explainable ai

Redesigning Authentic Assessment and Feedback Practices in the Generative AI Era

The rapid growth of Generative Artificial Intelligence in higher education has made assessment more complex. Its importance lies in protecting genuine learning and academic integrity in AI rich environments. The main objective of this chapter is to explain how assessment and feedback practices can be redesigned to meas...

A Comprehensive Review of Applications, Challenges, and Future Directions of Artificial Intelligence in Mortgage Lending

The mortgage lending industry is experiencing a significant transformation as it embraces Artificial Intelligence (AI) for its impact on decision-making, operations, risk management, and customer service. Many of the activities associated with mortgage processes can be automated and improved using technologies such as...

PREreview of "The Genetic Fence Strategy: Key for Cell Differentiation, Organism Development, Biodiversity, Cellular Homeostasis, Cancer Prevention, and Disease Sequestering"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23269329. Major issues The article has an interesting, engaging and comprehensive. Although, Abstract and Introduction: The central concept of the "Genetic fence" was not sufficient...

Mobile Generative AI Literacy and English Writing Self-Efficacy: The Role of AI Feedback Engagement in Higher Education

This study examines the relationship between mobile Generative Artificial Intelligence (GenAI) literacy and English writing self-efficacy (EWSE) among university students, with AI feedback engagement (AFE) proposed as a mediating mechanism. Using a quantitative cross-sectional design, data were collected from 312 unive...

Mechanistic Interpretability and Explainable AI (XAI) in Foundation Models: Reverse-Engineering Circuits, Superposition, and Safety Bounds

Abstract—Foundation models, particularly autoregressive Transformer Large Language Models (LLMs) and Vision-Language Models (VLMs), have exhibited unprecedented reasoning and generative capabilities across computer science and engineering. However, their internal representations operate as opaque, high-dimensional 'bla...

Use of generative Artificial Intelligence tools in medical student research projects: An activity system analysis.

This study aimed to characterise how generative AI is reshaping the activity of learning to do research within a mandatory medical student research project, and to identify the contradictions driving that change.

Explaining FOMO Symptoms Based on Maladaptive Perfectionism and Emotional Loneliness with Emphasis on the Mediating Role of Artificial Intelligence Dependency among Female High School Adolescents

Objective: The present study aimed to explain FOMO (Fear of Missing Out) symptoms based on maladaptive perfectionism and emotional loneliness, with a particular focus on the mediating role of artificial intelligence dependency among female high school adolescents. Methods and Materials: This correlational study employe...

Explainable automated classification of cervical cancer cells using SE-LGANet with squeeze and excitation blocks and local and global attention mechanisms

A Convolutional Neural Network integrated with Squeeze-and-Excitation blocks and dual attention mechanisms was developed to classify five distinct cell types, providing an explainable and systematically validated approach for cervical cell evaluation.

An explainable semi-supervised self-training approach for hardware Trojan detection using LIME

An Explainable Semi-Supervised Self-Training approach for HT detection in the pre-silicon IC phase is proposed, which effectively handles the scarcity of labeled training data by leveraging both labeled and unlabeled samples and a hybrid ADASYN-ENN sampling strategy is proposed.

Forecasting spatio-temporal wildlife strike risk for aviation safety using explainable AI

Interpretable Smart Shelf: AI-Driven Food Shelf Life and Quality Prediction

Interpretable SmartShelf is proposed—a non-invasive machine learning algorithm for food classification, freshness detection, and shelf-life estimation based on RGB images that provides the user with an interpretable interface to visualize the predictions.

Explainable machine learning models for AI enabled credit scoring and financial inclusion in emerging markets

Findings support explainability- and governance-centered model selection for inclusive credit scoring, while underscoring the need for multi-metric fairness auditing, external validation, and continued monitoring in operational deployment.