Latest Articles for Explainable AI

MiMICRI framework enhances AI interpretations in cardiovascular healthcare, engaging medical experts effectively.

A new framework enhances traffic forecasting through counterfactual explanations for better decision-making.

A method to assess user trust in AI, especially in healthcare settings.

Innovative methods aim to reduce harmful online language while preserving original meaning.

Introducing PQAH for better understanding of AI heatmaps and their evaluation.

Examining the role of AI in agriculture, autonomous systems, and healthcare.

This research focuses on using AI for early detection of retinal diseases.

Using machine learning to forecast lateral spreading risks from earthquakes.

Exploring the role of logic-based methods in AI decision-making transparency.

This study examines how AI predicts sentiment using confusing features.

Combining data types improves early detection and treatment of breast cancer.

Understanding Chronic Kidney Disease and the role of AI in detection.

A look at ensuring AI technologies are reliable and trustworthy.

Machine learning enhances early detection of melanoma thickness through dermoscopy images.

A new approach to explainable AI enhances predictions for Alzheimer's risk through clinical data.

New models enhance accuracy in predicting urban land use and improve planning.

Ensuring AI explanations are clear and reliable for user trust.

Examining the role of explainable AI in addressing bias.

AMORE produces clear rules for better understanding AI decisions in various fields.

VCHAR improves recognition of complex human activities using innovative visual methods.

Exploring the role of neurons in enhancing IR model interpretability.

This study examines how explanations impact user perceptions of AI capabilities.

New model improves accuracy in classifying retinal diseases.

AI helps tackle subjectivity in corporate sustainability assessments.

This article discusses AI's role in improving wireless channel estimation techniques.

Exploring LaFAM: A label-free method for better AI decision understanding.

A new classifier improves explainability and accuracy in AI image recognition.

Exploring how AI improves the analysis of extreme weather forecasts.

CHILLI improves AI explanations for better trust and understanding.

A deep dive into AI’s decision-making and its comparison to human reasoning.

Using data and technology to forecast crop yields effectively.

A new framework enhances understanding of parton density functions using machine learning.

Exploring the need for semantic continuity in AI systems for better understanding.

Advancements in deep learning improve skin disease diagnosis accuracy.

This research provides insights into AI choices in competitive and cooperative settings.

Improving trust and transparency in large language models through explainable AI.

Examining how explainable AI can aid in certifying AI systems.

BONES streamlines Shapley Value estimation for better AI interpretation.

A study on using language models to assess AI explanation methods for activity recognition.

WLDA improves AI classification by handling missing data effectively.