New data-driven model predicts shear behavior of grouped studs in composite bridges
Researchers built explicit equations from 249 push-out tests that predict the full nonlinear shear force–slip behavior of grouped stud connectors ...
Tag: Machine Learning
New AI Model Scales Up Learning for Knowledge Graphs Full of Unseen Entities
A new contrastive learning framework called VMCL improves knowledge graph embedding for unseen entities and shows smooth, predictable gains as ...
Accelerated biological ageing flags chronic disease and mortality risk in US adults
A study of 7,624 US adults links accelerated phenotypic ageing, calculated from nine blood biomarkers, to chronic disease burden and ...
Sugarcane ash and limestone sludge yield stronger, greener concrete predicted by AI
Researchers combined sugarcane bagasse ash, lime sludge ash and polypropylene fibres to make stronger, less permeable concrete, and trained a ...
Lightweight AI Intrusion Detection System Targets IoT and Medical Device Threats
Researchers report a lightweight, imbalance-aware intrusion detection system achieving up to 0.9998 accuracy on IoT and medical IoT benchmark datasets.
Neural Network Spots Nanosatellite Power Faults in Simulation With 100 Percent Accuracy
A simulation-only proof of concept shows a compact residual-based neural system can distinguish severe faults across a nanosatellite electrical power ...
Sepsis Research Pushes Toward Predictive AI, Molecular Subtypes and Hydrogen Therapy
A new editorial in Anesthesiology and Perioperative Science maps how machine-learning risk models, immunometabolic targets and molecular hydrogen are reshaping ...
Graph neural networks shape propagation differently, large comparison study finds
A controlled comparison of ten graph neural network architectures finds that PNA, GAT, GCN, and EvolveGCN produce embedding spaces associated ...
Fine-tuned AI model flags early autism from children’s medical records in Chinese study
A multicenter Chinese study found that a fine-tuned large language model identified autism spectrum disorder in young children from electronic ...
Computational study links tire rubber antioxidant 6PPD to lung cancer molecular pathways
A computational study predicts that the tire antioxidant 6PPD may bind multiple lung-cancer-related proteins and nominates three diagnostic gene biomarkers.
MRI histogram analysis outperforms habitat modelling for predicting 1p/19q codeletion in gliomas
A retrospective analysis of 122 patients with IDH-mutant gliomas found that whole-region histogram features moderately predicted 1p/19q codeletion, while adding ...
Portland State virologists win $1 million NSF grant to trace crucivirus evolution
A three-year, $1 million National Science Foundation grant will fund Portland State University's eXtreme Virus Lab in its targeted search ...
Binary ‘Skeletal Failure’ Rule Proposed to Make AI Vertebral Fracture Screening Trustworthy
A new invited review proposes a binary
Simulated poultry antibiotic residue data test a machine-learning pipeline for Salmonella resistance analysis
A new proof-of-concept study used entirely synthetic data to test whether machine learning can recover a predefined link between poultry ...
Big Data Health Science Conference Gathers Global Cohort to Bridge Discovery and Delivery
The 7th National Big Data Health Science Conference in Columbia, South Carolina, drew more than 200 participants from 17 states ...
Machine learning predicts strength of nanoparticle-modified basalt fiber composites
Eight machine learning models trained on published experimental data predict the tensile and flexural strength of nanoparticle-modified basalt fiber reinforced ...
Machine learning sorts Guillain-Barré syndrome subtypes from nerve conduction data
Interpretable machine-learning models trained on acute-phase nerve conduction data from 99 Korean patients showed preliminary ability to reproduce expert-assigned Guillain-Barré ...
Bayesian Framework Merges Clinical Expertise With Machine Learning Diagnosis
A new Bayesian framework called PIML combines machine learning analysis of electrical impedance signals with clinical prior knowledge, improving diagnostic ...
Multi-paradigm EEG signals and AI enable reliable biometric authentication
A multi-paradigm EEG protocol combined with machine learning achieved a 1.6 percent equal error rate in cross-session biometric authentication.
Parkinson’s Disease Raises Fracture Risk, and Osteoporosis Care Must Keep Up
A new perspective article argues that osteoporosis prevention deserves far more attention in people with Parkinson's disease, especially when dementia ...
POPULAR NEWS
-
Perceptually Guided Optimization Cuts Computational Costs for Personalized Spatial Audio Models
-
Combined Aerobic and Strength Exercise Reduces Geriatric Depression in Controlled Trial
-
Miniature Pig Kidney Atlas Reveals Developmental Dynamics and Key Regulator
-
Genetic study reveals multiple invasion paths for invasive snail in Brazil