Bücher der Reihe SpringerBriefs in Computer Science

The volume of data being collected in solar astronomy has exponentially increased over the past decade and we will be entering the age of petabyte solar data. Deep learning has been an invaluable tool exploited to efficiently extract key information from the massive solar observation data, to solve the tasks of data archiving/classification, object detection and recognition.Astronomical study starts with imaging from recorded raw data, followed by image processing, such as image reconstruction, inpainting and generation, to enhance imaging quality. We study deep learning for solar image processing. First, image deconvolution is investigated for synthesis aperture imaging. Second, image inpainting is explored to repair over-saturated solar image due to light intensity beyond threshold of optical lens. Third, image translation among UV/EUV observation of the chromosphere/corona, Ha observation of the chromosphere and magnetogram of the photosphere is realized by using GAN, exhibiting powerful image domain transfer ability among multiple wavebands and different observation devices. It can compensate the lack of observation time or waveband. In addition, time series model, e.g., LSTM, is exploited to forecast solar burst and solar activity indices.This book presents a comprehensive overview of the deep learning applications in solar astronomy. It is suitable for the students and young researchers who are major in astronomy and computer science, especially interdisciplinary research of them.

When possible, the methods discussed are evaluated on real-world social media data sets to emphasize their robustness to the noisy nature of the social media environment.On completion of the book, the reader will be well-versed with the complexity of text-mining in multilingual, low-resource environments;

This SpringerBrief provides the first systematic review of the existing works of cohesive subgraph search (CSS) over large heterogeneous information networks (HINs). It also covers the research breakthroughs of this area, including models, algorithms and comparison studies in recent years. This SpringerBrief offers a list of promising future research directions of performing CSS over large HINs.The authors first classify the existing works of CSS over HINs according to the classic cohesiveness metrics such as core, truss, clique, connectivity, density, etc., and then extensively review the specific models and their corresponding search solutions in each group. Note that since the bipartite network is a special case of HINs, all the models developed for general HINs can be directly applied to bipartite networks, but the models customized for bipartite networks may not be easily extended for other general HINs due to their restricted settings. The authors also analyze and compare these cohesive subgraph models (CSMs) and solutions systematically. Specifically, the authors compare different groups of CSMs and analyze both their similarities and differences, from multiple perspectives such as cohesiveness constraints, shared properties, and computational efficiency. Then, for the CSMs in each group, the authors further analyze and compare their model properties and high-level algorithm ideas.This SpringerBrief targets researchers, professors, engineers and graduate students, who are working in the areas of graph data management and graph mining. Undergraduate students who are majoring in computer science, databases, data and knowledge engineering, and data science will also want to read this SpringerBrief.

This Springer Brief presents a selection of tools and techniques which either enable or improve the use of DevOps for airborne software engineering. They are evaluated against the unique challenges of the aviation industry such as safety and airworthiness, and exercised using a demonstrator in order to gather first experience.The book is structured as follows: after a short introduction to the main topics of the work in chapter 1, chapter 2 provides more information on the tools, techniques, software and standards required to implement the subsequently presented ideas. In particular, the development practice BDD, the relation between DevOps, CI & CD and both the Rust & the Nix programming language are introduced. In chapter 3 the authors explain and justify their ideas towards advancing the state of the art, mapping the aforementioned tools and techniques to the DevOps Cycle while considering aspects of Do-178C. Next, in chapter 4 the experiences gathered while implementing a demonstrator using the tools and techniques are described. Eventually, chapter 5 briefly summarizes the findings and presents a compilation of open points and missing pieces which are yet to be resolved.The book targets three different reader groups. The first one are development managers from the aerospace industry who need to see examples and experience reports for the application of DevOps for airborne software. The second group are investigators in the safety-critical embedded systems domain who look for benchmarks at various application domains. And the third group are lecturers who offer graduate level software engineering courses for safety-critical software engineering.

