Curriculum-guided AI framework boosts semi-supervised chest X-ray disease classification
The CARD framework reached a Macro-AUROC of 75.9% in semi-supervised chest X-ray disease classification, rising to 77.0% when pre-diagnostic clinical ...
Tag: Machine Learning
Multimodal AI system turns regional music into visual classroom cues
A new multimodal model called MusicFormer fuses audio, sheet music, lyrics and regional cultural labels to recognize regional music styles ...
AI Model Reads Chest Scans to Tell Fungal Infection and Tuberculosis Apart in HIV Patients
A retrospective Chinese study reports that a CT-based multimodal 2.5D deep learning model achieved an AUC of 0.931 and 0.981 ...
Hybrid AI model sharpens breast cancer survival prediction, UC study shows
University of Cincinnati Cancer Center researchers report that a hybrid statistical and deep learning survival model outperformed comparison models on ...
Visual Transformer Algorithm Scores Athletic Movement from Ordinary RGB Video
A Visual Transformer-based algorithm reported in Discover Artificial Intelligence assigns technical scores and grades to gymnastics, jumping, and racquet-sport movements ...
Predicting the incidence of type 2 diabetes using FINDRISC and machine learning approaches: evidence from a population-based cohort
In a population-based cohort of 8,859 adults followed for six years, component-level machine learning models showed higher observed AUCs than ...
Random-Forest Phasing Tool Nearly Doubles Contiguity of Diploid Genome Assemblies
The alignment-free phasing tool RFhap used multi-scale parental k-mers and a random forest classifier to nearly double corrected haplotype NG50 ...
AI Maps Glioma Ecosystems and Exposes a Macrophage-Driven Vulnerability in Glioblastoma
An AI-driven single-cell and spatial multi-omics study defines three glioma ecosystem states and shows that a hypoxic myeloid-mesenchymal state independently ...
Generative AI sharpens laryngeal lesion classification from radiomic features
A generative AI framework that augments radiomic features rather than images improved laryngeal lesion classification on NBI endoscopy data, with ...
Causal recommender untangles trust, drift and diversity in social suggestions
A new framework called CT-IDR combines recency-aware preference encoding, signed social influence propagation, and causal debiasing to improve both accuracy ...
AI Framework Designs Fly Ash Geopolymer Concrete Balancing Strength, Cost and CO2
A new study combines CTGAN-generated synthetic data, hybrid machine learning, SHAP explainability, reliability analysis and multi-objective optimization to design fly ...
Fuzzy Graph Neural Network Sorts Research Papers Using Uncertainty and Trust
Researchers have built a graph neural network that classifies scientific papers by combining intuitionistic fuzzy uncertainty, node-level Laplacian energy, and ...
Hybrid transformer framework detects DDoS attacks with high accuracy in benchmark tests
A hybrid framework called NEAT-ID combines evolutionary feature selection, attention-enhanced Transformers and wavelet-based temporal encoding to detect DDoS attacks with ...
Predictive Model for Nursing Home Dependency Loses Accuracy Outside VA Data
External validation of the Computational Barthel Index Tool in over 843,000 SEER-Medicare nursing home patients showed substantial performance loss that ...
Machine learning flags hidden anxiety in children with chronic abdominal pain
A stacking machine learning model integrating pain, school, psychosocial, and family variables identified comorbid anxiety disorder in children and adolescents ...
AI Meets the Blood Drop: Scientists Map the Rules for Merging Liquid Biopsy Data in Cancer Research
A new methods article outlines how artificial intelligence should be used to integrate liquid biopsy biomarkers in cancer research, finding ...
Machine Learning Model Cracks the Black Box of US News Mechanical Engineering Rankings
A Random Forest classifier predicts U.S. News mechanical engineering graduate program rank intervals with 0.91 test accuracy, revealing which measurable ...
Machine Learning Model Improves Kidney Function Estimates in Young People
A BMC Pediatrics study finds that a random forest model combining serum creatinine and cystatin C, further improved by adding ...
Diffusion Model Reclaims Lost Bits in High-Speed Analog-to-Digital Converters
A conditional diffusion model with physics-based constraints boosted effective resolution, SNDR, and spurious-free dynamic range in high-speed ADCs tested from ...
Facial Landmarks Let Autonomous Vehicles Read Driver States in Real Time
A calibration-driven facial landmark system aboard an autonomous electric shuttle distinguished five driver behavioral states with interpretable machine learning, reaching ...
POPULAR NEWS
-
How Parkinson Disease Genetics Is Guiding Precision Medicine and Targeted Therapies
-
Study Analyzes NBA Return Rates After Major Lower-Extremity Tendon Surgeries
-
Zinc Oxide Coating Enhances Wear and Corrosion Resistance of Titanium Alloy
-
Staggered Antibiotic Delivery Overcomes Bacterial Nutrient-Driven Tolerance in Lab Tests