Articles tagged with Educational Software
A new open-source software, GI4RAQ Platform, enables practitioners to estimate pollutant concentration changes resulting from different planting schemes in streets. It focuses on key pollutants from road transport and provides a detailed analysis of the urban form and planting specified by users.
Researchers have developed a machine learning program that accurately predicts the band gap of photovoltaics materials in milliseconds, using freely available software. This breakthrough could render supercomputers unnecessary for some applications, as stoichiometry is found to be a crucial factor in predicting band gaps.
Researchers at Max Planck Florida Institute for Neuroscience used machine learning to develop Gold Digger software that can accurately identify gold particles bound to specific proteins of interest. The software uses a deep learning approach to distinguish gold particles from shadow artifacts with near-human level accuracy.
A new project seeks to fill a gap in identifying vulnerabilities in ML frameworks by using Software Composition Analysis and Directed Grammar-Based Fuzzing. The tool can automatically report vulnerabilities in open-source libraries that an application depends on, helping developers address them before they can be exploited.
Researchers at Princeton University have created a new microchip design that enables AI systems to process data closer to the edge of computing infrastructure. The innovative design reduces power consumption and latency, making AI more accessible and efficient.
A team of Penn State researchers used machine learning algorithms to improve the efficiency of design evaluations for porous materials. By leveraging image colorization techniques, they reduced computational load while maintaining accuracy. The findings provide a framework for designers to create more structurally responsible parts wit...
Researchers at Università di Trento developed RoomTetris algorithm to efficiently allocate rooms, increasing hotel occupancy rates and profits. The software has shown promising results in tests, with potential to double profitability for some hotels.
Researchers developed self-learning algorithms to analyze bioscientific image data, enabling fast and accurate organ detection in medical imaging. The AI-powered software can process whole-body scans of mice in seconds, outperforming human analysts.
The SyNRG team at the University of Illinois is exploring a new sub-area of mobile technology called 'earable computing' that will run on earphones. This platform aims to continuously sense human behavior, provide acoustic augmented reality, and offer seamless security, among other capabilities.
Scientists from the University of Groningen developed a machine learning-based algorithm, PySurf, which reduces electronic structure calculations significantly. The software requires several orders of magnitude less computational time than existing direct dynamics software and is available as an open-source free download.
Insilico Medicine introduces Molecular Sets (MOSES), a benchmarking platform for generative chemistry models, enabling easy comparison and evaluation of new models against existing approaches. The platform provides a curated dataset, metrics, and baselines for assessing model performance.
Researchers at the University of California, Berkeley, have created AI software that gives robots speed and skill to grasp objects, making it feasible for them to assist humans in warehouses. The technology reduces computation time from 29 seconds to under one-tenth of a second.
Researchers create cheat-detection system for massively multiplayer online games, eliminating need for decrypted data. The approach can identify cheating patterns in real-time and take action to protect fair play.
ESEC/FSE 2020, a leading software engineering conference, presents outstanding research results and trends in virtual format. The conference features keynote addresses on human-computer collaboration, diversity, and inclusion initiatives.
A new software tool called ATLAS measures children's phonological awareness, a critical skill for literacy development. The study found that the software was effective in assessing over 1,100 children aged 3-7 with varying levels of speech and language impairment.
Researchers at TUM have developed a software module that analyzes and predicts events while driving, ensuring the vehicle will not cause accidents. The system determines movement options and emergency maneuvers to prevent collisions, using simplified dynamic models for swift calculations.
A new tracking technology using Footprint Identification Technique (FIT) helps monitor endangered black rhinos in Namibia. The software analyzes footprint images to identify individual animals and track their movements without disturbing them.
Scientists have developed an artificial intelligence system that autonomously learns how to grip and move individual molecules, overcoming the complexity of nanoscale manipulation. The system uses reinforcement learning to find optimal movement patterns, enabling targeted assembly and separation of molecules.
A new study warns that unregulated AI can be detrimental to sustainable development, particularly in developing nations. AI's misuse by big tech can lead to biases, corruption, and job displacement, highlighting the need for proactive regulatory measures.
Researchers developed an AI algorithm that can accurately diagnose Alzheimer's without expensive scans or in-person testing, with over 95% accuracy. The software also explains its conclusions, allowing physicians to double-check the accuracy of its diagnoses.
