Articles tagged with Big Data
A new computational framework, Non-MapReduce, uses random sampling to efficiently sort through Big Data files, reducing communication and memory costs. This approach enables faster processing times and energy efficiency in cloud computing.
Researchers at the University of Illinois Urbana-Champaign found that people's use of popular websites and social media platforms differs significantly based on their location and language. The study analyzed data from 124 countries and found that YouTube and Twitter are used in distinct ways across regions.
Researchers provide a comprehensive catalog of medical knowledge graphs, their creation, and usage. Medical knowledge graphs have wide-ranging utility in the medical field, including disease diagnosis and drug development.
A new study used satellite data and public registry information to track the changing identities of commercial fishing vessels, revealing that nearly 20% of high seas fishing is carried out by unregulated or unauthorized vessels. The study found hotspots of potential IUU fishing in the Southwest Atlantic Ocean and western Indian Ocean.
Researchers at Rensselaer Polytechnic Institute developed a model to predict cryptocurrency scams using Benford's Law and found that scam addresses deviated from the law. They also advocated for robust blockchain interoperability to provide stability in decentralized systems.
A research team developed a method to efficiently identify potentially dangerous intersections for child traffic accidents using a combination of empirical Bayesian estimation and geo-informatized data. The model proved effective in identifying seven or more high-risk spots, improving upon methods based solely on past accident data.
A study published in Diabetes Research and Clinical Practice found that women with diabetes mellitus are at a higher risk of venous thromboembolism (VTE) than men, particularly during perimenopause. The risk is 1.52 times higher for women with DM compared to those without DM.
Researchers from Complexity Science Hub and Medical University of Vienna found that high doses of cholesterol-lowering statins impair bone quality in mice, with a significant increase in osteoporosis risk. The study confirms previous findings on the correlation between statin use and osteoporosis diagnosis in humans.
The EU project CRAFT-OA aims to strengthen institutional publishing using Diamond Open Access model across Europe. The project will enable local platforms and service providers to expand their content services with the aim of networking them with other information systems in science.
A new space-time coding antenna developed at City University of Hong Kong enables manipulation of beam direction, frequency, and amplitude for improved user flexibility in 6G wireless communications. The antenna relies on software control and combines research advances in leaky-wave antennas and space-time coding techniques.
The Wuhan University research team has developed a powerful model called FingerDTA, which uses convolutional neural networks to predict drug-target binding affinity. This can help identify potential novel drug candidates and reduce costs and time in traditional drug discovery methods.
A new study proposes a scalable, bottom-up approach to developing energy-saving initiatives at the individual level by analyzing real-time energy usage data. The research team developed an energy calculator that can be scaled up to the building- and community-level, enabling more accurate occupant-level measurements.
A novel cloud-based framework is proposed to manage and analyze industrial IoT data in cloud environments, optimizing energy consumption through reinforcement learning. The system aims to provide an energy-efficient and secure environment for industries such as healthcare and education.
A new CNN framework, PE-Net, is proposed for predicting machine remaining useful life (RUL) accurately. The framework uses a novel architecture with small-sized one-dimensional convolution kernels and deep networks to learn features from input time series signals.
A perspective paper explores the role of clinician-data-scientists in healthcare, emphasizing their need for interdisciplinary knowledge and training. The researchers highlight the importance of integrating data science into conventional medical education to prepare clinicians for the digital health era.
The Earth System Grid Federation is upgrading its climate projection data system to improve access and curation, with the goal of enabling scientists to make the best guess about the future trajectory of our climate. The new system will provide faster download speeds and enable previously infeasible data analyses.
Researchers developed a mathematical model to analyze cognitive changes and impairment in the brain, applicable to multiple sclerosis and other neurodegenerative diseases. The model uses multilayer networks for comprehensive analysis of CT scans, X-rays, ultrasound, and magnetic resonance imaging data.
The Center for BrainHealth has launched three research projects to develop objective metrics of improved brain systems in response to interventions. These projects aim to determine the changes in the brain's physiology, structure, and function linked to gains in comprehensive psycho-social measurements over time.
Healthcare researchers caution against misusing AI algorithms in clinical research, highlighting concerns about bias, transparency, and data quality. The team advocates for evaluating ML methods against traditional statistical approaches and ensuring clinician decision-making is complemented, not replaced.
