Explainable Intelligence in Digital Twins : Proceedings of EIDT, Ho Chi Minh City, Vietnam, November 12-14, 2025 (Lecture Notes in Electrical Engineering)

Dao, Nhu-Ngoc (EDT)/ Truong Hoang, Vinh (EDT)/ Dornaika, Fadi (EDT)

Springer Verlag, Singapore（2026/03発売）

• 製本 Hardcover:ハードカバー版
• 言語 ENG
• 商品コード 9789819561100

Full Description

This book presents selected papers from the International Conference on Explainable Intelligence in Digital Twins (EIDT 2025) held during November 12-14, at Ho Chi Minh City, Vietnam. The integration of explainable intelligence in digital twins offers significant advantages, enhancing transparency, trust, and informed decision-making across various industries, including manufacturing, healthcare, transportation, and smart cities. By combining real-time data with AI-driven analytics, digital twins enable predictive maintenance, process optimization, transparent communication, and system automation. While these technologies have immense potential to revolutionize digital ecosystems, they also pose significant challenges, such as bias in AI models, scalability of explainable methods, and trade-offs between performance and interpretability. To address these critical issues, the International Conference on Explainable Intelligence in Digital Twins (EIDT) was established as a dedicated platform for research scholars and engineers to discuss, innovate, and collaborate on advancing transparent, interpretable, and trustworthy AI-driven digital twins. EIDT fosters cutting-edge research and real-world applications that drive the next generation of explainable intelligence in digital twin networks and systems.

Contents

Explainable Intelligence in Digital Twins: State-Of-The-Art and Open Challenges.- QLoRA and RAG Application in Building Admissions Support Chatbot: Performance Evaluation and Knowledge Update Ability.- AI-Driven Hand Gesture Recognition for Intelligent Human-Computer Interaction in Healthcare.- A Novel Approach to Analyze the Correlation Between Assessment Methods and CLO Learning Outcomes in Higher Education.- Enhancing Speaker Identification with Hybrid Deep Learning Models and Multi-Feature Fusion.