Articles tagged with Educational Software
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.
Scientists have devised an elegant tool to quantify the movement and changing morphology of cells through time using machine learning. The software, Usiigaci, analyzes microscopic snapshots of migrating cells and detects their changing outlines, enabling single-cell tracking at unprecedented resolution.
Researchers from the University of Seville applied Life-Cycle Assessment (LCA) to the Roman Theatre of It¡lica to reduce its environmental impact. The study developed tools that integrate LCA and BIM software to make environmental-impact reduction criteria part of the design process.
Researchers have developed an innovative new software that measures electrical activity in the heart, which may help identify potentially lethal arrhythmia. The open-source ElectroMap software can detect, map, and analyze arrhythmic phenomena for various data types, leading to a deeper understanding of heart diseases.
The University of Illinois Chicago will lead a $3 million project to design and develop GAMEPLAY, a system that identifies security vulnerabilities in web software. Once identified, the system will generate patches for these vulnerabilities, known as exploits, to improve software security.
Researchers at MUSC created an online software package to train health care workers using simulation in safe Ebola disease response, increasing knowledge of effective prevention by up to 19% and reducing critical errors. The program aims to reduce the number of critical errors and risky actions committed when treating an Ebola patient.
A team of researchers at the University of Sussex has developed a fast and energy-efficient simulation of part of a rat brain using off-the-shelf computer hardware. By leveraging Graphics Processing Units (GPUs), they achieved processing speeds up to 10% faster than current supercomputers, while reducing energy consumption by 10 times.
Researchers at Argonne National Laboratory are developing a machine learning-based framework called BLAST to accelerate and simplify materials modeling and simulation. This software will enable companies to quickly perform molecular dynamics simulations needed for new material vetting, with applications in polymers and steel alloys.
A new study will assess the effectiveness of AI-assisted ultrasound technology in enabling non-specialist medical professionals to capture high-quality echocardiograms. The 'SHAPE' study aims to determine if AI-guided acquisition and interpretation can detect more patients with cardiac disease in primary care settings.
MSU researchers developed a new course 'Integrative Biology: From DNA to Populations' featuring Avida-ED, a digital evolution software program. This approach allows students to engage with biological concepts in a familiar and interesting context, resulting in increased understanding of evolution-influenced topics.
A new wireless location system has been developed to drive future wireless innovation, providing control over disparate radio and network technologies. The system's integration with WiSHFUL architecture allows for experimental investigation of network applications using real-time location data.
A study published in Science Translational Medicine shows that PGDx's CerebroTM technology can detect tumor-specific mutations with higher sensitivity and positive predictive value compared to existing methods. This improvement is crucial for accurate treatment decisions, particularly for biomarkers like tumor mutation burden.
NYU is part of IRIS-HEP, a National Science Foundation-backed coalition developing next-generation cyberinfrastructure for high-energy physics research. The institute aims to drive innovations in data analysis and algorithms essential to handling massive LHC data.
A new study reveals that IT jobs have grown by 19.5% between 2004 and 2017, while less IT-intensive occupations grew only 2.4% over the same period. The growth in IT jobs is more than eight times the growth rate of other jobs.
D-Wave Systems Inc. has successfully demonstrated a topological phase transition using its 2048-qubit annealing quantum computer, simulating a phenomenon behind the 2016 Nobel Prize. This breakthrough could lead to faster materials prototyping at lower costs.
A team of NYU Tandon researchers has received a $900,000 NSF grant to develop tools for safer AI deployment. The tools will address defensive schemes against malicious attacks and detect 'backdoors' in AI systems.
The ShareBackup system uses fast switches and software to take over network traffic after a failure, minimizing downtime for applications. It can analyze problems, including misconfigurations, and diagnose faulty devices, helping data centers optimize their networks.
University of Melbourne researchers have developed a software tool to predict landslide boundaries by identifying subtle patterns in motion, allowing for early warning signs to be detected. The tool uses big data analytics and applied mathematics to shed light on the microstructure level of failure in landslides.
Researchers discovered a security hole in popular encryption software that could have allowed hackers to steal encryption keys from smartphones by intercepting electromagnetic signals. A fix for the vulnerability was adopted in software versions made available in May.
