explainable ai

Explainable AI for transportation process management: symbolic regression of freight train speeds using Kolmogorov–Arnold networks (KANs)

Beyond the first railway application of KAN, the study presents a complete framework for explainable capacity management: it shows how a single KAN model can be distilled into a human-readable, operationally meaningful equation that quantifies nonlinear, asymptotic and interaction effects – a capability not offered by...

Digital Twins and Explainable AI for Decision Support in Port and Maritime Operations

Digital Transformation and the Rise of Shadow IT: Implicationsfor Organisational Complexity and Cyber Governance

An integrated conceptual framework is developed that explains how digital transformation drives Shadow IT adoption, links unauthorised technology use to organisational complexity and cyber governance risks, and identifies governance mechanisms that balance innovation, security, and compliance.

Human–AI Collaboration Readiness Across Generations: The Roles of Digital Skills, Growth Mindset, and Organizational Support

The findings support generationally differentiated HR interventions for strengthening human–AI collaboration in higher education and contribute to SDGs 4, 8, and 9.

Analogies and Metaphors for Agentic AI: How Industry Practitioners Explain Emerging AI Systems

This work conducts semi-structured interviews with industry practitioners working with agentic AI systems, indicating that agentic AI systems are mainly explained through organizational and anthropomorphic source domains, such as employees, teams, or assistants, which embed abstract system qualities within familiar soc...

Deep Learning in Medical Imaging: Architectures, Clinical Applications, and Emerging Directions

Major deep learning architectures, including CNNs, residual networks, UNet, attention-based models, Vision Transformers, and hybrid approaches, along with their clinical applications are summarized and emerging directions such as self-supervised learning, Explainable AI, federated learning, and lightweight models are h...

Data ethics and privacy in machine learning-driven financial systems: Implications for U.S. Credit Unions and Community Banks

It is concluded that credit unions and community banks can benefit from machine learning only when innovation is balanced with fairness, privacy protection, human oversight, vendor accountability, and community-centered governance.

NeuroCAM-X: An Explainable Hybrid AI Framework for Brain Tumor Classification Using MRI and Clinical Reports with Advanced Tumor Analytics

NeuroCAM-X is presented, a novel explainable hybrid artificial intelligence framework that integrates deep learning-based MRI image analysis with Optical Character Recognition-enabled clinical report interpretation for comprehensive brain tumor diagnosis and addresses critical gaps in medical AI.

Data analytics and internal controls in U.S. financial systems: A review of fraud detection and financial reporting integrity

The study concludes that strengthening fraud detection and financial reporting integrity requires integrating analytics and internal controls within a unified governance framework supported by continuous monitoring, institutional accountability, and transparent oversight mechanisms.

Autonomous Decision Assurance Layer for AI-Driven Enterprise Analytics: Bridging Governance, Multi-Agent AI, and Executive Decision Intelligence in Saudi Vision 2030 Organizations

An Autonomous Decision Assurance Layer (ADAL) is proposed for AI-driven enterprise analytics environments that bridges data governance, multi-agent AI, human-in-the-loop oversight, responsible AI controls, and executive decision intelligence.

Comprehensive overview of A Transformer-Based Model for Detecting Fake news and Sentiment Trends on the Social Media Platform

This review paper looks at transformer-based unified models that incorporate sentiment analysis and false tweet detection, and stresses how transformer-based models, such as BERT, RoBERTa, and XLNet, outperform traditional machine learning algorithms due to their attention mechanisms and contextual knowledge.

AI-driven forecasting for efficient integration of renewable energy systems

Emerging research directions, such as explainable AI, federated learning, digital twins, edge intelligence, and physics-informed machine learning, are identified as promising strategies for developing resilient, intelligent, and sustainable future power grids.