Smart farming could pay off on half of global cropland
An international model estimates that smart-farming technologies are already profitable on 42% of global cropland and could pay off on ...
Tag: Machine Learning
Hybrid machine learning improves lost-circulation prediction in small oil-field dataset
A hybrid CatBoost pipeline using synthetic sampling and optimized class weights achieved the strongest reported classification results in a 258-record ...
AI could clarify molecular diversity in ovarian cancer liver metastases
A Mini Review finds that AI-assisted integration of genomic and spatial data may reveal lesion-specific biology in ovarian cancer liver ...
Blood inflammation index associated with poorer sleep in substance use disorders
A cross-sectional study found that the systemic inflammatory response index was associated with sleep disturbance in people with substance use ...
Raw PERG waveforms lead in four of six retinal disease classification tasks
An internally validated comparison of 672 pattern electroretinography recordings found that amplitude-preserving raw waveforms led in four of six retinal ...
Machine learning links immune-cell measures to resected lung cancer prognosis
A retrospective study of 165 surgically treated patients found that machine-learning analysis of whole-slide images linked CD8-positive immune-cell density, Foxp3-positive ...
Biomass feedstock variation shapes carbon material performance
A peer-reviewed review finds that differences in biomass composition and structure can shape the pore networks, chemistry, and performance of ...
Machine learning predicts liposome uniformity across 306 formulations
A study of 306 microfluidic liposome formulations found that gradient boosting predicted polydispersity better than one prior benchmark and identified ...
Neural network predicts mine ecological quality one year ahead
A staged neural-network framework predicted 2020 ecological-quality grades in a Chinese mine field with grade-specific accuracies of 87.3% to 94.1%.
Machine Learning and Multi-Omics Reveal Toxicity Signals in Adverse Reactions to a Traditional Chinese Medicine
A clinical study combining metabolomics, microbiome sequencing and machine learning identified molecular and microbial signatures that predict adverse reactions to ...
AI Recommenders Learn When Your Tastes Shift
A dual-stream AI recommender balances recent intentions with long-term preferences through a personalized gate that detects changing tastes.
AI Becomes the Design Engine Behind Terahertz Metamaterial Devices
A new review in PhotoniX Synergy details how machine learning, generative models, and large language models are transforming the design ...
Eight-Gene Blood Test Shows Striking Accuracy in Detecting Heart Attacks
Researchers used nested machine learning on public blood transcriptome data to derive an eight-gene index that diagnoses acute myocardial infarction ...
CT Scans May Predict Who Develops Leukopenia After Cervical Cancer Radiotherapy
For women with early-stage cervical cancer, surgery is often just the beginning of treatment. Many patients with stage IB to ...
Hand-crafted features beat raw sequences when battery protocols shift
Every lithium-ion cell in an electric vehicle carries a hidden countdown. Long before capacity visibly fades, subtle electrochemical fingerprints in ...
AI Model Flags Which Mild Stroke Patients Won’t Fully Recover After Clot-Busting Drugs
Researchers in China built an explainable XGBoost model using six routine admission variables to predict which mild stroke patients will ...
AI-Designed Molecules Show Promise as Host-Directed Antiviral Hits Against DHPS
Korea University researchers used benchmarked AI models to design small-molecule fragments that experimentally inhibited the human enzyme DHPS, a host ...
Core-Shell Nanoparticles and Smartphones Team Up to Catch E. coli in Minutes
Researchers have built a core-shell Ag@Au nanoparticle biosensor that pairs plasmonic sensing with smartphone-based machine learning to rapidly and selectively ...
Smart Ear Tags and Machine Learning Catch Calf Pneumonia Early, New Study Shows
Researchers combined ear tag, feeder, pedometer, and environmental data with random forest models to detect bovine respiratory disease in pre-weaned ...
Machine Learning Spots Broken Circuit Parts With 98.5% Accuracy
Researchers developed a two-stage random forest framework that classifies faults in Sallen–Key and Chebyshev analog filter circuits with about 98.5% ...
