Machine Learning and Probabilistic Graphical Models for Decision Support Systems

We are in the midst of rapid development and era of use of powerful applications of advanced technologies, leading to the 4th industrial revolution. The wide use of cyber-physical systems and the Internet of Things lead to the era of Big Data. A decision support system (DSS) is an information system that analyses data from organizations and presents it so that managers can make decisions more easily. In the era of Big Data, DSS has become vital for organizations. Machine learning is a powerful form of Artificial Intelligence that can be useful to process and analyze Big Data. Machine learning has the potential to advance DSS with a combination of data dictated and human-driven analytics. DSS applications can be used in a vast array of diverse fields, such as making operational decisions, medical diagnosis, and predictive maintenance.

While substantial research has been conducted in the development and application of DSS, there are no reference publications presenting systematically and in depth, the application of Machine Learning to develop the DSS in the context of the process with uncertainty. This book presents recent advancements in research, new methods and techniques, and applications in DSS with Machine Learning and Probabilistic Graphical Models which are very powerful techniques to extract knowledge from big data effectively and interpret decisions. It explores Bayesian network learning, Control Chart, Reinforcement Learning for multi-criteria DSS, Anomaly Detection in Smart Manufacturing with Federated Learning, DSS in healthcare, DSS for supply chain management, etc. The book aims to stimulate scientific exchange, ideas, and experiences in the field of DSS applications. Researchers and practitioners alike will benefit from this book to enhance the understanding of machine learning, Probabilistic Graphical Models, and their use in DSS in the context of decision making with uncertainty. The real-world case studies in various fields with guidance and recommendations for the practical applications of these studies are introduced in each chapter.

我們正處於快速發展和強大應用先進技術的時代，這導致了第四次工業革命。智慧物聯網和物聯網的廣泛應用帶來了大數據時代。決策支援系統（DSS）是一種信息系統，它分析組織的數據並呈現給管理者，以便他們更容易做出決策。在大數據時代，DSS對組織至關重要。機器學習是一種強大的人工智能形式，可以用於處理和分析大數據。機器學習有潛力通過結合數據驅動和人工驅動的分析來推進DSS。DSS應用可以在各種不同領域中使用，例如操作決策、醫學診斷和預測性維護。

儘管在DSS的開發和應用方面進行了大量研究，但沒有參考出版物系統地和深入地介紹了在具有不確定性的過程背景下應用機器學習開發DSS。本書介紹了DSS中機器學習和概率圖模型的最新進展、新方法和技術以及應用，這些都是從大數據中有效提取知識並解釋決策的強大技術。它探討了貝葉斯網絡學習、控制圖、多標準DSS的強化學習、智能製造中的異常檢測與聯邦學習、醫療保健中的DSS、供應鏈管理中的DSS等。本書旨在促進DSS應用領域的科學交流、思想和經驗。研究人員和從業人員都將從本書中受益，以增強對機器學習、概率圖模型及其在具有不確定性的決策中的DSS中的應用的理解。每章介紹了各個領域的實際案例研究，並提供了指導和建議，以便在實際應用中使用這些研究。

Kim Phuc Tran is an Associate Professor of Artificial Intelligence and Data Science at ENSAIT & GEMTEX,
University of Lille, France, and a Senior Scientific Advisor at Dong A University, Vietnam. He obtained a Ph.D. in
Automation and Applied Informatics at the University of Nantes, and an HDR (Dr. Habil.) in Computer Science and
Automation at the University of Lille, France. His research focuses on Artificial Intelligence and applications. He has
published more than 60 papers in SCIE peer-reviewed international journals and proceedings of international conferences. He edited 3 books with Springer Nature and CRC Press, Taylor & Francis Group.

Kim Phuc Tran是法國里爾大學（University of Lille）ENSAIT & GEMTEX的人工智慧和數據科學副教授，同時也是越南東亞大學（Dong A University）的高級科學顧問。他在南特大學（University of Nantes）獲得了自動化和應用信息學博士學位，並在法國里爾大學獲得了計算機科學和自動化的HDR（Dr. Habil.）學位。他的研究專注於人工智慧和應用領域。他在SCIE同行評審的國際期刊和國際會議論文集上發表了60多篇論文。他與Springer Nature和CRC Press, Taylor & Francis Group合作編輯了3本書籍。