This book provides basic knowledge about main memory management in relational databases as it is needed to support large-scale applications processed completely in memory. In business operations, real-time predictability and high speed is a must. Hence every opportunity must be exploited to improve performance, including reducing dependency on the hard disk, adding more memory to make more data resident in the memory, and even deploying an in-memory system where all data can be kept in memory.The book provides one chapter for each of the main related topics, i.e. the memory system, memory management, virtual memory, and databases and their memory systems, and it is complemented by a short survey of six commercial systems: TimesTen, MySQL, VoltDB, Hekaton, HyPer/ScyPer, and SAP HANA.

This SpringerBrief presents the underlying principles of machine learning and how to deploy various deep learning tools and techniques to tackle and solve certain challenges facing the cybersecurity industry.By implementing innovative deep learning solutions, cybersecurity researchers, students and practitioners can analyze patterns and learn how to prevent cyber-attacks and respond to changing malware behavior. The knowledge and tools introduced in this brief can also assist cybersecurity teams to become more proactive in preventing threats and responding to active attacks in real time. It can reduce the amount of time spent on routine tasks and enable organizations to use their resources more strategically. In short, the knowledge and techniques provided in this brief can help make cybersecurity simpler, more proactive, less expensive and far more effectiveAdvanced-level students in computer science studying machine learning with a cybersecurity focus will find this SpringerBrief useful as a study guide. Researchers and cybersecurity professionals focusing on the application of machine learning tools and techniques to the cybersecurity domain will also want to purchase this SpringerBrief.

This book investigates compressive sensing techniques to provide a robust and general framework for network data analytics. The goal is to introduce a compressive sensing framework for missing data interpolation, anomaly detection, data segmentation and activity recognition, and to demonstrate its benefits. Chapter 1 introduces compressive sensing, including its definition, limitation, and how it supports different network analysis applications. Chapter 2 demonstrates the feasibility of compressive sensing in network analytics, the authors we apply it to detect anomalies in the customer care call dataset from a Tier 1 ISP in the United States. A regression-based model is applied to find the relationship between calls and events. The authors illustrate that compressive sensing is effective in identifying important factors and can leverage the low-rank structure and temporal stability to improve the detection accuracy. Chapter 3  discusses that there are several challenges in applying compressive sensing to real-world data. Understanding the reasons behind the challenges is important for designing methods and mitigating their impact. The authors analyze a wide range of real-world traces. The analysis demonstrates that there are different factors that contribute to the violation of the low-rank property in real data. In particular, the authors find that (1) noise, errors, and anomalies, and (2) asynchrony in the time and frequency domains lead to network-induced ambiguity and can easily cause low-rank matrices to become higher-ranked. To address the problem of noise, errors and anomalies in Chap. 4, the authors propose a robust compressive sensing technique. It explicitly accounts for anomalies by decomposing real-world data represented in matrix form into a low-rank matrix, a sparse anomaly matrix, an error term and a small noise matrix. Chapter 5 addresses the problem of lack of synchronization, and the authors propose a data-driven synchronization algorithm. It can eliminate misalignment while taking into account the heterogeneity of real-world data in both time and frequency domains. The data-driven synchronization can be applied to any compressive sensing technique and is general to any real-world data. The authors illustrates that the combination of the two techniques can reduce the ranks of real-world data, improve the effectiveness of compressive sensing and have a wide range of applications. The networks are constantly generating a wealth of rich and diverse information. This information creates exciting opportunities for network analysis and provides insight into the complex interactions between network entities. However, network analysis often faces the problems of (1) under-constrained, where there is too little data due to feasibility and cost issues in collecting data, or (2) over-constrained, where there is too much data, so the analysis becomes unscalable. Compressive sensing is an effective technique to solve both problems. It utilizes the underlying data structure for analysis. Specifically, to solve the under-constrained problem, compressive sensing technologies can be applied to reconstruct the missing elements or predict the future data.  Also, to solve the over-constraint problem, compressive sensing technologies can be applied to identify significant elementsTo support compressive sensing in network data analysis, a robust and general framework is needed to support diverse applications. Yet this can be challenging for real-world data where noise, anomalies and lack of synchronization are common. First, the number of unknowns for network analysis can be much larger than the number of measurements. For example, traffic engineering requires knowing the complete traffic matrix between all source and destination pairs, in order to properly configure traffic and avoid congestion. However, measuring the flow between all source and destination pairs is very expensive or even infeasible. Reconstructing data from a small number of measurements is an underconstrained problem. In addition, real-world data is complex and heterogeneous, and often violate the low-level assumptions required by existing compressive sensing techniques. These violations significantly reduce the applicability and effectiveness of existing compressive sensing methods. Third, synchronization of network data reduces the data ranks and increases spatial locality. However, periodic time series exhibit not only misalignment but also different frequencies, which makes it difficult to synchronize data in the time and frequency domains.The primary audience for this book is data engineers, analysts and researchers, who need to deal with big data with missing anomalous and synchronization problems. Advanced level students focused on compressive sensing techniques will also benefit from this book as a reference.

