Tag: Machine Learning

A new review argues that stable isotope fractionation patterns, long used to reconstruct Earth's history, could become mechanistic biomarkers for ...

A hybrid deep learning framework combining two complementary LSTM models with Bayesian ensemble stacking predicts winter road surface temperature more ...

A pilot machine learning study of 20 mother-child dyads found that maternal lactation nutrients such as phosphatidylcholine, glutathione, and glycemic ...

A multicenter Chinese study of 3,148 Parkinson's disease patients developed and validated interpretable survival prediction models and deployed the best-performing ...

A two-center study trained a deep learning radiomics model on routine breast ultrasound images to predict sentinel lymph node metastasis ...

Researchers have built an AI-powered traffic control system that uses cameras, infrared and sound sensors with lightweight neural networks to ...

A Houston study of nearly 8,000 pediatric appointments found that while social risk data did not improve AI no-show prediction, ...

Researchers have developed an iterative residual correction method that uses new soil profile data to significantly improve the accuracy and ...

A multi-omics study of 67 Parkinson's disease patients and 64 controls reveals microbial-driven lipid and amino acid pathways, with gut-derived ...

Using SHAP, ALE, and LIME explainable AI techniques on daily data from 2008 to 2025, researchers show that oil market ...

Researchers used automated machine learning and cluster analysis of Nigeria Malaria Indicator Survey data to predict malaria risk in minors ...

A four-month campaign at Finland's SMEAR II station used machine learning to screen hundreds of environmental variables against ice-nucleating particle ...

A multi-agent reinforcement learning framework schedules tasks across a 2000-node big data cluster with 92.4 percent success and millisecond-scale latency, ...

A new neural-physical framework called NeuPlume reconstructs complete three-dimensional greenhouse gas plumes and emission rates from sparse drone measurements, outperforming ...

A machine learning analysis of over 6,000 power plants shows that identical emissions can be visible or invisible to satellites ...

Researchers have introduced DACD, a dynamic adaptive learning method that detects concept drift in streaming data with a window-based CUSUM ...

Researchers have developed an evidential deep learning framework that detects stroke with near-perfect accuracy while quantifying its own uncertainty in ...

A new lightweight deep learning framework called LCASP-MMANet achieves state-of-the-art sign language recognition accuracy while remaining efficient enough for real-world, ...

A scoping review of 19 studies finds that multimodal AI fusing raw images with non-image data in mental and cognitive ...

Researchers used a consumer tablet app to capture facial blendshape features that objectively quantify Parkinson's hypomimia, revealing asymmetry and interaction ...