Machine learning crash severity review finds imbalance and interpretability gaps
A systematic review of 306 studies finds most machine learning crash severity models ignore class imbalance and a large share ...
Tag: model interpretability
Machine learning offers limited screening for poor fitness in Tibet
A cross-sectional study of 5,750 adults at three Tibetan altitudes found moderate discrimination and substantial sensitivity-specificity trade-offs in machine-learning screening ...
Neural network predicts three-year local recurrence after lung SBRT with higher accuracy than standard models
A retrospective single-center study developed an interpretable artificial neural network that predicted three-year local recurrence after lung SBRT with an ...
Interpretable machine learning predicts Victorian zonal crash counts
A nested-validation study in Victoria found that an interpretable XGBoost model could retrospectively concentrate crashes in small sets of zones, ...
Systematic review finds attention explanations are rarely tested for faithfulness
A systematic review of 168 primary studies found that 57.14% did not examine the performance–faithfulness relationship, 41.07% reported synergy and ...
Research report: INSIGHT: a scalable cluster-based framework with theoretical guarantees for interpretable fraud detection in mixed-feature data
INSIGHT combines mixed-distance clustering, cluster-aware oversampling and interpretability analyses to improve fraud detection in two financial transaction datasets.
Mahabad Dam modeling study reports 80% lower mean absolute error for total nitrogen predictions
A Mahabad Dam modeling study reported an 80% reduction in mean absolute error and a rise in Willmott’s index from ...
Hybrid knowledge-tracing model outperforms baselines in cultural-education dialogue study
A study of 8,000 students found that a hybrid knowledge-tracing model combining language semantics, dialogue behavior and multidimensional memory achieved ...
AI That Explains Itself: New Benchmark Reveals Which Neural Networks Truly See Pneumonia
A standardized benchmark of six convolutional neural networks shows that the most accurate pneumonia-detecting models also produce the most faithful ...
New AI Explainer Finds Extreme Data Archetypes That SHAP and LIME Miss
A new framework called ARCHEX uses archetypal analysis to reveal global structural patterns in machine learning models that local explanation ...
-
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!