Qihui Wu – författare

This two-volume set LNICST 357-358 constitutes the post-conference proceedings of the 11th EAI International Conference on Wireless and Satellite Services, WiSATS 2020, held in Nanjing, China, in September 2020. The 91 full papers and workshop papers were carefully reviewed and selected from 200 submissions. Part I - LNICST 357 - details original research and results of wireless and satellite technology for a smarter global communication architecture. The theme of WISATS 2020 is “Intelligent Wireless and Satellite Communications for Beyond 5G”. Part II – LNICST 358 - presents 6 workshop papers: High Speed Space Communication and Space Information Networks (HSSCSIN); Integrated Space and Onboard Networks (ISON); Intelligent Satellite Operations, Managements, and Applications (ISOMA); Intelligent Satellites in Future Space Networked System (ISFSNS); Satellite Communications, Networking and Applications (SCNA); Satellite Internet of Things; Trusted Data Sharing, Secure Communication (SIOTTDSSC).

This two-volume set LNICST 357-358 constitutes the post-conference proceedings of the 11th EAI International Conference on Wireless and Satellite Services, WiSATS 2020, held in Nanjing, China, in September 2020. The 91 full papers and workshop papers were carefully reviewed and selected from 200 submissions. Part I - LNICST 357 - details original research and results of wireless and satellite technology for a smarter global communication architecture. The theme of WISATS 2020 is “Intelligent Wireless and Satellite Communications for Beyond 5G”. Part II – LNICST 358 - presents 6 workshop papers: High Speed Space Communication and Space Information Networks (HSSCSIN); Integrated Space and Onboard Networks (ISON); Intelligent Satellite Operations, Managements, and Applications (ISOMA); Intelligent Satellites in Future Space Networked System (ISFSNS); Satellite Communications, Networking and Applications (SCNA); Satellite Internet of Things; Trusted Data Sharing, Secure Communication (SIOTTDSSC).

This book is designed to provide a well-structured, comprehensive, and practical textbook on machine learning for undergraduate and graduate students in related fields. Through clear and accessible explanations, this book allows readers go master the concepts and techniques of machine learning, equipping them with the ability to solve real-world problems.A distinctive feature of this book is its emphasis on interpretability. In the world of machine learning, models need not only to be accurate but also to be understandable and explainable. For students, understanding the underlying principles and logic of algorithms is more important than simply using them as black boxes. Therefore, each chapter in this textbook not only introduces the mathematical background and implementation principles of the algorithms but also demonstrates them through detailed Python code, helping readers understand how each algorithm works and providing valuable insights.From the foundational concepts of linear regression and logistic regression to more complex techniques such as deep neural networks, convolutional neural networks, and recurrent neural networks, this book covers the full spectrum of classical algorithms and cutting-edge technologies in machine learning. We also provide in-depth discussions on ensemble learning, reinforcement learning, and Transformer models, addressing some of the most popular topics in the field. Through real-world case studies, we connect these algorithms with practical applications, helping readers better understand how they are used in various scenarios.While focusing on theoretical learning, we also emphasize the development of practical skills. The case studies in each chapter are based on real-world data and cover a variety of domains, including classification, regression, image processing, and natural language processing. Through these case studies, readers will not only grasp the ideas behind the algorithms but also experience how to apply these theories to solve actual problems.Finally, this book includes a special section on large language models, showcasing how machine learning has evolved into today's cutting-edge technology. It guides readers toward the frontier of artificial intelligence, highlighting breakthroughs in natural language understanding and generation. This marks not just an extension of machine learning techniques, but also their profound impact in the realm of language processing.This book is suitable not only for academic teaching but also for scholars and practitioners who wish to deepen their understanding of machine learning. We hope that it helps readers strengthen their theoretical foundation, enhance their practical skills, and pave the way for engaging with frontier research and innovation in this field.

This book presents reinforcement learning (RL) based solutions for user-centric online network selection optimization. The main content can be divided into three parts. The first part (chapter 2 and 3) focuses on how to learning the best network when QoE is revealed beyond QoS under the framework of multi-armed bandit (MAB). The second part (chapter 4 and 5) focuses on how to meet dynamic user demand in complex and uncertain heterogeneous wireless networks under the framework of markov decision process (MDP). The third part (chapter 6 and 7) focuses on how to meet heterogeneous user demand for multiple users inlarge-scale networks under the framework of game theory. Efficient RL algorithms with practical constraints and considerations are proposed to optimize QoE for realizing intelligent online network selection for future mobile networks. This book is intended as a reference resource for researchers and designers in resource management of 5G networks and beyond.

This book presents reinforcement learning (RL) based solutions for user-centric online network selection optimization. The main content can be divided into three parts. The first part (chapter 2 and 3) focuses on how to learning the best network when QoE is revealed beyond QoS under the framework of multi-armed bandit (MAB). The second part (chapter 4 and 5) focuses on how to meet dynamic user demand in complex and uncertain heterogeneous wireless networks under the framework of markov decision process (MDP). The third part (chapter 6 and 7) focuses on how to meet heterogeneous user demand for multiple users inlarge-scale networks under the framework of game theory. Efficient RL algorithms with practical constraints and considerations are proposed to optimize QoE for realizing intelligent online network selection for future mobile networks. This book is intended as a reference resource for researchers and designers in resource management of 5G networks and beyond.