Machine learning helps researchers discover how bacterial populations adapt to environmental diversity by analyzing growth curves. The analysis reveals distinct decision-making components for lag, growth, and saturation phases, protecting the population from extinction.
The article discusses new guidelines for big data research, including the potential for group harm. It also explores biobank research from an African American community's perspective and the implementation of electronic consent procedures during the COVID-19 pandemic.
A new platform called MoveApps enables scientists and wildlife managers to explore animal movement data with little more than a device and a browser. The system uses open-source code and allows users to create complex analyses with simple clicks.
A Southwest Research Institute team has developed a machine learning tool to label large, complex datasets efficiently. The iterative labeling technique reduces manual verification time by 50%, enabling deep learning models to identify potentially hazardous solar events more accurately.
CU Cancer Center member Ryan Layer developed a method to scan thousands of DNA samples using big data, identifying common benign mutations. This approach helps reduce false negatives in detecting complex DNA mutations associated with cancers.
The article discusses how big data can improve non-communicable disease (NCD) surveillance by providing real-time information and reducing costs. This new approach uses electronic health records, national administrative data, and other datasets to track NCDs more effectively.
Researchers at Cedars-Sinai Cancer have identified a novel immune checkpoint pathway that could lead to better understanding and treatment of hepatocellular carcinoma. The study suggests that blocking this pathway, combined with immunotherapy, may provide a new therapeutic strategy for liver cancer.
A new training program at MUSC and Clemson University aims to make future data scientists aware of health inequities, particularly in rural communities. The SC BIDS4HEALTH program will build on existing relationships with HBCUs and community groups across the state.
Researchers used game theory to create models of cooperative and competitive behaviors in multi-agent systems, focusing on distributed online optimization, federated optimization, and static/dynamic games. The findings have potential applications in smart cities, market competition, information security, and drug development.
Researchers have used a data-sharing innovation to categorise 16 uncertain BRCA variants as benign or likely benign, potentially allowing women with these variants to skip invasive surgeries. This could lead to thousands of people avoiding difficult treatments for no reason.
The Taylor Geospatial Institute brings together eight leading research institutions to collaborate on geospatial technology research and development. The Institute aims to accelerate St. Louis' position as the global center of geospatial innovation, with a focus on key areas such as food security, geospatial health, and national security.
A new study developed by Jenna Krall predicts air pollution model performance in health studies, improving their accuracy. The approach helps determine whether air pollution prediction models can be used in epidemiologic studies, assessing health effects.
A new Stanford University-led study uses machine learning and human insights to map regions and ports most at risk for illicit practices, like forced labor or illegal catch. The results highlight two main risk factors: the vessel's flag state and type of fishing gear onboard.
Researchers used big data and computer modeling to map contributions of women and men to history developments between 1950-2015. The study found that demographic diversity results in new knowledge, and newcomers launch new areas of research.
A new framework for portfolio management uses deep reinforcement learning to predict price trends and make strategic decisions, overcoming limitations of existing systems. The system consists of evolving agent modules and strategic agent modules, allowing for modular design and scalability.
Glenn Stone's analysis reveals how precision agriculture tools, such as detailed soil mapping and autonomous vehicles, can erode peasants' ability to self-manage their communities. Small farmers may face a paradigm shift in lifestyle and subsistence, with increased dependencies on external commercial services.
A study published in Ibis used machine learning to predict population trends of 801 bird species worldwide, estimating nearly half are declining. Fragmented populations, particularly non-migratory birds in tropical forests, were found to be the top predictor of population declines globally.
Researchers from the University of Oxford's Big Data Institute have created a single genealogy tracing the ancestry of all humans, combining genome sequences from eight databases and 3,609 individual genomes. The study successfully recaptured key events in human evolutionary history, including migration out of Africa.
The University of Texas at El Paso establishes a new Systems Modeling and Simulation concentration, enhancing students' skills in data analytics, computer simulation, and machine learning. The program aims to train students for innovative industries with rapidly changing environments.
A UCI team uncovered key brain mechanisms by which the hippocampus organizes memories into sequences, enabling decision-making. The finding may help understand memory failures in Alzheimer's disease and other forms of dementia.
A team of scientists has developed a pioneering approach to combine advances in computer vision with ecological expertise to analyze wildlife populations. By leveraging AI and machine learning algorithms, researchers can extract key features from images and videos to quickly classify species, count individuals, and track behavior.
