explainable ai

A proof of a conjecture of H. Gruber: finite unary languages by the alphabetic width of their regular expressions

We prove a statement recorded by H. Gruber in 2012 in the OEIS entry A000079 (the powers of 2), verified by him up to n = 17: for n >= 1, the number of distinct finite languages over a one-letter alphabet whose minimum regular expression has alphabetic width n is 2^n. The alphabetic width of a regular expression is the...

The fixed space of the ribbon-to-homogeneous transition matrix of noncommutative symmetric functions: a proof of a conjecture recorded by J. M. Campbell

We prove a conjecture recorded by J. M. Campbell in 2018 in the OEIS entry A001405 (the central binomial coefficients binomial(n, floor(n/2))). Let NSym be the algebra of noncommutative symmetric functions of Gelfand, Krob, Lascoux, Leclerc, Retakh and Thibon, and let C_n(R, H) be the transition matrix from the ribbon...

Foundations of Human-Centric AI and Machine Learning for Construction 6.0

The foundations of Human-Centric Artificial Intelligence and Machine Learning as enablers of Construction 6.0, emphasizing the integration of automation, cognitive systems, and human expertise are examined. The chapter outlines how Artificial Intelligence is transforming architecture, engineering, and construction thro...

A context-aware multimodal multi-agent deep reinforcement learning framework for autonomous personalized education

This paper introduces the Context-Aware Multi-Agent Deep Reinforcement Learning (CA-MA-DRL) framework for personalised digital education, shifting from passive analytics to autonomous decision-making agents. The framework integrates Multimodal Learning Analytics with advanced coordination mechanisms, fusing heterogeneo...

Human-Centric AI-Driven Sustainable and Resilient Design AI for Energy-efficient and Carbon-neutral Buildings

This chapter examines how Human-Centric Artificial Intelligence is transforming sustainable and resilient design in the built environment. With buildings responsible for nearly 40% of global energy use and 30% of greenhouse gas emissions, the chapter underscores the need for energy-efficient and carbon-neutral architec...

Physical‑Intuition‑Driven Nonlinear Ignition‑Threshold Scaling and Shell‑Aspect‑Ratio Regime Separation for 1D ICF via TreeSHAP Explainable AI

Laser-driven inertial-confinement-fusion (ICF) achieves thermonuclear ignition via spherical capsule compression, yet high-fidelity multi-dimensional radiation-hydrodynamic simulations demand prohibitive computational resources. The ignition-threshold-factor (ITF) quantifies ignition margins to constrain target-design...

Toward the Alignment of Understandability, Reasoning, and Explainability in TEL

An Integrated Explainable AI and Universal Design for Learning (UDL) Framework for Inclusive Special Education Systems

Algorithmic Bias in AI Marketing: Implications for Consumer Equity and Brand Reputation

Artificial intelligence (AI) is increasingly embedded in targeting, personalization, pricing, recommendation, and content-generation systems, intensifying concerns about algorithmic bias and its consequences for consumers and brands. This critical literature review synthesizes peer-reviewed and applied research publish...

TrustmeWatcher: An Application for Workplace Micro-Sensing and Explainable Well-Being Feedback

Workplace sensing studies combine long-running behaviour traces with self-reports, yet the tools that collect those data often sit apart from the interface that returns results. We present TrustmeWatcher, the application built for the TRUST-ME project to connect this work. TrustmeWatcher reuses ActivityWatch's OS-level...

Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems

Neural-network (NN) controllers are increasingly used in nonlinear control systems, but their highly nonlinear behavior makes them difficult to explain and verify, raising trustworthiness concerns in safety- and mission-critical applications. A key step toward certifiable trustworthiness is to find a Forward-Invariant...

A Unified and Interpretable Geometric Optimization Framework for Intelligent Automated Implant Planning in CBCT from Single to Consecutive Multiple Missing Teeth

Automated dental implant planning using artificial intelligence (AI) faces challenges in interpretability, safety assurance, and applicability beyond single-tooth cases. This paper presents a unified explainable framework for cone-beam computed tomography (CBCT) that handles both single-tooth and consecutive multiple m...