Houbing Herbert Song - Böcker

Cyber-Physical Systems: Foundations, Principles and Applications explores the core system science perspective needed to design and build complex cyber-physical systems. Using Systems Science's underlying theories, such as probability theory, decision theory, game theory, organizational sociology, behavioral economics, and cognitive psychology, the book addresses foundational issues central across CPS applications, including System Design -- How to design CPS to be safe, secure, and resilient in rapidly evolving environments, System Verification -- How to develop effective metrics and methods to verify and certify large and complex CPS, Real-time Control and Adaptation -- How to achieve real-time dynamic control and behavior adaptation in a diverse environments, such as clouds and in network-challenged spaces, Manufacturing -- How to harness communication, computation, and control for developing new products, reducing product concepts to realizable designs, and producing integrated software-hardware systems at a pace far exceeding today's timeline. The book is part of the Intelligent Data-Centric Systems: Sensor-Collected Intelligence series edited by Fatos Xhafa, Technical University of Catalonia.

Indexing: The books of this series are submitted to EI-Compendex and SCOPUS

�

Includes in-depth coverage of the latest models and theories that unify perspectives, expressing the interacting dynamics of the computational and physical components of a system in a dynamic environment Focuses on new design, analysis, and verification tools that embody the scientific principles of CPS and incorporate measurement, dynamics, and control Covers applications in numerous sectors, including agriculture, energy, transportation, building design and automation, healthcare, and manufacturing

Approx.374 pagesApprox.374 pages

Federated Learning for Digital Healthcare Systems critically examines the key factors that contribute to the problem of applying machine learning in healthcare systems and investigates how federated learning can be employed to address the problem. The book discusses, examines, and compares the applications of federated learning solutions in emerging digital healthcare systems, providing a critical look in terms of the required resources, computational complexity, and system performance.In the first section, chapters examine how to address critical security and privacy concerns and how to revamp existing machine learning models. In subsequent chapters, the book's authors review recent advances to tackle emerging efficient and lightweight algorithms and protocols to reduce computational overheads and communication costs in wireless healthcare systems. Consideration is also given to government and economic regulations as well as legal considerations when federated learning is applied to digital healthcare systems.

Provides insights into real-world scenarios of the design, development, deployment, application, management, and benefits of federated learning in emerging digital healthcare systemsHighlights the need to design efficient federated learning-based algorithms to tackle the proliferating security and patient privacy issues in digital healthcare systemsReviews the latest research, along with practical solutions and applications developed by global experts from academia and industry

Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Use Cases delineates how graph data science significantly empowers the application of data science. The book discusses the emerging paradigm of graph data science in detail along with its practical research and real-world applications. Readers will be enriched with the knowledge of graph data science, graph analytics, algorithms, databases, platforms, and use cases across a variety of research and topics and applications. This book also presents how graphs are used as a programming language, especially demonstrating how Sleptsov Net Computing can contribute as an entirely graphical concurrent processing language for supercomputers. Graph data science is emerging as an expressive and illustrative data structure for optimally representing a variety of data types and their insightful relationships. These data structures include graph query languages, databases, algorithms, and platforms. From here, powerful analytics methods and machine learning/deep learning (ML/DL) algorithms are quickly evolving to analyze and make sense out of graph data. As a result, ground-breaking use cases across scientific research topics and industry verticals are being developed using graph data representation and manipulation. A wide range of complex business and scientific research requirements are efficiently represented and solved through graph data analysis, and Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Graph Data Science gives readers both the conceptual foundations and technical methods for applying these powerful techniques.Provides comprehensive coverage of the emerging paradigm of graph data science and its real-world applicationsGives readers practical guidance on how to approach and solve complex data analysis problems using graph data science, with an emphasis on deep analysis techniques including graph neural networks (GNNs), machine learning, algorithms, graph databases, and graph query languagesCovers extended graph models such as bipartite directed graphs of place-transition nets, graphs with dynamical processes defined on them - Petri and Sleptsov nets, and graphs as programming languagesPresents all the key tools and techniques as well as the foundations of graph theory, including mathematical concepts, research, and graph analytics

