This book highlights the state of the art and recent advances in Big Data clustering methods and their innovative applications in contemporary AI-driven systems. The book chapters discuss Deep Learning for Clustering, Blockchain data clustering, Cybersecurity applications such as insider threat detection, scalable distributed clustering methods for massive volumes of data; clustering Big Data Streams such as streams generated by the confluence of Internet of Things, digital and mobile health, human-robot interaction, and social networks; Spark-based Big Data clustering using Particle Swarm Optimization; and Tensor-based clustering for Web graphs, sensor streams, and social networks. The chapters in the book include a balanced coverage of big data clustering theory, methods, tools, frameworks, applications, representation, visualization, and clustering validation.

This book examines the principles of and advances in personalized task recommendation in crowdsourcing systems, with the aim of improving their overall efficiency. It discusses the challenges faced by personalized task recommendation when crowdsourcing systems channel human workforces, knowledge, skills and perspectives beyond traditional organizational boundaries. The solutions presented help interested individuals find tasks that closely match their personal interests and capabilities in a context of ever-increasing opportunities of participating in crowdsourcing activities. In order to explore the design of mechanisms that generate task recommendations based on individual preferences, the book first lays out a conceptual framework that guides the analysis and design of crowdsourcing systems. Based on a comprehensive review of existing research, it then develops and evaluates a new kind of task recommendation service that integrates with existing systems. The resulting prototype provides a platform for both the field study and the practical implementation of task recommendation in productive environments.

This book demonstrates how quantitative methods for text analysis can successfully combine with qualitative methods in the study of different disciplines of the Humanities and Social Sciences (HSS). The book focuses on learning about the evolution of ideas of HSS disciplines through a distant reading of the contents conveyed by scientific literature, in order to retrieve the most relevant topics being debated over time. Quantitative methods, statistical techniques and software packages are used to identify and study the main subject matters of a discipline from raw textual data, both in the past and today. The book also deals with the concept of quality of life of words and aims to foster a discussion about the life cycle of scientific ideas. Textual data retrieved from large corpora pose interesting challenges for any data analysis method and today represent a growing area of research in many fields. New problems emerge from the growing availability of large databases and new methods are needed to retrieve significant information from those large information sources. This book can be used to explain how quantitative methods can be part of the research instrumentation and the "toolbox" of scholars of Humanities and Social Sciences. The book contains numerous examples and a description of the main methods in use, with references to literature and available software. Most of the chapters of the book have been written in a non-technical language for HSS researchers without mathematical, computer or statistical backgrounds.

This book addresses the current status, challenges and future directions of data-driven materials discovery and design. It presents the analysis and learning from data as a key theme in many science and cyber related applications. The challenging open questions as well as future directions in the application of data science to materials problems are sketched. Computational and experimental facilities today generate vast amounts of data at an unprecedented rate. The book gives guidance to discover new knowledge that enables materials innovation to address grand challenges in energy, environment and security, the clearer link needed between the data from these facilities and the theory and underlying science. The role of inference and optimization methods in distilling the data and constraining predictions using insights and results from theory is key to achieving the desired goals of real time analysis and feedback. Thus, the importance of this book lies in emphasizing that the full value of knowledge driven discovery using data can only be realized by integrating statistical and information sciences with materials science, which is increasingly dependent on high throughput and large scale computational and experimental data gathering efforts. This is especially the case as we enter a new era of big data in materials science with the planning of future experimental facilities such as the Linac Coherent Light Source at Stanford (LCLS-II), the European X-ray Free Electron Laser (EXFEL) and MaRIE (Matter Radiation in Extremes), the signature concept facility from Los Alamos National Laboratory. These facilities are expected to generate hundreds of terabytes to several petabytes of in situ spatially and temporally resolved data per sample. The questions that then arise include how we can learn from the data to accelerate the processing and analysis of reconstructed microstructure, rapidly map spatially resolved properties from high throughput data, devise diagnostics for pattern detection, and guide experiments towards desired targeted properties. The authors are an interdisciplinary group of leading experts who bring the excitement of the nascent and rapidly emerging field of materials informatics to the reader.