The article reports on a research paper comparing onsite server setups and virtualized cloud setups for teaching GIS courses online. The authors share user feedback and discuss resource metrics needed to support student computing needs, highlighting the growing need for fast computers.
Researchers at Oak Ridge National Laboratory developed an AI software named Peregrine for powder bed 3D printers, assessing part quality in real-time. The software uses convolutional neural networks to analyze images and detect anomalies, alerting operators for adjustments.
Researchers at Texas A&M University are using advanced machine-learning analysis to reveal the evolution of cracks in rock and concrete. By combining data from multiple sources, including sound waves, electromagnetics, and pressure measurements, they aim to improve our understanding of crack damage and development.
A new study found that ad blockers can help websites target specific audiences with less intrusive ads, benefiting both platforms and users. The study suggests that allowing ad blockers can lead to a more efficient market, resulting in better-quality content for users.
A new model called Swiftaid has been developed to automate the process of claiming Gift Aid on donations, allowing charities to claim up to £2.50 for every £10 donated. This system uses formal methods to improve design and security, streamlining the process and unlocking millions in extra funding.
Tel Aviv University and IDC Herzliya researchers discovered a DNS vulnerability that could have enabled a massive DDoS attack, potentially disabling critical parts of the internet. The 'NXNSAttack' technique takes advantage of vulnerabilities in common DNS software to overwhelm servers with false requests.
The Chan Zuckerberg Initiative is awarding $3.8 million to support essential open source software projects in biomedical research and clinical medicine. These grants will enable awardees to improve software tools, enhance collaboration, and advance biomedical science.
A team of engineers has created hardware that can learn skills using a type of AI that currently runs on software platforms. The hardware, made of a quantum material, is capable of learning numbers and demonstrates artificial tree-like memory at room temperature.
A new software platform is being developed to produce searchable digital atlases of whole organs at the cellular level, offering a Google Maps-style tool for high-resolution 3D images. This platform will allow researchers to easily search normal and diseased organs to track change over time.
Nathan Burtch is creating an open laboratory manual for quantitative methods courses in geography, addressing a long-standing need for resources. The manual will utilize statistics to solve real-world geographical problems and be available to instructors across Virginia and beyond.
Using Euclid's algorithm as an example, Dr. Lamport showed how a precise mathematical formula can be used to specify an algorithm, making it more efficient and easier to debug. By using math instead of code, developers can reduce the size of their programs by up to ten times and make debugging easier.
Researchers created a digital amplifier model using a deep neural network that can accurately simulate the sound of various guitar amplifiers, including popular brands like Marshall and Orange. The study uses black-box modelling to replicate the observed input-output mapping of analogue circuitry.
Researchers at Texas A&M University developed a tool to identify the source of errors caused by software updates using deep learning. The algorithm, which analyzes performance counters, can find bugs in a matter of hours instead of days.
Researchers propose incorporating 'feminist design thinking' to develop software reducing algorithmic bias against underrepresented groups in IT workforce. The approach aims to value inclusion and equity across gender, race, and ethnicity.
A team of researchers led by Carnegie Mellon University aims to create AI agents that can infer human thoughts based on behavior. They plan to test these socially intelligent agents in a search-and-rescue scenario within Minecraft to understand what humans are thinking.
Researchers at UC San Diego developed a computer-based method to determine crystal structures of materials and molecules using a machine learning algorithm, achieving at least 95% accuracy. The new approach autonomously analyzes electron diffraction patterns and can perform analysis on large samples with multiple length scales.
Researchers found that kinaesthetic imagery ability enhances golf putting performance, and mental practice can improve a golfer's putting ability even if they already have a good feel for the game. The study suggests that this technique may reduce a golfer's handicap and is crucial in determining earnings on the PGA Tour.
Etalumis, a probabilistic programming framework, has been developed to control existing simulators and run on large-scale HPC platforms. It enables researchers to interpret vast volumes of experimental data by essentially 'reversing' simulations, bringing new insights into complex physics problems.
A deep convolutional neural network-based software improved radiologist detection of malignant lung nodules by 70.3%, reducing false positives to 0.18 per X-ray. The study suggests machine learning methods can help overcome challenges in detecting lung lesions on chest X-rays.