A new brain-inspired computer called SpiNNaker has been developed to mimic the human brain's neural networks. It produces results similar to the best brain-simulation supercomputer software currently used for neural-signaling research, advancing our knowledge of neural processing in the brain.
A new software has been developed to automate the identification of dendritic spines in brain cells using machine learning. The software can identify spines with over 90% accuracy and is designed to be fast, scalable, and easy to use.
Boston University School of Medicine is developing a software application to identify and share professional development opportunities for graduate and postdoctoral trainees. The grant will support pilot projects to prepare students and researchers for successful careers in biomedical sciences.
The Specify team has adopted a biological museum-membership organization to migrate from grant-supported to community-supported funding. The new model allows institutions of all sizes to contribute to the operating budget, while maintaining open-source software licensing and free access for users.
UNIST's Statistical Artificial Intelligence Lab (SAIL) won the digital curling competition with an AI-based software designed by Kyowoon Lee, Sol-A kim, and Professor Choi. The team applied Kernel Regression and Reinforcement Learning-based Deep Learning Technique to form self-winning strategies.
HyperTools uses mathematical techniques to visualize complicated datasets and reveal underlying geometric structures. The tool provides insights into patterns, clusters, and relationships in data, enabling researchers to develop machine learning algorithms.
The Texas Advanced Computing Center (TACC) is developing innovative software solutions to enhance scientific productivity. Their interactive parallelization tool, IPT, enables researchers to convert serial code into parallel code using tens of thousands of processors, achieving significant speed-ups and user productivity enhancements. ...
A U.S. Army Research Laboratory researcher has developed a mathematical approach to design chemical compounds, reducing complexity and leveraging machine learning. This method could lead to the discovery of new materials with unique properties.
Bayou, developed by Rice University, uses neural sketch learning to recognize patterns in Java code and generate code snippets. This enables developers to get immediate feedback on their queries, making it easier to navigate the numerous APIs.
A Polish-Colombian team developed software using bee and cuckoo behavior to optimize flight routes, achieving measurable financial and environmental savings. The algorithm allows real-time modification of routes, reducing greenhouse gas emissions and operating costs.
A recent study suggests that information security managers can motivate employees to act more securely by providing relatable messages and offering options. Employees may not realize they're putting company data at risk, but giving them choices can encourage better behavior.
The TRAPPIST-1 planets are curiously light, suggesting the presence of water instead of atmospheric gases. The team found that the inner planets have less than 15% water by mass, while the outer planets have more than 50%.
Researchers developed AI software to predict glioma patient survival by analyzing tissue biopsies, outperforming human pathologists' predictions. The approach combines deep-learning and conventional methods to provide more accurate and consistent information for doctors.
A software prototype called eFeed-Hungers has been developed to divert excess food to those in need, reducing food waste in the US and India. The interactive online network allows donors to post food they have to donate and those in need to find nearby locations for pickup.
Researchers will co-design hardware and software to realize quantum computing's potential more rapidly, focusing on efficient algorithms and tools for programming and education. The collaboration aims to create a community of academic and industry partners to drive progress in the field.
The Real-Time Captcha approach uses a randomly-selected question within a Captcha image, requiring users to respond quickly and making it difficult for machine learning programs to spoof legitimate users. The technique combines face recognition with Captcha, strengthening biometric authentication.
A recent study by UL and Johns Hopkins University found that artificial intelligence (AI) is superior to traditional animal testing in detecting toxic substances. The AI-powered software, REACHAcross™, can predict chemical toxicity with high accuracy and speed, reducing the need for animal testing.
Researchers at Princeton University have developed a software tool using machine learning to predict reaction yields, reducing time and cost for synthesizing new medicines. The tool, which can handle up to four reaction components, uses random forest models to accurately forecast yields for thousands of reactions.
The Scanpy software is a candidate for analyzing the Human Cell Atlas, enabling comprehensive analysis of large gene-expression datasets. It uses graph-based algorithms to characterize cells by identifying their closest neighbors, similar to social networks.
A study using Avida-ED curriculum found that students who used the digital evolution software improved their understanding of evolutionary principles, including variation, randomness, and natural selection. The tool also increased acceptance of evolution among students, suggesting it could be an effective educational tool.
