Articles tagged with Network Modeling
Researchers will use airborne GPR and ground-based TEM to collect rich geophysical data, estimating carbon storage and gas emissions in peatlands across a latitudinal gradient. The project aims to reduce uncertainty in these predictions and provide valuable information on how to better protect carbon stocks.
The 3D lung model can replicate realistic breathing maneuvers and offer personalized evaluation of aerosol therapeutics under various breathing conditions. The researchers detail in the paper how they built the 3D structure and what they’ve learned so far.
Research advances higher-order networks to capture multi-agent interactions, enabling accurate modeling of biological, social, and physical systems. The Dirac-Bianconi operator provides a powerful generalization of the graph Laplacian, encoding local and global interactions across different topological dimensions.
The open-source AI model analyzes medical images, generates detailed reports, and answers clinical questions to streamline diagnostics and improve accuracy. BiomedGPT aims to democratize healthcare and reduce disparities amongst patients by providing easily accessible data to bolster underserved hospitals.
A new study by University of Toronto researchers has developed a model that can help municipalities choose optimal locations for bike lanes, minimizing congestion and increasing cycling ridership. The model uses traffic and commuter mobility data to predict the impact of bike lane expansion on driving travel time and emissions.
Researchers developed a system to detect and decode fiducial markers in challenging lighting conditions using neural networks. The system, DeepArUco++, overcomes the limitations of classic machine vision techniques and can be applied today thanks to open availability of its code.
Researchers propose a new strategy to stabilize quantum networks by rebuilding connections after each use, which leads to an eventual stable network state. The key is finding the optimal number of links to add, determined to be the square root of the number of users.
A new hybrid machine learning model predicts ultimate axial strength of CFRP-strengthened CFST columns with high accuracy, enabling safer and more efficient designs. The model can be used to optimize construction processes and enhance the safety of structures at a lower cost.
A new study led by University of Oxford suggests that plants are more likely to be eavesdroppers than altruists when tapping into underground networks. The study found that it is unlikely that plants would evolve to warn other plants of impending attacks, instead finding that plants may signal dishonestly to harm their neighbors.
The new model, based on a PV-RNN framework, achieves compositionality by combining language with vision, proprioception, working memory, and attention. It requires less computing power than large language models (LLMs) and makes mistakes similar to humans.
The study utilizes infrared spectroscopy and a machine-learned protocol to map spectroscopic fingerprints to atomistic structures. The authors demonstrate the accuracy of their network in predicting local atomistic structures and energetic variations, enabling the tracking of dynamic C–C coupling on Cu surfaces.
A new computational model reveals how place cells in the hippocampus can store episodic memories, including those of events without a spatial component. The model proposes that grid cells form a scaffold that anchors memories and drives recall by connecting to sensory cortex.
Researchers developed an explainable deep learning model to predict and analyze HABs in Chinese lakes and reservoirs, achieving significant improvement over conventional machine learning methods. The model identified water temperature as the most influential factor driving algal bloom dynamics.
Mayo Clinic is developing foundation models with Microsoft Research and Cerebras Systems to personalize patient care, accelerating diagnostic time and improving accuracy. These multimodal models integrate radiology images and genomic sequencing data to transform clinical diagnosis and treatment.
Researchers at UVA have developed computer models to target specific bacteria in specific parts of the body, reducing the chance of antibiotic resistance. This approach could lead to more effective treatments and reduce the need for broad-spectrum antibiotics.
Researchers developed a cutting-edge method leveraging Graph Neural Networks (GNNs) to predict mesozooplankton community dynamics and visualize their interactions. The study achieved remarkable improvements in forecasting accuracy by integrating inter-series relationships and temporal dependencies among input-variables.
Researchers developed a predictive tool using the Florey Dementia Index to forecast onset ages of mild cognitive impairment and Alzheimer's. The validated tool may help prioritize patients for disease-modifying treatments.
A new study published in Nature Medicine shows that AI-based models can accurately identify ovarian cancer in ultrasound images, achieving an accuracy rate of 86.3%. The models also reduce the need for expert referrals and misdiagnosis rates by 63% and 18%, respectively.
A study published in Chinese Medical Journal explores the use of artificial intelligence to identify potential medications for treating glaucoma. Researchers used AI models to predict the effectiveness of small-molecule compounds targeting RIPK3, a key signaling molecule involved in programmed cell death.