This book provides a review of advanced topics relating to the theory, research, analysis and implementation in the context of big data platforms and their applications, with a focus on methods, techniques, and performance evaluation. The explosive growth in the volume, speed, and variety of data being produced every day requires a continuous increase in the processing speeds of servers and of entire network infrastructures, as well as new resource management models. This poses significant challenges (and provides striking development opportunities) for data intensive and high-performance computing, i.e., how to efficiently turn extremely large datasets into valuable information and meaningful knowledge. The task of context data management is further complicated by the variety of sources such data derives from, resulting in different data formats, with varying storage, transformation, delivery, and archiving requirements. At the same time rapid responses are needed for real-time applications. With the emergence of cloud infrastructures, achieving highly scalable data management in such contexts is a critical problem, as the overall application performance is highly dependent on the properties of the data management service.

Pattern Recognition on Oriented Matroids covers a range of innovative problems in combinatorics, poset and graph theories, optimization, and number theory that constitute a far-reaching extension of the arsenal of committee methods in pattern recognition. The groundwork for the modern committee theory was laid in the mid-1960s, when it was shown that the familiar notion of solution to a feasible system of linear inequalities has ingenious analogues which can serve as collective solutions to infeasible systems. A hierarchy of dialects in the language of mathematics, for instance, open cones in the context of linear inequality systems, regions of hyperplane arrangements, and maximal covectors (or topes) of oriented matroids, provides an excellent opportunity to take a fresh look at the infeasible system of homogeneous strict linear inequalities - the standard working model for the contradictory two-class pattern recognition problem in its geometric setting. The universal language of oriented matroid theory considerably simplifies a structural and enumerative analysis of applied aspects of the infeasibility phenomenon. The present book is devoted to several selected topics in the emerging theory of pattern recognition on oriented matroids: the questions of existence and applicability of matroidal generalizations of committee decision rules and related graph-theoretic constructions to oriented matroids with very weak restrictions on their structural properties; a study (in which, in particular, interesting subsequences of the Farey sequence appear naturally) of the hierarchy of the corresponding tope committees; a description of the three-tope committees that are the most attractive approximation to the notion of solution to an infeasible system of linear constraints; an application of convexity in oriented matroids as well as blocker constructions in combinatorial optimization and in poset theory to enumerative problems on tope committees; an attempt to clarify how elementary changes (one-element reorientations) in an oriented matroid affect the family of its tope committees; a discrete Fourier analysis of the important family of critical tope committees through rank and distance relations in the tope poset and the tope graph; the characterization of a key combinatorial role played by the symmetric cycles in hypercube graphs. Contents Oriented Matroids, the Pattern Recognition Problem, and Tope Committees Boolean Intervals Dehn-Sommerville Type Relations Farey Subsequences Blocking Sets of Set Families, and Absolute Blocking Constructions in Posets Committees of Set Families, and Relative Blocking Constructions in Posets Layers of Tope Committees Three-Tope Committees Halfspaces, Convex Sets, and Tope Committees Tope Committees and Reorientations of Oriented Matroids Topes and Critical Committees Critical Committees and Distance Signals Symmetric Cycles in the Hypercube Graphs

Clinical Decision Support and Beyond: Progress and Opportunities in Knowledge-Enhanced Health and Healthcare, now in its third edition, discusses the underpinnings of effective, reliable, and easy-to-use clinical decision support systems at the point of care as a productive way of managing the flood of data, knowledge, and misinformation when providing patient care. Incorporating CDS into electronic health record systems has been underway for decades; however its complexities, costs, and user resistance have lagged its potential. Thus it is of utmost importance to understand the process in detail, to take full advantage of its capabilities. The book expands and updates the content of the previous edition, and discusses topics such as integration of CDS into workflow, context-driven anticipation of needs for CDS, new forms of CDS derived from data analytics, precision medicine, population health, integration of personal monitoring, and patient-facing CDS. In addition, it discusses population health management, public health CDS and CDS to help reduce health disparities. It is a valuable resource for clinicians, practitioners, students and members of medical and biomedical fields who are interested to learn more about the potential of clinical decision support to improve health and wellness and the quality of health care.

