Tag: Explainable AI

A new scoping review of 73 studies argues that explanations in AI-driven 5G and 6G networks must balance fidelity, latency, ...

FedSPA combines Shapley-value analysis and model parameter similarity to identify malicious clients in federated learning under data poisoning attacks.

A class-adaptive ensemble of three neural networks classifies brain tumors in MRI scans with 99.39 percent benchmark accuracy, validated by ...

A proof-of-concept study shows explainable AI can reconstruct dairy cow welfare-risk scores from routine milk records while revealing how, and ...

An explainable transformer model fusing MRI with texture descriptors reached over 99 percent accuracy in Alzheimer's disease staging benchmarks, with ...

Researchers report an entropy-driven adaptive spatial modeling framework that classifies drought, salinity, heat and nutrient-deficiency stress in grapevine leaf images ...

A federated, differentially private multimodal framework detects depression and anxiety across three benchmarks with F1 up to 0.806 while cutting ...

A new multimodal AI system called HMTF-Net combines text, conversation context, user interaction graphs, images and metadata to detect cyberbullying, ...

SalientNet is an unsupervised framework that generates mechanistically grounded saliency maps for CNN medical image classifiers, outperforming Grad-CAM, Grad-CAM++, and ...

An explainable XGBoost model retained good discrimination for 28-day mortality in a later MIMIC-IV calendar period, but early hemodynamic summaries ...

Researchers report a multimodal framework combining Bengali OCR, hybrid visual encoders, and vision-language reasoning that achieved 97% accuracy on a ...

A benchmark study couples CNN saliency maps, a cortical atlas and three LLMs to generate interpretable diagnostic reports from brain ...

A PRISMA-based systematic review of 119 studies from 2018 to 2026 maps AI and robotics applications across industries, alongside challenges ...

Researchers combined a conditional diffusion model, a hypertuned YOLO26x detector and a Swin-V2-B classifier with a new SHAP-CAM explainability method ...

A systematic review of mortgage-lending fairness research finds decision trees offer the most interpretable bias detection while neural networks and ...

A study of 762,106 buildings damaged in Nepal's 2015 Gorkha earthquake combines an MLP classifier with imbalance correction, sensitivity analysis, ...

A new study combines machine learning and spatial explainable AI to predict surface urban heat island intensity across the Mumbai ...

A self-supervised CNN framework with Grad-CAM heatmaps reached up to 94.38% validation accuracy on a 2,137-image cotton leaf disease dataset.

A systematic review finds hybrid CNN-transformer models lead stroke lesion analysis, but explainable AI appears in only 11 percent of ...

A new review argues that deep learning skin lesion analysis must prove itself through external validation, fairness and clinical utility ...