A recent study demonstrates how DNNs can predict fragrance profiles from essential oil chemical compositions, validating sensory evaluations. The model achieved high accuracy in predicting floral scents and showed promise for generating new and unique combinations.
Environmental heterogeneity consistently increases pathogen virulence and infectivity. Modest variations in local conditions can lead to up to 40% higher evolved virulence compared to homogeneous metapopulations.
Researchers developed a new benchmark for health care using reinforcement learning, which shows promise in managing chronic or psychiatric diseases. However, current methods are data-hungry and fail to perform accurately when tested on real-world data.
A new framework evaluates tsunami risk to seaports and the global port network, estimating potential economic losses in trade caused by port disruptions. The study found that a Manila Trench tsunami could damage up to 15 international seaports under present-day sea-level conditions.
A new AI framework, ADAI, improves adaptability of distributed sensor systems by leveraging unlabeled data from each target region. The framework remodels the 'brain' of DSS to handle regional variations, achieving accuracy increases and low false alarm rates.
Researchers at Pusan National University developed a hybrid model to predict metal wear in magnesium alloys, enabling safer, lighter designs. The model combines machine learning and physics to improve fatigue life prediction, offering greater predictive reliability for enhanced safety and longevity.
Researchers identified critical trains that significantly transfer delays to subsequent services, known as 'influencer trains'. Adding new train services or replacing sharing rolling stock can reduce overall delays by up to 40%.
A new deep learning model enhances railroad condition monitoring by combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, achieving 97% accuracy in detecting train positions and conditions. The model's real-time processing capabilities enable swift intervention and mitigation of potential hazards.
Researchers developed a new tool called SigRM to analyze single-cell epitranscriptomics data, enabling the study of RNA modifications in individual cells. This can provide valuable insights into gene regulation and its impact on health and disease, particularly in complex conditions like cancer.
Researchers develop TriGuard, a tripartite evolutionary game model to counteract bribery in Delegated Proof-of-Stake blockchain systems, promoting fair participation and robust security.
A new model reveals that supply chain risks can amplify financial losses, with banks facing up to five times higher losses than traditional credit risk models. The study highlights the need for regulators to rethink systemic risk monitoring, focusing on firms with central roles in supply chains.
Scientists at MIT developed a fully integrated photonic processor that can perform all key computations of a deep neural network optically on the chip. The device completed machine-learning classification tasks in under half a nanosecond while achieving over 92% accuracy, similar to traditional hardware.
A new AI tool generates realistic satellite images of future flooding, which can help communities visualize and prepare for approaching storms. The method combines a generative artificial intelligence model with a physics-based flood model, producing more accurate and realistic images than an AI-only approach.
The National Center for Supercomputing Applications (NCSA) has received the Readers' Choice Award: Best HPC Collaboration and Editors' Choice: Best Use of HPC in Physical Sciences. This is the 14th consecutive year NCSA has been honored with an HPCwire award.
Researchers have trained AI models to distinguish brain tumors from healthy tissue using convolutional neural networks and transfer learning. The models achieved an average accuracy of 85.99% at detecting brain cancer, with the ability to generate images showing specific areas in its tumor-positive or negative classification.
Researchers have developed a deep-learning-powered metalens imaging system that overcomes limitations of traditional metalenses. The system pairs a mass-produced metalens with an image restoration framework driven by AI to achieve aberration-free, full-color images while maintaining compact form factor.
Researchers discovered that NMDA receptors set the baseline level for neural network activity, helping maintain stable brain function. The study's findings suggest potential innovative treatments for diseases linked to disrupted neural stability.
Researchers have developed a simple model system to break down fibrils into their constituent single units or liquid droplets. This discovery has the potential to treat neurodegenerative diseases such as Alzheimer's and Parkinson's by targeting pathological fibrils.
A new study published in JAMA Network Open found that using Chat GPT Plus does not significantly improve the accuracy of doctors' diagnoses, but it outperformed conventional methods in certain cases. The researchers suggest that physicians need more training and experience with AI to capitalize on its potential.
The study emphasizes the need for a coherent approach to understanding A.I. threats, recognizing the intricate interplay between technology and society. Experts propose involving laypeople and experts in risk assessment processes, as well as promoting social resilience to ensure better decision-making.
Researchers at the University of Kansas have developed atomically tunable memory resistors, dubbed 'memristors,' to enable brain-inspired advanced computing. The innovation enables precise atomic-scale tuning of oxide semiconductor memristors for high-speed and high-energy efficiency.