This SpringerBrief introduces methodologies and tools for quantitative understanding and assessment of supply chain risk to critical infrastructure systems. It unites system reliability analysis, optimization theory, detection theory and mechanism design theory to study vendor involvement in overall system security. It also provides decision support for risk mitigation.This SpringerBrief introduces I-SCRAM, a software tool to assess the risk. It enables critical infrastructure operators to make risk-informed decisions relating to the supply chain, while deploying their IT/OT and IoT systems.The authors present examples and case studies on supply chain risk assessment/mitigation of modern connected infrastructure systems such as autonomous vehicles, industrial control systems, autonomous truck platooning and more. It also discusses how vendors of different system components are involved in the overall security posture of the system and how the risk can be mitigated through vendor selection and diversification. The specific topics in this book include: Risk modeling and analysis of IoT supply chains Methodologies for risk mitigation, policy management, accountability, and cyber insurance Tutorial on a software tool for supply chain risk management of IoT  These topics are supported by up-to-date summaries of the authors' recent research findings. The authors introduce a taxonomy of supply chain security and discusses the future challenges and directions in securing the supply chains of IoT systems. It also focuses on the need for joint policy and technical solutions to counter the emerging risks, where technology should inform policy and policy should regulate technology development.This SpringerBrief has self-contained chapters, facilitating the readers to peruse individual topics of interest. It provides a broad understanding of the emerging field of cyber supply chain security in the context of IoT systems to academics, industry professionals and government officials.

This SpringerBrief presents a brief introduction to probabilistic risk assessment (PRA), followed by a discussion of abnormal event detection techniques in industrial control systems (ICS). It also provides an introduction to the use of game theory for the development of cyber-attack response models and a discussion on the experimental testbeds used for ICS cyber security research. The probabilistic risk assessment framework used by the nuclear industry provides a valid framework to understand the impacts of cyber-attacks in the physical world. An introduction to the PRA techniques such as fault trees, and event trees is provided along with a discussion on different levels of PRA and the application of PRA techniques in the context of cybersecurity. A discussion on machine learning based fault detection and diagnosis (FDD) methods and cyber-attack detection methods for industrial control systems are introduced in this book as well.A dynamic Bayesian networks based method that can be used to detect an abnormal event and classify it as either a component fault induced safety event or a cyber-attack is discussed. An introduction to the stochastic game formulation of the attacker-defender interaction in the context of cyber-attacks on industrial control systems to compute optimal response strategies is presented. Besides supporting cyber-attack response, the analysis based on the game model also supports the behavioral study of the defender and the attacker during a cyber-attack, and the results can then be used to analyze the risk to the system caused by a cyber-attack. A brief review of the current state of experimental testbeds used in ICS cybersecurity research and a comparison of the structures of various testbeds and the attack scenarios supported by those testbeds is included. A description of a testbed for nuclear power applications, followed by a discussion on the design of experiments that can be carried out on the testbed and the associated results is covered as well.This SpringerBrief  is a useful resource tool for researchers working in the areas of cyber security for industrial control systems, energy systems and cyber physical systems. Advanced-level students that study these topics will also find this SpringerBrief useful as a study guide.