This textbook presents the main principles of visual analytics and describes techniques and approaches that have proven their utility and can be readily reproduced. Special emphasis is placed on various instructive examples of analyses, in which the need for and the use of visualisations are explained in detail. The book begins by introducing the main ideas and concepts of visual analytics and explaining why it should be considered an essential part of data science methodology and practices. It then describes the general principles underlying the visual analytics approaches, including those on appropriate visual representation, the use of interactive techniques, and classes of computational methods. It continues with discussing how to use visualisations for getting aware of data properties that need to be taken into account and for detecting possible data quality issues that may impair the analysis. The second part of the book describes visual analytics methods and workflows, organised by various data types including multidimensional data, data with spatial and temporal components, data describing binary relationships, texts, images and video. For each data type, the specific properties and issues are explained, the relevant analysis tasks are discussed, and appropriate methods and procedures are introduced. The focus here is not on the micro-level details of how the methods work, but on how the methods can be used and how they can be applied to data. The limitations of the methods are also discussed and possible pitfalls are identified. The textbook is intended for students in data science and, more generally, anyone doing or planning to do practical data analysis. It includes numerous examples demonstrating how visual analytics techniques are used and how they can help analysts to understand the properties of data, gain insights into the subject reflected in the data, and build good models that can be trusted. Based on several years of teaching related courses at the City, University of London, the University of Bonn and TU Munich, as well as industry training at the Fraunhofer Institute IAIS and numerous summer schools, the main content is complemented by sample datasets and detailed, illustrated descriptions of exercises to practice applying visual analytics methods and workflows.

With the onset of massive cosmological data collection through media such as the Sloan Digital Sky Survey (SDSS), galaxy classification has been accomplished for the most part with the help of citizen science communities like Galaxy Zoo. Seeking the wisdom of the crowd for such Big Data processing has proved extremely beneficial. However, an analysis of one of the Galaxy Zoo morphological classification data sets has shown that a significant majority of all classified galaxies are labelled as Uncertain .

This book reports on how to use data mining, more specifically clustering, to identify galaxies that the public has shown some degree of uncertainty for as to whether they belong to one morphology type or another. The book shows the importance of transitions between different data mining techniques in an insightful workflow. It demonstrates that Clustering enables to identify discriminating features in the analysed data sets, adopting a novel feature selection algorithms called Incremental Feature Selection (IFS). The book shows the use of state-of-the-art classification techniques, Random Forests and Support Vector Machines to validate the acquired results. It is concluded that a vast majority of these galaxies are, in fact, of spiral morphology with a small subset potentially consisting of stars, elliptical galaxies or galaxies of other morphological variants."

This book reviews the latest developments in nature-inspired computation, with a focus on the cross-disciplinary applications in data mining and machine learning. Data mining, machine learning and nature-inspired computation are current hot research topics due to their importance in both theory and practical applications. Adopting an application-focused approach, each chapter introduces a specific topic, with detailed descriptions of relevant algorithms, extensive literature reviews and implementation details. Covering topics such as nature-inspired algorithms, swarm intelligence, classification, clustering, feature selection, cybersecurity, learning algorithms over cloud, extreme learning machines, object categorization, particle swarm optimization, flower pollination and firefly algorithms, and neural networks, it also presents case studies and applications, including classifications of crisis-related tweets, extraction of named entities in the Tamil language, performance-based prediction of diseases, and healthcare services. This book is both a valuable a reference resource and a practical guide for students, researchers and professionals in computer science, data and management sciences, artificial intelligence and machine learning.

This book provides information on data-driven infrastructure design, analytical approaches, and technological solutions with case studies for smart cities. This book aims to attract works on multidisciplinary research spanning across the computer science and engineering, environmental studies, services, urban planning and development, social sciences and industrial engineering on technologies, case studies, novel approaches, and visionary ideas related to data-driven innovative solutions and big data-powered applications to cope with the real world challenges for building smart cities.