The American Heart Association has awarded $75,000 to local entrepreneurs to develop innovative solutions addressing health inequities in their communities. The EmPOWERED to Serve Business Accelerator program supports social entrepreneurs and organizations focused on improving health outcomes.
A full-scale in silico model of the rat hippocampal CA1 region has been developed, integrating diverse experimental data from synapse to network. This community-based approach overcomes challenges in integrating data from different experimental approaches.
A team of MIT engineers has developed a new computational method for analyzing complex biological systems, including the immune system's response to tuberculosis vaccination. The approach uses probabilistic graphical networks to identify key interactions and mechanisms, shedding light on how vaccines induce immunity.
Yihao Zheng and his team are developing a fiber-optic probe that analyzes artery blockages in the brain and guides procedures for blockage removal. The technology uses light and advanced calculations to determine the properties of blood clots, enabling doctors to make informed decisions about how to remove them.
Researchers developed an AI model that can identify and measure aggressive prostate cancer lesions with high accuracy. The model's estimates of tumor size were associated with the likelihood of cancer recurrence or metastasis.
A machine learning model predicts soil behavior during earthquakes, identifying areas vulnerable to liquefaction and providing contour maps for safer construction sites. The study uses geological data to create detailed 3D maps of soil layers, improving prediction accuracy by 20%.
A study of 50 U.S.-licensed physicians found that GPT-4 did not significantly improve clinical reasoning compared to conventional resources. The integration of GPT-4 as a diagnostic aid alongside clinicians showed promising results but required further exploration to understand its potential benefits.
Researchers developed an AI model that addresses uncertainties in renewable energy generation and electric vehicle demand, making power grids more reliable. The model uses multi-fidelity graph neural networks to optimize solutions within seconds, improving grid performance even under unpredictable conditions.
A team of University of Houston engineers developed an AI tool to predict and control pandemic spread by analyzing international air travel. The analysis found that reducing flights in Western Europe can lead to fewer global COVID-19 cases, making it a key strategy for controlling the pandemic.
Researchers at Newcastle University developed a novel approach using electromagnetic waves to solve partial differential equations, specifically the Helmholtz wave equation. The innovative structure, known as a metatronic network, effectively behaves like a grid of T-circuits and allows for control over PDE parameters.
Deep learning models used in remote sensing tasks are susceptible to various types of noise and attacks, compromising their performance. The study assesses the vulnerabilities of DL algorithms for object detection, revealing several weaknesses that can be leveraged by attackers.
A new study reveals that AI-driven chatbots may perpetuate racial and ethnic biases in pain assessment, leading to further inequalities in healthcare. Researchers found that Black patients were consistently underassessed for their pain compared to white patients, regardless of whether the rater was human or AI.
Researchers use machine learning to analyze optimal bike lane placement in Toronto, balancing accessibility for all with overall efficiency. Key findings include a trade-off between equity and utility, with essential routes like Bloor West's bike lanes serving neighbourhoods far from their endpoints.
Researchers emphasize the need for updating offshore turbine designs to reflect the complexity of storms. Advanced modeling techniques and data-driven models are being developed to address this issue.
Mayo Clinic scientists created mini brain models in a dish that closely match key features seen in the brains of patients with Lewy body dementia. The team identified four potential drug compounds that may offer approaches to treating the disease.
Researchers analyzed atmospheric mercury concentrations and found a 10% decline between 2005 and 2020, contrary to global inventories that indicate an increase. The study suggests that human activity-driven emissions are driving the trend, but limitations in data and scientific understanding remain.
The COVID-19 pandemic has provided researchers with an opportunity to explore the role of social connections in the spread of both disease and ideas. By analyzing data on human interaction networks, mathematician Nicholas Landry aims to understand how ideas are transmitted and how they can be tracked.
Recent advances in Brain Network Models (BNMs) have improved simulations of brain activities, understanding neuropathological mechanisms, and predicting disease progression. BNMs integrate structural and functional connectivity data to analyze abnormal network dynamics.
Researchers have discovered that small networks of neurons in the fruit fly's brain can generate an accurate internal compass, contrary to previous assumptions. This finding expands our knowledge of what small networks can do and challenges traditional views on brain size and function.
Researchers developed an AI-driven approach to model complex hand movements, overcoming current limitations in neuroscience and biomedical engineering. The model achieved a 100% success rate in controlling virtual Baoding balls, showcasing its strength in various challenging situations.