AI Model Spots Microscopic Fabric Defects With 98 Percent Accuracy
Researchers report an AI model combining CNN feature extraction and a spiking neural network that classifies microscopic fabric defects with ...
Tag: Machine Learning
Neural Network Learns Earthquake Response by Tuning Itself to a Building’s Natural Frequencies
A new physics-informed neural network embeds a structure's natural frequencies into its architecture, cutting seismic response prediction errors below 2 ...
Hybrid AI Spots Seizures in Brain Recordings With Near-Perfect Accuracy
A hybrid vision transformer-CNN model detected epileptic seizures in pediatric EEG recordings with 99.8 percent average sensitivity while quantitatively explaining ...
Hybrid Deep Learning Model Detects Intrusions in Wireless Sensor Networks
A new framework combining reinforcement learning and Siamese convolutional networks with blockchain-secured routing reports over 92 percent accuracy in detecting ...
Capsule Networks Push Antimicrobial Peptide Prediction Past 97 Percent Accuracy
A capsule neural network model called AMP-CapsNet achieved 97.29 percent test accuracy in classifying antimicrobial peptides when using dipeptide composition ...
Particle Swarm Optimization Steers Client Selection in Decentralized Federated Learning
A new decentralized federated learning framework uses particle swarm optimization to dynamically select clients, reporting 76.2% accuracy on CIFAR-10 under ...
Smart Neural Network Steers Dual-Input Converter for Electric Vehicles
A 500 W laboratory prototype of a dual-input converter with a modified deep neural network controller achieved a peak efficiency ...
Machine Learning Maps Three Fatigue Subgroups in Breast Cancer Patients
A cross-sectional study of 1,005 breast cancer patients identified three fatigue subgroups and found perceived stress, depression, and self-compassion were ...
Better AI Molecular Models Need Many Short Simulations, Not One Long Run
A new commentary argues that AI models trained on molecular dynamics data are more reliable when built from multiple short, ...
Ultrafast Raman Imaging Speeds Toward Label-Free Head and Neck Cancer Histopathology
A pilot study combined broadband coherent Raman imaging of head and neck cancer tissue from five patients with a high-speed ...
Imaging, Genes and Proteins Combine to Predict Liver and Pancreas Disease Risk
A UK Biobank study of 38,844 participants shows that integrating MRI-derived liver and pancreas traits with genetic variants and proteomic ...
Inflammatory blood markers sharpen machine learning detection of mild frailty
A study of older adults in the GAINS cohort found higher IL-2 levels in mild frailty and showed inflammatory markers ...
Graph Neural Networks Map How Campus Waterfront Spaces Move and Hold Their Visitors
Wi-Fi probes and graph neural networks at two Chinese university campuses show that pedestrian movement along waterfront spaces is far ...
Machine Learning Surrogates Predict Wing Aerodynamics and Stress in Seconds
Researchers built regressor chain surrogate models that predict pressure and stress fields across varied wing planforms with modest prediction errors ...
DeBERTa-v3 and Aspect Attention Decode Mixed Sentiment in Amazon Reviews
A dual-track AI framework reads Amazon reviews with DeBERTa-v3 encoders and aspect-specific attention, assigning sentiment to product, delivery, and service ...
Synthetic Brain Scans Bridged Between Sites Sharpen Brain Age Prediction
Researchers have developed an interpolation-based method that generates synthetic MRI training data between age- and gender-matched participants from different scanners, ...
AI Model Predicts Concrete Strength With Near-Perfect Accuracy Using Metaheuristic Optimization
A new study reports that hybrid broad learning systems optimized by parameter-free metaheuristics predict concrete compressive strength with MAPE below ...
Machine learning and water quality indices reveal monsoon pollution hotspots in Odisha’s Baitarani River
A twelve-year study of Odisha's Baitarani River combined water quality indices, multivariate statistics and machine learning to identify monsoon-season pollution ...
Machine Learning Forecasts Rock Fracture Minutes Ahead in Lab Experiments
A random forest model trained on acoustic emission signals from granite hydraulic fracturing experiments forecast specimen failure up to 1800 ...
Phase Separation Is an Evolvable Trait, Argues New Evolutionary Framework
A new perspective argues that liquid–liquid phase separation should be studied as an evolvable molecular phenotype shaped by natural selection.
POPULAR NEWS
-
Vaping adults without smoking history report slightly more respiratory symptoms, large survey finds
-
AI Advances in Upper Limb Prosthetics Reviewed
-
Papain Pre-Digestion Unlocks Potent Bioactive Peptides From Snapper Salmon Skin Collagen
-
Deep Learning Model Accelerates Drug Target Screening and Repurposing Opportunities