New research shows software firms tend to set up close to established businesses, creating clusters that persist due to the ready supply of skilled employees. This clustering leads to sustained employment in certain areas, but does not necessarily result in increased profitability.
A new AI software developed by University of Oxford scientists can recognize individual chimpanzee faces in the wild, allowing researchers to track behavior over long periods. This technology has potential for conservation efforts and animal behavior research, offering a sustainable solution to monitor species.
A team of scientists from FEFU developed a software module to automatically diagnose defects in sensors and electric drives in various kinds of robots. The system can compensate for detected defects in real time, preserving the required levels of operating quality.
University of Arizona researchers are using the Catalina Sky Survey's near-Earth object telescopes to find optical counterparts to gravitational waves triggered by massive mergers. The team found several supernovae and a near-Earth object during their ongoing campaign, which began in April.
A new machine learning tool, KymoButler, automates the analysis of kymographs to track particle movements inside living cells. This improves research efficiency and reduces bias.
West Virginia University is creating 40 annual scholarships to support students in cybersecurity roles. The program aims to address the growing demand for cybersecurity experts amid escalating cyber threats and unfilled positions globally.
Researchers discovered over 1,600 vulnerabilities in the Google Play Store's backend systems, exposing personal information and potentially mobile devices. An automated system called SkyWalker has been created to vet these servers and software library systems, helping developers improve app security.
A new framework for software management was recognized for its potential impact on computation-based science, enabling the Ohio Supercomputer Center to efficiently install and test applications for a wide range of users. The framework leverages automated tools and continuous integration to streamline the process.
A team of FEFU scientists created software allowing industrial robots with technical vision to adjust movement trajectories in real-time without sacrificing precision. The new smart control method has improved accuracy by up to 0.5mm, a significant step towards overcoming current technology limitations.
Scientists developed a command-and-control plugin for intelligent industrial robots, allowing for high-quality 3D computer models to be built quickly and precisely. The software helps solve the issue of hard programming of industrial robots and can fix in-process workpieces on universal positioning devices.
Galahad uses role-based isolation, real-time sensing, and machine learning to detect malicious activity in cloud workloads. The system provides a secure platform for users to host applications without relying on specialized AWS services.
A Rutgers University study uses artificial intelligence to control a robotic arm that efficiently packs boxes, saving businesses time and money. The system develops software and algorithms for robust motion and real-time monitoring to detect failures.
A NUS pilot study demonstrates the potential of CURATE.AI to create individualized profiles for customized training, leading to improved cognitive performance. The AI platform tailors training intensity and duration based on a person's unique response data.
The ML-DSP tool can provide conclusive answers to complex questions about species, DNA, and viruses. It has been shown to outperform other classification software tools in terms of accuracy and speed.
The University of Texas at San Antonio (UTSA) researchers have each been awarded a National Science Foundation (NSF) Faculty Early Career Development (CAREER) Award, totaling $2 million. The awards will support various projects, including energy planning and management for smart cities and biomedical engineering research.
Mendel Rosenblum's work on virtual machines transformed datacenters and enabled modern cloud computing. His contributions led to the development of Amazon Web Services, Microsoft Azure, and Google Cloud.
A team of researchers has developed MyRoot, an AI-powered software that uses machine learning to analyze root growth of Arabidopsis thaliana seedlings. The software has been shown to reduce the time required for manual measurements by approximately half and provide more precise root length measurements.
A team of researchers led by H. Paul LeBlanc III has developed a software prototype aimed at reducing the time companies spend training data analysts, using statistical knowledge in real-world research problems. The NSF grant will help them refine their product and develop a suite of software products for commercial use.
Thierry Pécot, a Hollings Cancer Center researcher, has received a $1.1 million grant from the Chan Zuckerberg Initiative to develop deep learning tools for biomedical image analysis. The goal is to enable biologists to apply these tools to their images and accelerate disease research.
Researchers at Saarland University have developed a free open-source software tool called Dave, which enables the rapid evaluation of signals, pattern recognition, and data visualization for large sensor datasets. The tool uses machine learning methodologies to identify patterns quickly and evaluate data cleanly.
Researchers found that firms in Pakistan were able to overcome political instability and security concerns through two strategies: 'step-up' and 'break-out'. The 'step-up' process involves firms mitigating client concerns and building trust, while the 'break-out' strategy focuses on short-term gains and quick turnaround.