The 5G technology has been commercialized worldwide and is expected to provide superior performance with enhanced mobile broadband, ultra-low latency transmission, and massive IoT connections. Meanwhile, the edge computing paradigm gets popular to provide distributed computing and storage resources in proximity to the users. As edge services and applications prosper, 5G and edge computing will be tightly coupled and continuously promote each other forward.Embracing this trend, however, mobile users, infrastructure providers, and service providers are all faced with the energy dilemma. On the user side, battery-powered mobile devices are much constrained by battery life, whereas mobile platforms and apps nowadays are usually power-hungry. At the infrastructure and service provider side, the energy cost of edge facilities accounts for a large proportion of operating expenses and has become a huge burden.This book provides a collection of most recent attempts to tackle the energy issues in mobile edge computing from new and promising perspectives. For example, the book investigates the pervasive low-battery anxiety among modern mobile users and quantifies the anxiety degree and likely behavior concerning the battery status. Based on the quantified model, a low-power video streaming solution is developed accordingly to save mobile devices' energy and alleviate users' low-battery anxiety. In addition to energy management for mobile users, the book also looks into potential opportunities to energy cost saving and carbon emission reduction at edge facilities, particularly the 5G base stations and geo-distributed edge datacenters.

This book addresses several knowledge discovery problems on multi-sourced data where the theories, techniques, and methods in data cleaning, data mining, and natural language processing are synthetically used. This book mainly focuses on three data models: the multi-sourced isomorphic data, the multi-sourced heterogeneous data, and the text data. On the basis of three data models, this book studies the knowledge discovery problems including truth discovery and fact discovery on multi-sourced data from four important properties: relevance, inconsistency, sparseness, and heterogeneity, which is useful for specialists as well as graduate students. Data, even describing the same object or event, can come from a variety of sources such as crowd workers and social media users. However, noisy pieces of data or information are unavoidable. Facing the daunting scale of data, it is unrealistic to expect humans to "e;label"e; or tell which data source is more reliable. Hence, it is crucial to identify trustworthy information from multiple noisy information sources, referring to the task of knowledge discovery. At present, the knowledge discovery research for multi-sourced data mainly faces two challenges. On the structural level, it is essential to consider the different characteristics of data composition and application scenarios and define the knowledge discovery problem on different occasions. On the algorithm level, the knowledge discovery task needs to consider different levels of information conflicts and design efficient algorithms to mine more valuable information using multiple clues. Existing knowledge discovery methods have defects on both the structural level and the algorithm level, making the knowledge discovery problem far from totally solved.

Latent factor analysis models are an effective type of machine learning model for addressing high-dimensional and sparse matrices, which are encountered in many big-data-related industrial applications. The performance of a latent factor analysis model relies heavily on appropriate hyper-parameters. However, most hyper-parameters are data-dependent, and using grid-search to tune these hyper-parameters is truly laborious and expensive in computational terms. Hence, how to achieve efficient hyper-parameter adaptation for latent factor analysis models has become a significant question.This is the first book to focus on how particle swarm optimization can be incorporated into latent factor analysis for efficient hyper-parameter adaptation, an approach that offers high scalability in real-world industrial applications.The book will help students, researchers and engineers fully understand the basic methodologies of hyper-parameter adaptation via particle swarm optimization in latent factor analysis models. Further, it will enable them to conduct extensive research and experiments on the real-world applications of the content discussed.

Emerging machine learning techniques bring new opportunities to flexible network control and management. This book focuses on using state-of-the-art machine learning-based approaches to improve the performance of Software-Defined Networking (SDN). It will apply several innovative machine learning methods (e.g., Deep Reinforcement Learning, Multi-Agent Reinforcement Learning, and Graph Neural Network) to traffic engineering and controller load balancing in software-defined wide area networks, as well as flow scheduling, coflow scheduling, and flow migration for network function virtualization in software-defined data center networks. It helps readers reflect on several practical problems of deploying SDN and learn how to solve the problems by taking advantage of existing machine learning techniques. The book elaborates on the formulation of each problem, explains design details for each scheme, and provides solutions by running mathematical optimization processes, conducting simulated experiments, and analyzing the experimental results.