The purpose of this book is to review the recent advances in E-health technologies and applications. In particular, the book investigates the recent advancements in physical design of medical devices, signal processing and emergent wireless technologies for E-health. In a second part, novel security and privacy solutions for IoT-based E-health applications are presented. The last part of the book is focused on applications, data mining and data analytics for E-health using artificial intelligence and cloud infrastructure. E-health has been an evolving concept since its inception, due to the numerous technologies that can be adapted to offer new innovative and efficient E-health applications. Recently, with the tremendous advancement of wireless technologies, sensors and wearable devices and software technologies, new opportunities have arisen and transformed the E-health field. Moreover, with the expansion of the Internet of Things, and the huge amount of data that connected E-health devices and applications are generating, it is also mandatory to address new challenges related to the data management, applications management and their security. Through this book, readers will be introduced to all these concepts. This book is intended for all practitioners (industrial and academic) interested in widening their knowledge in wireless communications and embedded technologies applied to E-health, cloud computing, artificial intelligence and big data for E-health applications and security issues in E-health.

With the growing popularity of "big data", the potential value of personal data has attracted more and more attention. Applications built on personal data can create tremendous social and economic benefits. Meanwhile, they bring serious threats to individual privacy. The extensive collection, analysis and transaction of personal data make it difficult for an individual to keep the privacy safe. People now show more concerns about privacy than ever before. How to make a balance between the exploitation of personal information and the protection of individual privacy has become an urgent issue. In this book, the authors use methodologies from economics, especially game theory, to investigate solutions to the balance issue. They investigate the strategies of stakeholders involved in the use of personal data, and try to find the equilibrium. The book proposes a user-role based methodology to investigate the privacy issues in data mining, identifying four different types of users, i.e. four user roles, involved in data mining applications. For each user role, the authors discuss its privacy concerns and the strategies that it can adopt to solve the privacy problems. The book also proposes a simple game model to analyze the interactions among data provider, data collector and data miner. By solving the equilibria of the proposed game, readers can get useful guidance on how to deal with the trade-off between privacy and data utility. Moreover, to elaborate the analysis on data collector's strategies, the authors propose a contract model and a multi-armed bandit model respectively. The authors discuss how the owners of data (e.g. an individual or a data miner) deal with the trade-off between privacy and utility in data mining. Specifically, they study users' strategies in collaborative filtering based recommendation system and distributed classification system. They built game models to formulate the interactions among data owners, and propose learning algorithms to find the equilibria.

This book presents a comprehensive and up-to-date treatise of a range of methodological and algorithmic issues. It also discusses implementations and case studies, identifies the best design practices, and assesses data analytics business models and practices in industry, health care, administration and business.Data science and big data go hand in hand and constitute a rapidly growing area of research and have attracted the attention of industry and business alike. The area itself has opened up promising new directions of fundamental and applied research and has led to interesting applications, especially those addressing the immediate need to deal with large repositories of data and building tangible, user-centric models of relationships in data. Data is the lifeblood of today's knowledge-driven economy.Numerous data science models are oriented towards end users and along with the regular requirements for accuracy (which are present in any modeling), come the requirements for ability to process huge and varying data sets as well as robustness, interpretability, and simplicity (transparency). Computational intelligence with its underlying methodologies and tools helps address data analytics needs.The book is of interest to those researchers and practitioners involved in data science, Internet engineering, computational intelligence, management, operations research, and knowledge-based systems.

With the improvements of artificial intelligence, processor speeds and database sizes, the rapidly expanding field of data mining continues to provide advancing methods for managing databases and gaining knowledge.Developments in Data Extraction, Management, and Analysis is an essential collection of research on the area of data mining and analytics. Presenting the most recent perspectives on data mining subjects and current issues, this book is useful for practitioners and academics alike.

This book presents an exhaustive and timely review of key research work on fuzzy XML data management, and provides readers with a comprehensive resource on the state-of-the art tools and theories in this fast growing area. Topics covered in the book include: representation of fuzzy XML, query of fuzzy XML, fuzzy database models, extraction of fuzzy XML from fuzzy database models, reengineering of fuzzy XML into fuzzy database models, and reasoning of fuzzy XML. The book is intended as a reference guide for researchers, practitioners and graduate students working and/or studying in the field of Web Intelligence, as well as for data and knowledge engineering professionals seeking new approaches to replace traditional methods, which may be unnecessarily complex or even unproductive.

