
Three UVA Engineering faculty members have been elected as AAAS Fellows for their groundbreaking work in computer architecture, energy transport, and hydrology. Sandhya Dwarkadas, Patrick E. Hopkins, and Venkataraman Lakshmi were recognized for their innovative research and contributions to their respective fields.
The Flatiron Institute's Center for Computational Astrophysics is now supporting MESA's ongoing maintenance and development after its creator Bill Paxton steps down. The center has hired Philip Mocz as a full-time software engineer to ensure MESA's continued growth and impact in stellar physics.
The study found significant improvements in symptoms for participants with major depressive disorder, generalized anxiety disorder, and eating disorders. Participants reported trusting and communicating with Therabot comparable to working with a therapist.
Deborah Levin and her Ph.D. student Irmak Taylan Karpuzcu conducted the first 3D simulations of hypersonic flows, exposing new disturbances in the interaction between gases and surfaces. The findings provide insights into the design considerations for hypersonic vehicles.
The University of Osaka and research partners have launched an open-source operating system for quantum computers, enabling cloud-based operation. The OQTOPUS OS can be customized to meet individual user needs and is expected to help make practical quantum computing a reality.
A team led by Dr. Marcus Botacin is creating a large language model (LLM) to automatically identify malware and write rules to defend against it. The LLM will use signatures to complement human analysts' skills, identifying malware faster and more accurately.
Researchers at Purdue University have developed AI-powered software, Molecular Intelligence, to structure biomolecules from cryo-EM image data. The tool uses deep learning to analyze low-resolution image data and construct accurate 3D structures of proteins and other biomolecules.
A $100 million philanthropic commitment from David A. Duffield will significantly expand Cornell Engineering's facilities, including the School of Electrical and Computer Engineering. The expansion will provide critical new lab space for strategic research priorities and experiential learning opportunities for students.
AutoCodeRover, a cutting-edge AI agent platform for software development, has been acquired by Sonar. The technology boosts software engineering and agentic AI innovation, creating new R&D jobs in Singapore.
A new method of biometric authentication has been developed using hyperspectral imaging and AI to identify individuals through the unique patterns in their blood vessels on the palm of their hand. The technology shows great promise for secure personal identification and could potentially be used as a key to unlock homes.
Researchers at Universidad Carlos III de Madrid developed video games 'Peter Jumper' and 'Andromeda' to promote hand and wrist rehabilitation. The system also measures grip strength and stores patient data for analysis, showing encouraging results in improving range of motion and grip strength up to 100%.
A University of Oklahoma researcher is developing a new coding language and computing infrastructure to tackle the increasing complexity of big data. The goal is to create more efficient algorithms for processing sparse and irregular data, which are challenging to manage using traditional tools.
Researchers at Mizzou have developed a proactive approach using artificial intelligence to address evolving threats against smart grids. The CIBR-Fort system can predict cyberattacks with 91.88% accuracy and defend against them in real-time, enabling scalable security for power grids of the future.
An international research team developed a user-friendly software method called Segment Anything for Microscopy, which can precisely segment images of tissues, cells, and similar structures. The new model improved performance for cell segmentation, enabling researchers to automate tasks that previously took weeks of manual effort.
CrySyst's QbC framework addresses crystallization monitoring, modeling and control using research from Purdue University. The software provides guided experiment selection, semiautomated model development and reliable solutions to reduce time and material usage.
Researchers developed a new zero-shot AI pipeline that leverages open-source foundation models like Segment Anything Model (SAM) and Grounding DINO to improve accuracy in automated image segmentation for remote sensing. The pipeline achieves outstanding segmentation results, reaching up to 99% accuracy, and operates in a zero-shot manner.
Researchers at North Carolina State University have developed a new technique to improve the efficiency of food-delivery operations. The technique accounts for key factors such as food supply, location, and vehicle capacity to determine optimized routes that make food delivery faster and more fuel-efficient.
Kun Sun proposes framework using Large Language Models (LLMs) and Retrieval-Augmented Generation techniques to analyze Android app behavior, overcoming limitations of current methods. The project aims to deliver explainable results and uncover hidden code insights for more resilient digital ecosystems.
The new Cellpose3 tool enables easy recognition of cell boundaries in distorted images, restoring crisp images for accurate segmentation. This improvement allows users to segment individual cells with ease, even in conditions with noise, blurring, or undersampling.
A study by Virginia Tech researchers found that electric vehicles generally produce less non-exhaust emissions than gasoline-powered vehicles when driving in city conditions. The research also highlights the environmental benefits of regenerative braking, which reduces brake abrasion emissions.
The researchers are developing high-performance Monte Carlo software to support computational materials design. The goal is to enable rigorous multi-scale simulations, allowing for the simulation of larger scale and fidelity than possible with current software.
The TU Graz AI system optimises vehicle components using simulation models and evolutionary algorithms to reduce development time by several months. It considers multiple objectives including production costs, efficiency and package space requirements, as well as CO2 emissions across the entire supply chain.
Schuman and her team aim to create a large library of open-source code, tools, and training programs for neuromorphic computing. They will provide community-level access to NMC systems, enabling widespread use and research in various scientific fields.
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 new tool will enhance the DLA's supply chain management capabilities, reduce operational disruptions, and bolster readiness. Quantum Research Sciences' technology will provide predictive capabilities and automate obsolescence management processes.