Researchers from the Complexity Science Hub Vienna propose that homophily, or interacting with like-minded individuals, automatically leads to social balance and stability. They demonstrate this using data from the Massive Multiplayer Online Game Pardus, where players tend to form friendships with those who share similar characteristics.
Researchers have identified a new highly virulent HIV variant in the Netherlands, known as VB variant, which shows significant differences in immune system recovery and survival compared to other variants. Early diagnosis and treatment are crucial to prevent damage from this more rapid decline in immune strength.
Researchers from UOC-led OptimalSharing@SmartCities project will analyze inhabitants' mobility patterns and demands to design more efficient shared transport practices. The project aims to develop agile optimization algorithms capable of processing large volumes of data in real-time for dynamic system coordination.
A new study by Universidad Carlos III de Madrid researchers has detected a significant digital gap in internet usage between rich and poor people, with poorer areas consuming more social media and traditional news outlets. The study found that higher levels of education and purchasing power are associated with more traditional online m...
The OneZoom tree of life is an interactive visualization that connects over 2.2 million living species, showcasing their evolutionary history and threat status. The platform also features images of over 85,000 species and allows users to explore their relationships with others.
Researchers from Harvard University and others have found that large-scale COVID-19 vaccination surveys were off by up to 17 percentage points due to systematic biases in the data. The 'Big Data Paradox' highlights how big data sets can minimize one type of error while magnifying another, leading to misleading results.
A research team developed an AI framework that analyzes protein interactions to predict effective and low-toxicity cancer drug combinations. The framework, GraphSynergy, outperforms conventional models in identifying synergistic combinations.
The human brain contains trillions of contact points, requiring massive computational resources. Researchers outline the need for exascale computing power to tackle brain complexity.
CanDIG, a collaboration of computer scientists, AI specialists, clinicians, and geneticists, enables studies needed to address health challenges in Canada. The platform is helping scientists access large-scale genomics data and connect Canada's genomic datasets to those from around the world.
A research team found that combining human and AI predictions yields more accurate results, especially in atypical cases with unknown factors. Human analysis can fill gaps in big data, leading to better collective predictions.
Machine learning enables better understanding of climate-induced hazards, predicting floods and landslides with high accuracy. The technology combines diverse data sources to assess risk extent, considering both triggering hazards and socio-economic vulnerability.
Rice University computer scientists have discovered an inexpensive way to implement rigorous personal data privacy in large databases for machine learning. Using locality sensitive hashing, their RACE method creates small summaries of enormous databases while scaling for high-dimensional data.
Researchers from academia and industry will converge at Lehigh University to discuss innovative solutions for optimizing efficiency and resiliency in the global supply chain. The workshop aims to leverage machine learning for prescriptive analytics, enabling proactive optimization of supply chain operations.
More deprived areas of England are less likely to have publicly available defibrillators, according to new analysis. This disparity disproportionately affects communities at greatest risk of cardiac arrest, highlighting an unacceptable health inequality.
Researchers at University of Maryland School of Medicine's Institute of Human Virology will use the grant to collect and analyze COVID-19 and HIV data from Nigeria and South Africa. The INFORM Africa project aims to provide new insights into virus mobility and impact, enabling governments to better respond to pandemics.
Researchers at NJIT, USC, and Harvard are developing a new software called StreamWare to analyze multiple sources of live data. The team plans to test new combinations of algorithms and hardware accelerators on various data sets, aiming to demonstrate prototypes in 3-6 months.
A study found that search engines like Yandex and Google often display inaccurate information about health treatments, including false claims about remedy effectiveness. The researchers argue that clearer warnings about possible health risks are needed for medical queries.
The study found that advances in iron metallurgy, horse riding, and agricultural productivity played a significant role in the development of military machines. Mega-empires emerged as societies supporting tens of millions of inhabitants and covering vast territories.
Researcher Jennifer Hurley is using in-vivo experimentation and big data analytics to identify environmental cues that tune the circadian clock's control over metabolism. Her study aims to find genes responsive to environmental signals, such as nutrients, to understand how environment affects sleep-wake cycle.
A Texas A&M team led by Dr. Byung-Jun Yoon has received $2.4 million to develop new computational techniques for reducing the size of large scientific data sets. The goal is to preserve quantities of interest while minimizing data storage and processing needs.