Cybersecurity Defensive Walls in Edge Computing dives into the creation of robust cybersecurity defenses for increasingly vulnerable edge devices. This book examines the unique security challenges of edge environments, including limited resources and potentially untrusted networks, providing fundamental concepts for real-time vulnerability detection and mitigation through novel system architectures, experimental frameworks, and AI/ML techniques. Researchers and industry professionals working in cybersecurity, edge computing, cloud computing, defensive technologies, and threat intelligence will find this to be a valuable resource that illuminates critical aspects of edge-based security to advance theoretical analysis, system design, and practical implementation of defensive walls. With a focus on fast-growing edge application scenarios, this book offers valuable insights into strengthening real-time security for the proliferation of interconnected edge devices.Provides researchers with insights into real-world scenarios of the design, development, deployment, application, management, and benefits of cybersecurity defensive walls in edge computingDiscusses critical cybersecurity defensive walls and their applications to resolve security and privacy issues which affect all parties in edge computing and provide practical learning-based solutions to solve these problemsPresents well-structured chapters from industry experts and global researchers who consider unique security challenges, including limited resources, diverse device types, and potentially untrusted network environments

Informative reference on the state of the art in cybersecurity and how to achieve a more secure cyberspace AI for Cybersecurity presents the state of the art and practice in AI for cybersecurity with a focus on four interrelated defensive capabilities of deter, protect, detect, and respond. The book examines the fundamentals of AI for cybersecurity as a multidisciplinary subject, describes how to design, build, and operate AI technologies and strategies to achieve a more secure cyberspace, and provides why-what-how of each AI technique-cybersecurity task pair to enable researchers and practitioners to make contributions to the field of AI for cybersecurity. This book is aligned with the National Science and Technology Council’s (NSTC) 2023 Federal Cybersecurity Research and Development Strategic Plan (RDSP) and President Biden’s Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Learning objectives and 200 illustrations are included throughout the text. Written by a team of highly qualified experts in the field, AI for Cybersecurity discusses topics including: Robustness and risks of the methods covered, including adversarial ML threats in model training, deployment, and reusePrivacy risks including model inversion, membership inference, attribute inference, re-identification, and deanonymizationForensic and formal methods for analyzing, auditing, and verifying security- and privacy-related aspects of AI componentsUse of generative AI systems for improving security and the risks of generative AI systems to securityTransparency and interpretability/explainability of models and algorithms and associated issues of fairness and biasAI for Cybersecurity is an excellent reference for practitioners in AI for cybersecurity related industries such as commerce, education, energy, financial services, healthcare, manufacturing, and defense. Fourth year undergraduates and postgraduates in computer science and related programs of study will also find it valuable.

An expert compilation of on-device training techniques, regulatory frameworks, and ethical considerations of TinyML design and development In Tiny Machine Learning: Design Principles and Applications, a team of distinguished researchers delivers a comprehensive discussion of the critical concepts, design principles, applications, and relevant issues in Tiny Machine Learning (TinyML). Expert contributors introduce a new low power resource, offering vast applications in IoT devices with system-algorithm co-design. Tiny Machine Learning explores TinyML paradigms and enablers, TinyML for anomaly detection, and the learning panorama under TinyML. Readers will find explanations of TinyML devices and tools, power consumption and memory in IoT microcontrollers, and lightweight frameworks for TinyML. The book also describes TinyML techniques for real-time and environmental applications. Additional topics covered in the book include: A thorough introduction to security and privacy techniques for TinyML devices, including the implementation of novel security schemesIncisive explorations of power consumption and memory in IoT MCUs, including ultralow-power smart IoT devices with embedded TinyMLPractical discussions of TinyML research targeting microcontrollers for data extraction and synthesisPerfect for industry and academic researchers, scientists, and engineers, Tiny Machine Learning will also benefit lecturers and graduate students interested in machine learning.

An up-to-date and expert discussion of neuro-symbolic artificial intelligence development In Neuro-symbolic AI: Foundations and Applications, a team of distinguished researchers delivers a comprehensive overview of the emerging field of neuro-symbolic artificial intelligence. Expert contributors explain the integration of symbolic representations with neural networks, demonstrating state-of-the-art practices in the field. The book fosters collaboration amongst diverse disciplines and promotes a deeper understanding of the challenges posed by deep learning, including generalizability, explainability, and robustness. It is an authoritative, self-contained reference text that provides a solid foundation for newcomers to the field as well as seasoned researchers and developers. Readers will find: A systematic perspective on the foundations of neuro-development AI system developmentComprehensive explorations of key concepts in neuro-symbolic artificial intelligenceDiscussions of real-world applications of neuro-symbolic AI in fields such as healthcare, finance, autonomous driving, and the militaryComplete treatments of the foundations of neuro-symbolic AI from multiple disciplinary perspectives, including computer science, software engineering, and academic researchPerfect for researchers and professionals in artificial intelligence involved industries, including autonomous driving, military, healthcare, and finance, Neuro-symbolic AI: Foundations and Applications will also benefit students of computer science, software engineering, data science, and machine learning.

