Machine learning forecasts bluetongue outbreaks up to six months ahead
A climate-informed machine-learning framework outperformed or matched 14 benchmarks while forecasting bluetongue outbreak risk across France, Greece and Italy.
Tag: Machine Learning
UVA’s Camille Bilodeau Named to AIChE 2026 35 Under 35
UVA assistant professor Camille Bilodeau was named to AIChE’s 2026 35 Under 35 class for developing computational tools that combine ...
BDNF markers linked to cognitive impairment in kidney disease
In a cross-sectional study of 240 patients with chronic kidney disease, higher serum BDNF levels and a BDNF-to-kidney-function ratio were ...
Technology adoption could reshape U.S. peak electricity demand by 2060
A U.S.-wide modeling study finds that heat-pump adoption could affect extreme peak electricity demand more than climate change in many ...
Wearable AI forecasts prolonged sitting in women with chronic pelvic pain
A peer-reviewed modeling study found that personalized AI using Fitbit data forecast prolonged sedentary periods one hour ahead in women ...
Few-shot adaptation improves minority-label Bangla hate speech detection
FewShot AdaptiveMLC raised macro-F1 by 0.072 on a multi-label Bangla hate speech dataset by fine-tuning task-specific heads for minority labels ...
Machine Learning Identifies Two Gene Markers of Allergic Rhinitis
A cross-algorithm analysis of public nasal-tissue data identified TNFSF14 and CD83 as a two-gene panel that distinguished allergic-rhinitis samples from ...
Reliability-calibrated contrastive learning improves plant leaf recognition
Prototype-reliability calibration improved plant leaf recognition across three benchmarks and a laboratory-to-field test while leaving the exported classifier architecture unchanged.
Machine Learning Shows Promise but Limited Clinical Validation in Keratoconus
A systematic review of 41 studies found that machine learning can classify keratoconus severity and estimate progression and surgical outcomes, ...
Reinforcement learning curbs drag in turbulent bluff-body wakes
A wind-tunnel reinforcement-learning system reduced drag and saved energy in a turbulent bluff-body wake, outperforming model-based baselines two to fourfold.
Coagulation-associated genes stratify acute myeloid leukemia and spotlight SPINT2
An integrated transcriptomic and laboratory study linked coagulation-associated gene activity to survival and immune states in acute myeloid leukemia, while ...
Integrating machine learning, density functional theory, and molecular dynamics for smart corrosion inhibitor design: a critical review
A critical review finds that integrating machine learning, quantum chemistry, molecular dynamics and experiments could accelerate corrosion-inhibitor design, but weak ...
Machine learning predicts severe lung disease risk in extremely preterm infants
A single-center retrospective study found that a calibrated random forest using respiratory monitoring, chest radiographs and perinatal data predicted severe ...
Driverless electric taxi fleets get smarter about uncertainty
A Chalmers University modelling study combined Bayesian forecasts with transparent optimisation to coordinate large self-driving electric taxi fleets under uncertain ...
Explainable AI prioritizes serum microRNAs for pancreatic cancer detection
A retrospective analysis of 1,101 serum samples used explainable artificial intelligence to prioritize circulating microRNAs that distinguished pancreatic cancer from ...
Machine learning estimates factory-worker stress from brain signals
An exploratory study of 20 participants linked EEG and fNIRS signals to self-reported anxiety-related stress, with the best model estimating ...
Machine Learning Finds Mixed Dietary Signals in Older Adults’ Predicted Skin Cancer
An interpretable machine-learning study of 3,729 older NHANES participants linked mixed dietary signals with predictions of prevalent, self-reported non-melanoma skin ...
Bayesian Network Matches Classifiers for IgE Sensitization Risk
A Bayesian network calibrated sensitization probabilities in 8,285 NHANES participants while matching logistic regression and random forest for discrimination, offering ...
Genomic resistance predictions need biological context, review finds
A 2026 mini-review finds that antimicrobial-resistance predictions become more reliable when gene presence is combined with expression, dosage, genomic context ...
Blockchain-backed IoHT framework reports over 99% accuracy on two attack datasets
A blockchain-integrated machine-learning framework reported accuracies above 99% for distinguishing attacks from normal activity in two IoHT healthcare-device datasets.
