Tran | Reliable AI Systems: Federated, Explainable, and Physics-informed Intelligence | Buch | 978-3-032-48405-5 | www.sack.de

Buch, Englisch, Format (B × H): 155 mm x 235 mm

Reihe: Springer Series in Reliability Engineering

Tran

Reliable AI Systems: Federated, Explainable, and Physics-informed Intelligence


Erscheinungsjahr 2027
ISBN: 978-3-032-48405-5
Verlag: Springer

Buch, Englisch, Format (B × H): 155 mm x 235 mm

Reihe: Springer Series in Reliability Engineering

ISBN: 978-3-032-48405-5
Verlag: Springer


This book examines how artificial intelligence can remain accurate, transparent, and dependable when deployed in real-world systems. Its central premise is that reliability must be engineered, measured, and maintained throughout the system lifecycle.

The book brings together federated learning, explainable AI, and physics-informed intelligence within a unified reliability framework. Federated learning enables organisations to develop shared models without exchanging sensitive data. Explainable AI makes model reasoning open to human examination. Physics-informed intelligence constrains learning through physical laws and operational knowledge. These approaches address different sources of failure and are therefore most effective when designed as complementary parts of the same system.

By connecting these methods with reliability engineering, the book shows how AI failures can be anticipated, assessed, contained, and reduced. Manufacturing, healthcare, and energy case studies illustrate how reliability metrics, human oversight, and technical evidence can be incorporated into model development and decision support. Readers will gain both the conceptual foundations and practical methods needed to build AI systems that people and organisations can responsibly depend on.

Tran Reliable AI Systems: Federated, Explainable, and Physics-informed Intelligence jetzt bestellen!

Zielgruppe


Research

Weitere Infos & Material


Introduction: Why Reliability Matters in AI Systems.- Fundamentals of Reliability Engineering for Intelligent Systems.- Federated Learning for Distributed and Privacy-Reliable Modeling.- Explainable AI for Reliable and Safety-Critical Decisions.- Physics-Informed ML for Reliable Digital Twins.- Reliable and Human-Centered Anomaly Detection for 3D Anthropometric Data (MeshDeepSVDD).- Hybrid Reliability Modeling (Data, Physics ,and Expert Knowledge).- Human-Centered Reliable AI and Decision Support.- Edge and Lightweight Reliable Intelligence.- Reliability and Risk Assessment in Federated & Explainable AI Systems.- Governance, Ethics, and Certification of Reliable AI Systems.- Case Study: Explainable Lightweight Federated Learning for Smart Energy Systems.


Kim Phuc Tran is a Maître de Conférences HDR (Senior Associate Professor) at ENSAIT, University of Lille, and a senior researcher at GEMTEX, France. He is the Founding Director of the International Chair in Data Science and Explainable Artificial Intelligence at Dong A University, Vietnam, where he has led international research and doctoral training since 2018. His research lies at the intersection of reliability engineering, explainable and human-centered AI, federated learning, anomaly detection, statistical process monitoring, and hybrid physics-data modelling. He introduced Human-Centered Learning Mechanics, a theoretical framework for governing the interaction between artificial intelligence, human judgement, and institutional authority. His work applies these ideas to manufacturing, healthcare, energy, textiles, and industrial cyber-physical systems. Dr. Tran is an IEEE Senior Member and serves on the Editorial Board of , published by Springer Nature, Engineering Applications of Artificial Intelligence , IEEE Transactions on Intelligent Transportation Systems , etc. He has contributed to major European and France 2030 research programmes and was recognised among the world’s top 2% of scientists in 2025. He is also the author of forthcoming Springer books on human-centered and reliable artificial intelligence. Across his research, teaching, and editorial work, he pursues a consistent question: how can intelligent systems become more capable while preserving human understanding, responsibility, and the freedom to change course?



Ihre Fragen, Wünsche oder Anmerkungen
Vorname*
Nachname*
Ihre E-Mail-Adresse*
Kundennr.
Ihre Nachricht*
Lediglich mit * gekennzeichnete Felder sind Pflichtfelder.
Wenn Sie die im Kontaktformular eingegebenen Daten durch Klick auf den nachfolgenden Button übersenden, erklären Sie sich damit einverstanden, dass wir Ihr Angaben für die Beantwortung Ihrer Anfrage verwenden. Selbstverständlich werden Ihre Daten vertraulich behandelt und nicht an Dritte weitergegeben. Sie können der Verwendung Ihrer Daten jederzeit widersprechen. Das Datenhandling bei Sack Fachmedien erklären wir Ihnen in unserer Datenschutzerklärung.