Resistance-Based Features Boost Machine Learning Fault Detection in Power Grids
A hybrid framework that turns voltage and current measurements into resistance-based statistical features enabled Random Forest to classify electrical faults ...
Tag: Machine Learning
Machine Learning Maps Soil Salinity at Depth—and Shows Where Predictions Falter
A study in Shandong Province, China, used quantile regression forests to map soil salinity across five depth intervals down to ...
Machine learning maps how neighborhoods, activity, and mental health intertwine in aging
A systematic review of 27 studies finds machine learning is transforming research on living environments, activity, and mental health in ...
Why Almost No Machine Learning Models Ever Reach the Hospital Bedside
An editorial in Frontiers in Medicine argues that the vast majority of clinical machine-learning models never reach patients, with fewer ...
Topology-guided AI reads gut microbe networks to classify type 2 diabetes across populations
A dual-stream graph attention network trained on conserved gut microbial network structures achieved an ROC-AUC of 0.9223 for type 2 ...
Telepharmacy Data Reveal Hidden Minority of Psoriasis Patients With Persistent Quality-of-Life Burden
A Spanish telepharmacy study found that average quality-of-life improvement in psoriasis concealed a persistently impaired minority, and that a single ...
Physics-regularized neural networks learn collective motion from trajectory data
A Physics-Regularized Graph Neural Network learns collective motion dynamics from trajectory data, achieving lower closed-loop position errors than five baselines ...
Quantum Annealing Meets PCA to Sharpen Carbon Emissions Predictions
A hybrid framework combining quantum-annealing-based feature selection with PCA reduced carbon-emissions prediction errors by 4 to 7 percent compared with ...
Interpretable Linear Model Predicts Concrete Strength with 0.805 Cross-Validated R2
A new Scientific Reports study presents an interpretable enhanced linear regression model that predicts concrete compressive strength with a nested ...
AI pinpoints and explains smart contract flaws at function level
Researchers at JAIST built a graph neural network and explanation framework that locates smart contract vulnerabilities at the individual function ...
AI Scoring of Immune Cells in Breast Cancer Tissue Is Booming, but Almost No Model Is Ready for the Clinic
A systematic review of 51 studies finds that machine learning assessment of tumor-infiltrating lymphocytes in breast cancer histopathology is technically ...
Computational drug screening struggles against drug-resistant tuberculosis, review finds
A new review argues that virtual screening and AI-driven modeling have expanded the search for anti-tuberculosis drugs, but persistent mismatches ...
Gastric Cancer’s Public Data Boom Produces Gene Lists, Not Clinical Answers, Review Warns
A sweeping methodological review published in Frontiers in Oncology argues that the explosion of public-omics research in gastric cancer has ...
Why Public Health Leaders Must Own AI Risk Decisions Now
Artificial intelligence is no longer a distant prospect for public health agencies; it is already reshaping how officials detect outbreaks, ...
Curated hydrogen database links storage capacity to release pressure
A Tohoku University-led team built a curated database of more than 30,000 hydrogen storage data entries and used interpretable AI ...
MRI Radiomics Plus Clinical Features Sharpen Prediction of Bladder Cancer Muscle Invasion
A combined MRI radiomics and clinical nomogram achieved an area under the curve of 0.897 in temporal validation for predicting ...
AI and Nondestructive Sensing Could Bring Flavor Into Legume Breeding at Scale
A review proposes a framework for using AI and nondestructive sensing to screen sensory-related traits across large legume breeding populations, ...
Blood Protein Panel Flags Early Esophageal Cancer with High Accuracy in Chinese Case-Control Study
A machine-learning model based on six serum proteins diagnosed esophageal squamous cell carcinoma with AUCs of 0.932 and 0.968 in ...
Which Amino Acids Track With Elevated Fasting Glucose in Chinese Children?
A cross-sectional analysis of 6,960 children and adolescents in four Chinese provinces links higher dietary methionine and threonine shares with ...
Open-data machine learning framework reaches near-perfect breast cancer diagnosis on benchmark dataset
A reproducible open-data framework using the Wisconsin Diagnostic Breast Cancer dataset achieved near-ceiling discrimination for malignant-versus-benign classification while doubling as ...
