GeoCluster Preprocessing Framework Achieves 88.87-Meter Accuracy in Sigfox Device Localization
A hybrid preprocessing framework called GeoCluster reduces feature space by over 80 percent and achieves an 88.87-meter mean geodesic error ...
Tag: feature importance
Hybrid Machine Learning Predicts Exercise Calorie Burn and Guides Personalized Training
Researchers paired supervised machine learning with rule-based reasoning to predict exercise energy expenditure and classify physical activity intensity from non-wearable ...
Tree Models Explain Intrusion Detection More Faithfully Than Deep Learning
A study evaluating XAI on live honeypot telemetry found that tree-based models provide more faithful explanations for intrusion detection than ...
Machine Learning Model Predicts Antimicrobial Peptide Synergy With High Test Accuracy
Supervised machine learning algorithms successfully predicted synergistic combinations between antimicrobial peptides and conventional antimicrobial agents using fractional inhibitory concentration data.
Machine Learning Pins Down Where Edible Seaweed Comes From
Combining near-infrared spectroscopy, elemental profiles, and stable isotope ratios with random forest achieved 87.5 percent accuracy in identifying the geographical ...
Machine Learning Forecasts Rock Fracture Minutes Ahead in Lab Experiments
A random forest model trained on acoustic emission signals from granite hydraulic fracturing experiments forecast specimen failure up to 1800 ...
Physics-guided AI predicts tunnel deformation from nearby foundation pit excavation
A hybrid physics-guided gradient boosting model trained on 154 Chinese engineering cases predicts tunnel heave from nearby foundation pit excavation ...
Generative deep learning for class imbalance in credit risk modeling: comparative evaluation of synthetic oversampling methods and an elastic oversampling extension
A new study in Financial Innovation compares generative and synthetic oversampling for rare-default prediction and introduces a tunable hybrid method ...
AI Learns to Hide Patient Fingerprints Hidden in Raman Spectra of Brain Tumors
An adversarial deep learning framework reduced patient-identity predictability in glioma Raman spectra from 68 percent to 12 percent while preserving ...
Simple Machine Learning Model Predicts Fluorinated Gas Capture in Ionic Liquids
A new study shows a CatBoost machine learning model with only seven simple inputs predicts fluorinated gas solubility in ionic ...
-
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!