This edited volume addresses the vast challenges of adapting Online Social Media (OSM) to developing research methods and applications. The topics cover generating realistic social network topologies, awareness of user activities, topic and trend generation, estimation of user attributes from their social content, behavior detection, mining social content for common trends, identifying and ranking social content sources, building friend-comprehension tools, and many others. Each of the ten chapters tackle one or more of these issues by proposing new analysis methods or new visualization techniques, or both, for famous OSM applications such as Twitter and Facebook. This collection of contributed chapters address these challenges. Online Social Media has become part of the daily lives of hundreds of millions of users generating an immense amount of 'social content'. Addressing the challenges that stem from this wide adaptation of OSM is what makes this book a valuable contribution to the field of social networks.

This volume conveys some of the surprises, puzzles and success stories in high-dimensional and complex data analysis and related fields. Its peer-reviewed contributions showcase recent advances in variable selection, estimation and prediction strategies for a host of useful models, as well as essential new developments in the field. The continued and rapid advancement of modern technology now allows scientists to collect data of increasingly unprecedented size and complexity. Examples include epigenomic data, genomic data, proteomic data, high-resolution image data, high-frequency financial data, functional and longitudinal data, and network data. Simultaneous variable selection and estimation is one of the key statistical problems involved in analyzing such big and complex data. The purpose of this book is to stimulate research and foster interaction between researchers in the area of high-dimensional data analysis. More concretely, its goals are to: 1) highlight and expand the breadth of existing methods in big data and high-dimensional data analysis and their potential for the advancement of both the mathematical and statistical sciences; 2) identify important directions for future research in the theory of regularization methods, in algorithmic development, and in methodologies for different application areas; and 3) facilitate collaboration between theoretical and subject-specific researchers.

The book studies the existing and potential connections between Social Network Analysis (SNA) and Formal Concept Analysis (FCA) by showing how standard SNA techniques, usually based on graph theory, can be supplemented by FCA methods, which rely on lattice theory. The book presents contributions to the following areas: acquisition of terminological knowledge from social networks, knowledge communities, individuality computation, other types of FCA-based analysis of bipartite graphs (two-mode networks), multimodal clustering, community detection and description in one-mode and multi-mode networks, adaptation of the dual-projection approach to weighted bipartite graphs, extensions to the Kleinberg's HITS algorithm as well as attributed graph analysis.

This fully updated book collects numerous data mining techniques, reflecting the acceleration and diversity of the development of data-driven approaches to the life sciences. The first half of the volume examines genomics, particularly metagenomics and epigenomics, which promise to deepen our knowledge of genes and genomes, while the second half of the book emphasizes metabolism and the metabolome as well as relevant medicine-oriented subjects. Written for the highly successful Methods in Molecular Biology series, chapters include the kind of detail and expert implementation advice that is useful for getting optimal results. Authoritative and practical, Data Mining for Systems Biology: Methods and Protocols, Second Edition serves as an ideal resource for researchers of biology and relevant fields, such as medical, pharmaceutical, and agricultural sciences, as well as for the scientists and engineers who are working on developing data-driven techniques, such as databases, data sciences, data mining, visualization systems, and machine learning or artificial intelligence that now are central to the paradigm-altering discoveries being made with a higher frequency.

This book presents the combined proceedings of the 7th International Conference on Computer Science and its Applications (CSA-15) and the International Conference on Ubiquitous Information Technologies and Applications (CUTE 2015), both held in Cebu, Philippines, December 15 - 17, 2015. The aim of these two meetings was to promote discussion and interaction among academics, researchers and professionals in the field of computer science covering topics including mobile computing, security and trust management, multimedia systems and devices, networks and communications, databases and data mining, and ubiquitous computing technologies such as ubiquitous communication and networking, ubiquitous software technology, ubiquitous systems and applications, security and privacy. These proceedings reflect the state-of-the-art in the development of computational methods, numerical simulations, error and uncertainty analysis and novel applications of new processing techniques in engineering, science, and other disciplines related to computer science.

