Tag: Explainable AI

A systematic review of 75 studies finds ECG-based AI models reporting 90 to 99 percent accuracy, but warns that external ...

Machine learning reads VR learning traces to model how students self-regulate

A study of 138 elementary students in Jakarta shows that interaction traces from VR-integrated e-modules can predict self-regulated learning with ...

Federated AI Learns to Spot Hospital Device Hacks Without Ever Seeing Patient Data

Researchers have built a federated, explainable deep learning framework that detects attacks on Internet of Medical Things devices with detection ...

New Monotone Scoring Method Aims to Make Human Oversight of Robots More Explainable

A new mathematically guaranteed scoring method keeps robot oversight decisions monotone and explainable, though its benefits so far are limited ...

AI Reads Student Records to Predict English Proficiency in Vocational Colleges

A new interpretable AI framework combining large language model embeddings with structured educational data predicted vocational college students' English proficiency ...

AI Learns to Read the Fine Print of Bacterial and Fungal Leaf Disease

A systematic review of 59 studies finds deep learning dominates fungal leaf disease detection while bacterial diagnosis, generative AI and ...

Explainable AI models track EV battery health over 6G networks

A new study combines LSTM-based deep learning with LIME and SHAP explainability to estimate EV battery state of health across ...

AI Wearable Framework Aims for Secure Multimodal Health Monitoring in Preclinical Testing

A four-tier wearable health monitoring framework combining multimodal deep learning, federated learning, differential privacy and blockchain auditability has reported strong ...

Deep learning maps a path toward smarter aneurysm surgery planning

A systematic review of 127 studies finds deep learning tools for cerebrovascular planning advancing rapidly, while small vessel segmentation, material ...

Explainable AI pipeline spots metastasising cancer cells in microscopy images

An explainable deep learning pipeline segments single cells in fluorescence microscopy images and classifies them as normal or metastasising, with ...

Federated AI Framework Pairs Medical Imaging Accuracy with Auditable Explanations

A new federated learning framework for chest X-ray analysis reports modest accuracy gains over existing methods while aligning explanations across ...

Adaptive AI framework keeps intrusion detection accurate as data drifts

A new adaptive learning framework combines temporal decay weighting, sliding-window retraining and closed-loop SHAP explanations to keep intrusion detection accurate ...

AI pinpoints and explains smart contract flaws at function level

Researchers at JAIST built a graph neural network and explanation framework that locates smart contract vulnerabilities at the individual function ...

Explainable AI learns to spot the hidden patterns of a Rembrandt

Carnegie Mellon researchers developed an explainable AI framework, published in PNAS, that scores paintings for statistical patterns associated with Rembrandt, ...

AI Model Predicts 28-Day Death Risk in Septic Shock From Routine Admission Blood Tests

Researchers in China built an automated machine learning tool, optimized by a fox-inspired algorithm, that estimates 28-day mortality in emergency ...

Vision transformer identifies coffee leaf nutrient deficiencies and treatment rules

A controlled study of 1,196 coffee leaf images found that an explainable Vision Transformer classified nutrient deficiencies with up to ...

Dual-Channel AI Model Links Sentiment, Performance and Educational Tool Adoption

A dual-channel machine-learning framework combined sentiment, academic performance and engagement data to predict educational AI adoption, learning gains and personalized ...

DeiT framework pairs plant disease detection with interpretable severity estimates

A hybrid DeiT system reached 99.13% accuracy on a 38-class plant disease benchmark while combining local and global AI explanations ...

Supervised meta-model improves human alignment of Arabic AI explanations

A study of 303 Arabic hotel reviews found that a supervised CatBoost meta-model matched human-selected words better than standard XAI ...

Chinese tuberculosis physicians outline explainability needs for clinical AI