explainable ai

Geospatial Artificial Intelligence (GeoAI) for Sustainable Urban Governance: A Systematic Review and Governance-Oriented Framework

GeoAI has advanced the analysis and prediction of urban systems by integrating GIS with artificial intelligence, yet its contribution to urban planning and governance remains limited. Many applications function as black-box predictive tools, making results difficult to interpret, justify, audit, and use in formal plann...

From Context to Plasticity: A Three-Timescale Architecture for Persistent Memory and Recursive Online Learning

This work presents a theoretical architecture for continually adapting AI systems organized around three distinct timescales: (1) fast transformer key-value context for immediate interaction, (2) medium-term persistent recurrent memory with decaying importance and consolidation, and (3) slow, controlled parameter adapt...

AI Meets Analytical Chemistry: The Next Era of Food Forensics

Food fraud and adulteration continue to threaten food safety, consumer confidence and international trade. The challenges of investigating food-forensics reliably are compounded by increasingly complex supply chains, changing deceptive practices and difficulties in interpreting high-dimensional analytical data. The rev...

Why the User Rages: A User-Centered Study on Conversational AI Models' Defensive Communication Behaviors and Their Effects

On August 8 (UTC+8), 2025, OpenAI rolled out GPT-5 to the public, and simultaneously removed access to all “legacy models” including GPT-4o. This action led to a global movement to “bring back GPT-4o”. The protest against “cold and detached” GPT-5 revealed users’ acute sensitivity to anthropomorphic AI responses: users...

Integrating Explainable AI Into Cybersecurity Operations Centers for Intelligent Threat Detection and Response

THE EL-RAKHAWI SOVEREIGN HEALTH PROTOCOL Electronic Health Records and Post-Quantum Defense in the Age of Medical AI Il Protocollo El-Rakhawi Sanitario Sovrano: Fascicolo Sanitario Elettronico e Difesa Post-Quantica nell'Era dell'IA Medica

"The El-Rakhawi Sovereign Health Protocol" by Dr. Mohamed Kamal Arafa Elrakhawi establishes a foundational framework for digital health sovereignty. It asserts medical data is a sovereign extension of the human body, not a corporate asset. The Protocol mandates four pillars: absolute patient ownership via cryptographic...

Critical-infrastructure-resilience-command-center: Critical Infrastructure Resilience Command Center — v0.1.0

Critical Infrastructure Resilience Command Center — v0.1.0 Initial public release of a research-prototype command center that unifies Zero Trust posture, post-quantum cryptography (PQC) migration readiness, and AI-driven predictive maintenance into a single resilience-scoring platform for synthetic critical-energy digi...

The Period a Moving-Average Crossover Finds Is Made by the Ratio of the Two Periods: Holding the Ratio Fixed and Multiplying Both Periods by Eight Moves the Normalised Interval Only from 0.650 to 0.653 [F001]

二本の移動平均のクロスについて「この組み合わせは約N本の波を捉えている」と言われることがある。そのNを決めているのが相場なのか、二本の期間の選び方なのかを、ティックデータで測った。 四銘柄(USDJPY・EURUSD・GBPUSD・XAUUSD)の2019年から2024年までの1時間足で、連続するクロスの間隔の中央値を、三つの族について測った。比を4.0に固...

Problem Sheets - Artificial Intelligence in the Life Sciences - Ruhr University Bochum

This record contains five problem sheets from the lecture Artificial Intelligence in the Life Sciences, held in the winter term 2025/26 at the Faculty of Biology and Biotechnology, Ruhr University Bochum. The exercises take students from classical machine learning to modern deep learning and explainable AI, and many of...

When risk becomes a story: Culture, loss allocation, and lessons from iceland

Abstract When Iceland's three largest banks failed in October 2008, the immediate problem was brutally concrete: a banking system that dwarfed the domestic economy had collapsed, and someone had to absorb the losses. Balance‐sheet structure explains why the banks failed. It says less about why repeated warnings carried...

When readiness fails: a TOE–TAM mixed-methods analysis of AI-enabled HR digitalization in a resource-constrained small island context

This study examines barriers to adopting artificial intelligence (AI) in human resource management (HRM)—hereafter AI-enabled human resources (AI-HR)—across Zanzibar’s public and private sectors and asks whether the standard predictors of an integrated Technology–Organization–Environment and Technology Acceptance Mod...

Stock Portfolio Optimization with Explainable AI: A Comparative Study with the Black-Litterman Model

This study aims to determine whether an artificial intelligence (AI) approach can outperform Black-Litterman (BL) -a classical stock portfolio optimization framework.Using a diversified dataset that contains market indices, sector exchange-traded funds (ETFs) and stocks, we compare the performance of XGBoost with a Bla...