Whether you are brand new to data mining or working on your tenth predictive analytics project, "Commercial Data Mining" will be there for you as an accessible reference outlining the entire process and related themes. In this book, you'll learn that your organization does not need a huge volume of data or a Fortune 500 budget to generate business using existing information assets. Expert author David Nettleton guides you through the process from beginning to end and covers everything from business objectives to data sources, and selection to analysis and predictive modeling.

"Commercial Data Mining" includes case studies and practical examples from Nettleton's more than 20 years of commercial experience. Real-world cases covering customer loyalty, cross-selling, and audience prediction in industries including insurance, banking, and media illustrate the concepts and techniques explained throughout the book.
Illustrates cost-benefit evaluation of potential projects Includes vendor-agnostic advice on what to look for in off-the-shelf solutions as well as tips on building your own data mining tools Approachable reference can be read from cover to cover by readers of all experience levelsIncludes practical examples and case studies as well as actionable business insights from author's own experience

This text integrates different mobility data handling processes, from database management to multi-dimensional analysis and mining, into a unified presentation driven by the spectrum of requirements raised by real-world applications. It presents a step-by-step methodology to understand and exploit mobility data: collecting and cleansing data, storage in Moving Object Database (MOD) engines, indexing, processing, analyzing and mining mobility data. Emerging issues, such as semantic and privacy-aware querying and mining as well as distributed data processing, are also covered. Theoretical presentation is smoothly interchanged with hands-on exercises and case studies involving an actual MOD engine. The authors are established experts who address both theoretical and practical dimensions of the field but also present valuable prototype software. The background context, clear explanations and sample exercises make this an ideal textbook for graduate students studying database management, data mining and geographic information systems.

This book is devoted to the modeling and understanding of complex urban systems. This second volume of Understanding Complex Urban Systems focuses on the challenges of the modeling tools, concerning, e.g., the quality and quantity of data and the selection of an appropriate modeling approach. It is meant to support urban decision-makers-including municipal politicians, spatial planners, and citizen groups-in choosing an appropriate modeling approach for their particular modeling requirements. The contributors to this volume are from different disciplines, but all share the same goal: optimizing the representation of complex urban systems. They present and discuss a variety of approaches for dealing with data-availability problems and finding appropriate modeling approaches-and not only in terms of computer modeling. The selection of articles featured in this volume reflect a broad variety of new and established modeling approaches such as: - An argument for using Big Data methods in conjunction with Agent-based Modeling; - The introduction of a participatory approach involving citizens, in order to utilize an Agent-based Modeling approach to simulate urban-growth scenarios; - A presentation of semantic modeling to enable a flexible application of modeling methods and a flexible exchange of data; - An article about a nested-systems approach to analyzing a city's interdependent subsystems (according to these subsystems' different velocities of change); - An article about methods that use Luhmann's system theory to characterize cities as systems that are composed of flows; - An article that demonstrates how the Sen-Nussbaum Capabilities Approach can be used in urban systems to measure household well-being shifts that occur in response to the resettlement of urban households; - A final article that illustrates how Adaptive Cycles of Complex Adaptive Systems, as well as innovation, can be applied to gain a better understanding of cities and to promote more resilient and more sustainable urban futures.

This book presents a comprehensive report on the evolution of Fuzzy Logic since its formulation in Lotfi Zadeh's seminal paper on "fuzzy sets," published in 1965. In addition, it features a stimulating sampling from the broad field of research and development inspired by Zadeh's paper. The chapters, written by pioneers and prominent scholars in the field, show how fuzzy sets have been successfully applied to artificial intelligence, control theory, inference, and reasoning. The book also reports on theoretical issues; features recent applications of Fuzzy Logic in the fields of neural networks, clustering, data mining and software testing; and highlights an important paradigm shift caused by Fuzzy Logic in the area of uncertainty management. Conceived by the editors as an academic celebration of the fifty years' anniversary of the 1965 paper, this work is a must-have for students and researchers willing to get an inspiring picture of the potentialities, limitations, achievements and accomplishments of Fuzzy Logic-based systems.