Incomplete big data are frequently encountered in many industrial applications, such as recommender systems, the Internet of Things, intelligent transportation, cloud computing, and so on. It is of great significance to analyze them for mining rich and valuable knowledge and patterns. Latent feature analysis (LFA) is one of the most popular representation learning methods tailored for incomplete big data due to its high accuracy, computational efficiency, and ease of scalability. The crux of analyzing incomplete big data lies in addressing the uncertainty problem caused by their incomplete characteristics. However, existing LFA methods do not fully consider such uncertainty.In this book, the author introduces several robust latent feature learning methods to address such uncertainty for effectively and efficiently analyzing incomplete big data, including robust latent feature learning based on smooth L1-norm, improving robustness of latent feature learning using L1-norm, improving robustness of latent feature learning using double-space, data-characteristic-aware latent feature learning, posterior-neighborhood-regularized latent feature learning, and generalized deep latent feature learning. Readers can obtain an overview of the challenges of analyzing incomplete big data and how to employ latent feature learning to build a robust model to analyze incomplete big data. In addition, this book provides several algorithms and real application cases, which can help students, researchers, and professionals easily build their models to analyze incomplete big data.

Wineinformatics is a new data science application with a focus on understanding wine through artificial intelligence. Thousands of new wine reviews are produced monthly, which benefits the understanding of wine through wine experts for winemakers and consumers. This book systematically investigates how to process human language format reviews and mine useful knowledge from a large volume of processed data.This book presents a human language processing tool named Computational Wine Wheel to process professional wine reviews and three novel Wineinformatics studies to analyze wine quality, price and reviewers. Through the lens of data science, the author demonstrates how the wine receives 90+ scores out of 100 points from Wine Spectator, how to predict a wine's specific grade and price through wine reviews and how to rank a group of wine reviewers. The book also shows the advanced application of the Computational Wine Wheel to capture more information hidden in wine reviews and the possibility of extending the wheel to coffee, tea beer, sake and liquors.This book targets computer scientists, data scientists and wine industrial researchers, who are interested in Wineinformatics. Senior data science undergraduate and graduate students may also benefit from this book.

This book investigates intelligent network resource management for IoV, with the objective of maximizing the communication and computing performance of vehicle users. Focusing on two representative use cases in IoV, i.e., safety message broadcast and autonomous driving, the authors propose link-layer protocol design and application-layer computing task scheduling to achieve the objective given the unique characteristics and requirements of IoV. In particular, this book illustrates the challenges of resource management for IoV due to network dynamics, such as time-varying traffic intensity and vehicle mobility, and presents intelligent resource management solutions to adapt to the network dynamics. The Internet of Vehicles (IoV) enables vehicle-to-everything connectivity and supports a variety of applications for vehicles on the road.Intelligent resource management is critical for satisfying demanding communication and computing requirements on IoV, while the highly dynamic network environments pose challenges to the design of resource management schemes. This book provides insights into the significance of adaptive resource management in improving the performance of IoV. The customized communication protocol and computing scheduling scheme are designed accordingly by taking the network dynamics information as an integral design factor. Moreover, the decentralized designs of the proposed solutions guarantee low signaling overhead and high scalability.A comprehensive literature review summarizing recent resource management schemes in IoV, followed by the customized design of communication and computing solutions for the two IoV use cases is included which can serve as a useful reference for professionals from both academia and industry in the area of IoV and resource management. Researchers working within this field and computer science and electrical engineering students will find this book useful as well.

This book provides a concise but comprehensive guide to representation, which forms the core of Machine Learning (ML). State-of-the-art practical applications involve a number of challenges for the analysis of high-dimensional data. Unfortunately, many popular ML algorithms fail to perform, in both theory and practice, when they are confronted with the huge size of the underlying data. Solutions to this problem are aptly covered in the book.In addition, the book covers a wide range of representation techniques that are important for academics and ML practitioners alike, such as Locality Sensitive Hashing (LSH), Distance Metrics and Fractional Norms, Principal Components (PCs), Random Projections and Autoencoders. Several experimental results are provided in the book to demonstrate the discussed techniques¿ effectiveness.

