AI Learns to Explain Itself: Graph Networks Map the Hidden Social Wealth of Migrant Workers
A new study combines graph neural networks with explainable AI to map how Laotian migrant workers in Bangkok build and ...
Tag: SHAP
AI Model Predicts Survival After Surgery for Gastrointestinal Stromal Tumors
Researchers built an explainable random survival forest model that predicts overall and cancer-specific survival in postoperative gastrointestinal stromal tumor patients, ...
Machine Learning Rewrites the Rules for Judging How Buildings Survive Earthquakes
Researchers have developed a machine learning framework that uses an experimental database of 236 cyclically tested beam-column connections to identify ...
AI Reads Ultrasound Signals to Predict Which Carotid Plaques May Trigger Stroke
A prospective study shows that a random forest model combining shear wave elastography, contrast-enhanced ultrasound and clinical factors can predict ...
Machine Learning Cracks the Code of Ultra-Green Concrete Strength
Researchers trained six machine learning models on 2,048 laboratory records and found gradient boosting predicts the compressive strength of cement-free ...
Decade of Data: How Explainable AI Is Cracking Open the Black Box of Crash Severity Prediction
A systematic review of 237 studies from 2014 to 2024 maps how explainable AI techniques such as SHAP and LIME ...
Lightweight AI Spots Grapevine Virus From Drone Hyperspectral Images
A lightweight vision transformer trained on drone hyperspectral imagery detected grapevine red blotch virus across Napa Valley vineyards with 75 ...
Machine Learning Forecasts Reservoir Water Well but Misses Silent Sediment Loss
A comparative study of Taiwan's Mingde and Shihmen reservoirs shows machine learning models forecast monthly storage with high skill but ...
Machine Learning Reveals How Warming Penetrates Frozen Soils of Northeast China
A new interpretable machine learning study shows that warming in Northeast China's frozen soils decreases with depth, with longwave radiation, ...
AI Reads Ancient Granite Chemistry to Reconstruct Earth’s Tectonic Past
A machine learning framework trained on more than 13,000 granite samples classifies tectonic settings with 91 percent accuracy while SHAP ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!