explainable ai

Explainable AI for malware opcode sequence analysis and explainability-motivated saliency-map based spurious correlation robustness in images

Explainability offers a powerful lens for understanding and improving the robustness of Machine Learning (ML) models. This work demonstrates how eXplainable AI (XAI) techniques can be used not only to interpret model behaviour, but also to develop robust training algorithms that encourage the learning of semantically m...

Biomass-LOSO-XAI: Multi-Seed LOSO Validation and Explainable AI for Agricultural Deep Learning

Reproducibility companion repository for the study "Evaluating Domain Generalization in Agricultural Deep Learning through Multi-Seed LOSO Validation and Explainable AI". The repository provides source code, experimental configurations, machine-readable results, and computational workflows for evaluating spatial genera...

UniConEt: A novel Hybrid Deep architecture for fine grained Land Use and Land Cover Classification Using Hyperspectral Imagery

In the rapidly developing field of Remote Sensing (RS), Land Use Land Cover (LULC) classification of Hyperspectral Images (HSI) is a fundamental yet challenging task. HSI is also challenging because of its high spectral dimensionality. Therefore, this research develops a comprehensive spectral and spatial classificatio...

An AI agent-based smart campus management platform

The continuing digital transformation of higher education has produced large volumes of heterogeneous campus data, including network access records, wireless access-point mappings, academic information, security alerts, and institutional documents. These resources are often isolated across operational systems and there...

Global trends and knowledge structure of cardiovascular magnetocardiography research: a bibliometric analysis

Background Cardiovascular diseases remain a leading global health threat. Recent advances in room-temperature sensing and artificial intelligence (AI) have renewed research interest in the clinical translation of magnetocardiography (MCG) for cardiovascular diagnosis, yet the global research evolution of MCG has yet to...

Space as a Growing Mesh of Entanglement: Hypotheses, Tests and a Falsified Prediction

This paper explores an idea I've been developing: that space is a web of quantum entanglement, and that the universe expands because the links in that web gradually weaken as new pieces of space are added.I set out two hypotheses. First, distance between points in space depends on how strongly they're entangled. Second...

Associations of metacognition, self-directed learning ability, and AI literacy with academic achievement among university students predominantly enrolled in health-related majors: a cross-sectional study

Self-directed learning ability is identified as the only examined learner competency that remained significantly associated with GPA after adjustment, and this study examines the associations of metacognition, self-directed learning ability, and AI literacy with self-reported academic achievement among university stude...

Space as a Growing Mesh of Entanglement: Hypotheses, Tests and a Falsified Prediction

This paper explores an idea I've been developing: that space is a web of quantum entanglement, and that the universe expands because the links in that web gradually weaken as new pieces of space are added.I set out two hypotheses. First, distance between points in space depends on how strongly they're entangled. Second...

Enhancing the manufacturing processes and productivity in Industry 5.0 with the integration of machine learning and cyber-physical systems

This paper aims to examine the synergistic integration of Cyber-Physical Systems (CPS) and Machine Learning (ML) as a foundational enabler for Industry 5.0, focusing on creating human-centric, sustainable and resilient manufacturing ecosystems. The study utilizes a synthesis and review approach, analyzing re...

A Federated Hybrid Deep Learning Framework for Multimodal MRI and CT Brain Tumor Diagnosis with Explainable AI

Human-centric digital twins in industry 5.0: technologies, applications, and future directions

Industry 5.0 (I5.0) emphasizes industrial technologies that are human-centric, sustainable, and resilient. Human-Centric Digital Twins (HCDTs) support this transition by integrating worker data with robots, machines, tasks, and industrial environments. However, the relevant research remains fragmented across human mode...

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR BUSINESS

artificial intelligence (AI) and machine learning (ML) have become general-purpose technologies that are reshaping how organisations make decisions, serve customers, design products and run operations. This chapter provides a management-oriented treatment of the principal AI and ML techniques and of the organisational...