This open access book provides information how to choose and collect the appropriate metrics for a software project in an organization. There are several kinds of metrics, based on the analysis of source code and developed for different programming paradigms such as structured programming and object-oriented programming (OOP). This way, the book follows three main objectives: (i) to identify existing and easily-collectible measures, if possible in the early phases of software development, for predicting and modeling both the traditional attributes of software systems and attributes specifically related to their efficient use of resources, and to create new metrics for such purposes; (ii) to describe ways to collect these measures during the entire lifecycle of a system, using minimally-invasive monitoring of design-time processes, and consolidate them into conceptual frameworks able to support model building by using a variety of approaches, including statistics, data mining and computational intelligence; and (iii) to present models and tools to support design time evolution of systems based on design-time measures and to empirically validate them.The book provides researchers and advanced professionals with methods for understanding the full implications of alternative choices and their relative attractiveness in terms of enhancing system resilience. It also explores the simultaneous use of multiple models that reflect different system interpretations or stakeholder perspectives.

An Introduction to the Machine Learning Empowered Intelligent Data Center NetworkingFundamentals of Machine Learning in Data Center Networks. This book reviews the common learning paradigms that are widely used in data centernetworks, and offers an introduction to data collection and data processing in data centers. Additionally, it proposes a multi-dimensional and multi-perspective solution quality assessment system called REBEL-3S. The book offers readers a solid foundation for conducting research in the field of AI-assisted data center networks.Comprehensive Survey of AI-assisted Intelligent Data Center Networks. This book comprehensively investigates the peer-reviewed literature published in recent years. The wide range of machine learning techniques is fully reflected to allow fair comparisons. In addition, the book provides in-depth analysis and enlightening discussions on the effectiveness of AI in DCNs from various perspectives, covering flow prediction, flow classification, load balancing, resource management, energy management, routing optimization, congestion control, fault management, and network security.Provides a Broad Overview with Key Insights. This book introduces several novel intelligent networking concepts pioneered by real-world industries, such as Knowledge Defined Networks, Self-Driving Networks, Intent-driven Networks and Intent-based Networks. Moreover, it shares unique insights into the technological evolution of the fusion of artificial intelligence and data center networks, together with selected challenges and future research opportunities.

A dynamic network is frequently encountered in various real industrial applications, such as the Internet of Things. It is composed of numerous nodes and large-scale dynamic real-time interactions among them, where each node indicates a specified entity, each directed link indicates a real-time interaction, and the strength of an interaction can be quantified as the weight of a link. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant dynamic network High Dimensional and Incomplete (HDI). An HDI dynamic network with directed and weighted links, despite its HDI nature, contains rich knowledge regarding involved nodes¿ various behavior patterns. Therefore, it is essential to study how to build efficient and effective representation learning models for acquiring useful knowledge.In this book, we first model a dynamic network into an HDI tensor and present the basic latent factorization of tensors (LFT) model. Then, we propose four representative LFT-based network representation methods. The first method integrates the short-time bias, long-time bias and preprocessing bias to precisely represent the volatility of network data. The second method utilizes a proportion-al-integral-derivative controller to construct an adjusted instance error to achieve a higher convergence rate. The third method considers the non-negativity of fluctuating network data by constraining latent features to be non-negative and incorporating the extended linear bias. The fourth method adopts an alternating direction method of multipliers framework to build a learning model for implementing representation to dynamic networks with high preciseness and efficiency.

Convolutional Neural Networks for Medical Applications consists of research investigated by the author, containing state-of-the-art knowledge, authored by Dr Teoh Teik Toe, in applying Convolutional Neural Networks (CNNs) to the medical imagery domain. This book will expose researchers to various applications and techniques applied with deep learning on medical images, as well as unique techniques to enhance the performance of these networks.Through the various chapters and topics covered, this book provides knowledge about the fundamentals of deep learning to a common reader while allowing a research scholar to identify some futuristic problem areas. The topics covered include brain tumor classification, pneumonia image classification, white blood cell classification, skin cancer classification and diabetic retinopathy detection. The first chapter will begin by introducing various topics used in training CNNs to help readers with common concepts covered across the book. Each chapter begins by providing information about the disease, its implications to the affected and how the use of CNNs can help to tackle issues faced in healthcare. Readers would be exposed to various performance enhancement techniques, which have been tried and tested successfully, such as specific data augmentations and image processing techniques utilized to improve the accuracy of the models.