In the era of big data and multi-connectivity via IoTs, protecting and securing multimedia data has become a real necessity and priority for organizations and businesses, but this can be a rather difficult task due to the heterogeneous nature of platforms and data sets. It is therefore essential to improve the security level of multimedia information by developing core technologies to prevent the loss and damage of information during processing and transmission.This book covers innovations and future perspectives in access control and security monitoring of multimedia Information processing and transmission. The authors present cybersecurity, privacy and control methods and technologies integrated with blockchain and multimedia AI, including encryption and watermarking techniques, wearable-based IoT security methods, multimedia data forensics and deepfake video security monitoring.This will be a useful reference for researchers, engineers and scientists in both academia and industry as well as lecturers and advanced students for developing efficient methods, frameworks and techniques for multimedia information processing security and privacy. It will also be of interest to multimedia platform and system developers and designers.

Billions of wireless applications are proliferating in the global space. The novel wireless systems to support these applications need to satisfy several user-defined metrics to ensure quality of physical experience, quality of service, low latency and ultra-high reliability. Enabling technologies are being developed in order to meet these rate-hungry requirements.Managing these complex wireless and computing resources requires a proactive analysis of the core wireless systems, especially in the metaverse, which is a virtual model of the physical world systems. The metaverse concept is intended to be self-sustainable and facilitates the seamless operation of wireless systems at minimal operational costs for the efficient management of wireless system resources. It is gaining widespread popularity using technologies such as advanced optimization theory, digital twins, virtual reality, machine learning, and blockchain.This book presents a comprehensive overview of advanced metaverse wireless communication systems. The authors highlight the technology enablers and critical design aspects, emphasize how the metaverse can support wireless systems but also show how wireless systems can empower the metaverse. They address critical concerns covering theoretical analysis, novel system architecture design and new implementation methodologies, emerging application scenarios, experimental frameworks, and reliability, security, privacy, technical, and ethical considerations, viable solutions, as well as open challenges, the social impacts of the metaverse concept and future perspectives.Offering a range of international perspectives from researchers in the field, this book is intended for researchers from academia and industry, and scientists, engineers, lecturers and advanced students in the fields of wireless and mobile communications, networking, computing, data science, AI/ML/DL, multimedia, haptics, sensing, CPS and immersive technologies.

Quantum computing has shown a potential to tackle specific types of problems, especially those involving a daunting number of variables, at an exponentially faster rate compared to classical computers. This volume focuses on quantum variants of machine learning algorithms, such as quantum neural networks, quantum reinforcement learning, quantum principal component analysis, quantum support vectors, quantum Boltzmann machines, and many more.

This book uncovers the innovative features of complex algebra i.e., the octonion -sparse concept in image processing and how it can help in improving the computational efficiency of image processing.It deals with the most common octonion convolution neural network, quaternion wavelet, and sparse representation-based techniques in multispectral image processing.The book focusses on how evolution in algebraic concepts i.e. octonion and sparse helps in improving accuracy and efficiency of various color image restoration, reconstruction and recognition.It provides examples of research and real-world applications related to biometric security, medical image processing, face recognition, and how crucial characteristics are extracted. The main focus of this book is to bring all the related technologies, novel findings and managerial applications of Colored Medical Imaging on a single platform to provide great readability, easy understanding, and smooth adaptability of various basic and advanced concepts to the Undergraduate and Postgraduate students, Researchers, Managers, Designers, Academicians, and Practitioners doing work in this domain.

mso-ansi-language: EN-US;">This book constitutes the refereed proceedings of the 18th International Conference on Network and System Security, NSS 2024, held in Abu Dhabi, United Arab Emirates, during November 20–22, 2024.