Tag: binary classification

Researchers evaluated hierarchical and flat machine learning models, finding a two-stage approach cut memory use while exceeding 99 percent detection ...

A methodological evaluation of hospital electronic health records found that simpler binary random forest models matched complex multi-outcome frameworks when ...

A new finite-sample inferential framework called FWKC improves the reliability of weighted kappa coefficient intervals in small-sample binary diagnostic agreement ...

A newly published study shows that StatMatch, a statistical matching-based undersampling method, can match SMOTE on some imbalanced datasets although ...

A deep learning framework trained on orthophotos from the 2011 Great East Japan Earthquake detected damaged roads and bridges with ...

A simulation study found that only the scaled Brier score consistently met proposed prevalence-related criteria for evaluating hard classifications in ...

A new open-source tool called RandomFuzzyRules replaces evolutionary search with random sampling to find compact, interpretable two-rule fuzzy classifiers that ...

A new AI framework called SliceMap uses lightweight two-dimensional neural networks to efficiently localize subtle discriminative regions in brain MRI, ...

A new classifier called CABLE-kNN caches local neighborhood evidence during training and neutralizes class priors, beating ordinary kNN on imbalanced ...

Researchers at Hanoi University of Science and Technology have developed a fuzzy-set-based hesitation score that makes multi-task AI models robust ...