A Dartmouth College study found that non-experts who responded to an online survey performed equally as well as the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software system in predicting repeat criminal behavior. The study also demonstrated that only two variables - a defendant's age and number of p...
A new study suggests that a widely used criminal risk assessment tool is no more accurate than untrained people in predicting recidivism. The researchers found that with fewer features, human predictions were just as accurate, and false positives were equally unfair to black defendants.
A new technique uses interactive software to analyze digital images of giant panda footprints, identifying individual animals and their sex with high accuracy. The system's ease of use makes it suitable for studying elusive species like the giant panda.
Researchers developed a compact and inexpensive camera that produces high-resolution 3D images from a single 2D image. The DiffuserCam uses computational imaging to reconstruct 100 million voxels from a 1.3-megapixel image, with potential applications in brain research, self-driving cars, and machine learning.
Researchers at IIT-Istituto Italiano di Tecnologia focus on iCub's evolution from its origin to date, showcasing hardware and software co-evolution. The robot's current version enables crawling, sitting, balancing, and recognizing objects, with a sensitive full-body electronic skin system.
Researchers found that action games enhance visual and reading attention in players, potentially aiding those with dyslexia. The study suggests that specific components of action games can be used to create new software to combat the disorder.
A new virtual child software is being developed to train professionals in behavioral intervention techniques for children with autism spectrum disorder. The software will feature a virtual child programmed with learning difficulties associated with autism, allowing users to practice and master treatment methods.
A software program can accurately predict tumor-specific markers on leukemia cells in patients who have received stem cell transplants. The researchers plan to use their findings to develop immune-based therapies that target these antigens.
A new system using thousands of Raspberry Pi nodes brings a powerful HPC testbed to system-software developers and researchers, enabling them to work on large supercomputers without dedicating expensive machine time. The scalable clusters have applications in education, internet of things, and HPC network topology research.
Researchers developed software using machine learning to analyze EEG signals from preterm infants, providing an estimate of brain functional maturity. The method is more precise than current methods and enables automatic monitoring of premature infant brain development.
The study uses image data to reconstruct the cell cycle of white blood cells and the progress of diabetic retinopathy, demonstrating the method's capability in handling continuous biological processes. The software also identifies individual categories and assigns measured data to clusters when data is not part of a continuous process.
The Ohio Supercomputer Center has released Open OnDemand 1.0, an open-source web portal for accessing high-performance computing (HPC) services. This initiative aims to lower the barrier to HPC use by providing a user-friendly interface.
A team of scientists from the University of Freiburg has created a self-learning algorithm that decodes human brain signals measured by an electroencephalogram (EEG) with high accuracy. The algorithm, based on brain-inspired models, can recognize and differentiate between various behavioral patterns from different movements, making it ...
Computer scientists at UMass Amherst have developed a new technique called 'Themis' to automatically test software for discrimination, highlighting the need for fairness in AI-driven decision-making. The researchers found that even fair-designed software can perpetuate bias when trained on biased data.
Virtual.Pyxis software enables designers to create stronger and more versatile parts while shortening lead time and development cost. It can process a larger number of variables and constraints at a lower cost than commercially available programs.
Researchers at USC and Georgia Tech will develop a powerful new data-analysis platform to process massive amounts of graph data in real-time, with potential applications in security, consumer applications, and predicting cyber attacks. The goal is to achieve a 1000-fold speed-up in processing data.
BUSM is developing a secure data-sharing platform using advanced cryptographic tools to share clinical, molecular and cellular datasets between India and the US. The project aims to analyze information on diabetes and other diseases in both countries, addressing infrastructure gaps and foreign hacking threats.
The project will establish a digital 'Online Cyber Security System' decision support service to rapidly bring together information on system vulnerabilities and alert organisations that may be affected. The system aims to address the acute shortage of cyber security experts by providing an up-to-date threat assessment and decision supp...
A three-year Lancaster University project uses geographic information systems (GIS) and 3D modeling to analyze space and place in literary texts. The project creates interactive and immersive teaching resources, including Minecraft versions of fictional settings.