"Foundations of Data Mining and Knowledge Discovery" contains the latest results and new directions in data mining research. Data mining, which integrates various technologies, including computational intelligence, database and knowledge management, machine learning, soft computing, and statistics, is one of the fastest growing fields in computer science. Although many data mining techniques have been developed, further development of the field requires a close examination of its foundations. This volume presents the results of investigations into the foundations of the discipline, and represents the state of the art for much of the current research. This book will prove extremely valuable and fruitful for data mining researchers, no matter whether they would like to uncover the fundamental principles behind data mining, or apply the theories to practical applications.

This book provides a readable and elegant presentation of the principles of anomaly detection,providing an easy introduction for newcomers to the field. A large number of algorithms are succinctly described, along with a presentation of their strengths and weaknesses. The authors also cover algorithms that address different kinds of problems of interest with single and multiple time series data and multi-dimensional data. New ensemble anomaly detection algorithms are described, utilizing the benefits provided by diverse algorithms, each of which work well on some kinds of data. With advancements in technology and the extensive use of the internet as a medium for communications and commerce, there has been a tremendous increase in the threats faced by individuals and organizations from attackers and criminal entities. Variations in the observable behaviors of individuals (from others and from their own past behaviors) have been found to be useful in predicting potential problems of various kinds. Hence computer scientists and statisticians have been conducting research on automatically identifying anomalies in large datasets. This book will primarily target practitioners and researchers who are newcomers to the area of modern anomaly detection techniques. Advanced-level students in computer science will also find this book helpful with their studies.

This book explores an approach to social robotics based solely on autonomous unsupervised techniques and positions it within a structured exposition of related research in psychology, neuroscience, HRI, and data mining. The authors present an autonomous and developmental approach that allows the robot to learn interactive behavior by imitating humans using algorithms from time-series analysis and machine learning. The first part provides a comprehensive and structured introduction to time-series analysis, change point discovery, motif discovery and causality analysis focusing on possible applicability to HRI problems. Detailed explanations of all the algorithms involved are provided with open-source implementations in MATLAB enabling the reader to experiment with them. Imitation and simulation are the key technologies used to attain social behavior autonomously in the proposed approach. Part two gives the reader a wide overview of research in these areas in psychology, and ethology. Based on this background, the authors discuss approaches to endow robots with the ability to autonomously learn how to be social. Data Mining for Social Robots will be essential reading for graduate students and practitioners interested in social and developmental robotics.

The field of data mining has made significant and far-reaching advances over the past three decades.Because of its potential power for solving complex problems, data mining has been successfully applied to diverse areas such as business, engineering, social media, and biological science. Many of these applications search for patterns in complex structural information. In biomedicine for example, modeling complex biological systems requires linking knowledge across many levels of science, from genes to disease. Further, the data characteristics of the problems have also grown from static to dynamic and spatiotemporal, complete to incomplete, and centralized to distributed, and grow in their scope and size (this is known as "big data"). The effective integration of big data for decision-making also requires privacy preservation.

The contributions to this monograph summarize the advances of data mining in the respective fields. This volume consists of nine chapters that address subjects ranging from mining data from opinion, spatiotemporal databases, discriminative subgraph patterns, path knowledge discovery, social media, and privacy issues to the subject of computation reduction via binary matrix factorization."

This book presents an overview of techniques for discovering high-utility patterns (patterns with a high importance) in data. It introduces the main types of high-utility patterns, as well as the theory and core algorithms for high-utility pattern mining, and describes recent advances, applications, open-source software, and research opportunities. It also discusses several types of discrete data, including customer transaction data and sequential data. The book consists of twelve chapters, seven of which are surveys presenting the main subfields of high-utility pattern mining, including itemset mining, sequential pattern mining, big data pattern mining, metaheuristic-based approaches, privacy-preserving pattern mining, and pattern visualization. The remaining five chapters describe key techniques and applications, such as discovering concise representations and regular patterns.

Managing and Mining Graph Data is a comprehensive survey book in graph management and mining. It contains extensive surveys on a variety of important graph topics such as graph languages, indexing, clustering, data generation, pattern mining, classification, keyword search, pattern matching, and privacy. It also studies a number of domain-specific scenarios such as stream mining, web graphs, social networks, chemical and biological data. The chapters are written by well known researchers in the field, and provide a broad perspective of the area. This is the first comprehensive survey book in the emerging topic of graph data processing.
Managing and Mining Graph Data is designed for a varied audience composed of professors, researchers and practitioners in industry. This volume is also suitable as a reference book for advanced-level database students in computer science and engineering.

This book explores community dynamics within social media. Using Wikipedia as an example, the volume explores communities that rely upon commons-based peer production. Fundamental theoretical principles spanning such domains as organizational configurations, leadership roles, and social evolutionary theory are developed. In the context of Wikipedia, these theories explain how a functional elite of highly productive editors has emerged and why they are responsible for a majority of the content. It explains how the elite shapes the project and how this group tends to become stable and increasingly influential over time. Wikipedia has developed a new and resilient social hierarchy, an adhocracy, which combines features of traditional and new, online, social organizations. The book presents a set of practical approaches for using these theories in real-world practice. This work fundamentally changes the way we think about social media leadership and evolution, emphasizing the crucial contributions of leadership, of elite social roles, and of group global structure to the overall success and stability of large social media projects. Written in an accessible and direct style, the book will be of interest to academics as well as professionals with an interest in social media and commons-based peer production processes.

Multi-database mining has been recognized recently as an important and strategically essential area of research in data mining. In this book, we discuss various issues regarding the systematic and efficient development of multi-database mining applications. It explains how systematically one could prepare data warehouses at different branches. As appropriate multi-database mining technique is essential to develop better applications. Also, the efficiency of a multi-database mining application could be improved by processing more patterns in the application. A faster algorithm could also play an important role in developing a better application. Thus the efficiency of a multi-database mining application could be enhanced by choosing an appropriate multi-database mining model, an appropriate pattern synthesizing technique, a better pattern representation technique, and an efficient algorithm for solving the problem. This book illustrates each of these issues either in the context of a specific problem, or in general.

This is the first study of Boko Haram that brings advanced data-driven, machine learning models to both learn models capable of predicting a wide range of attacks carried out by Boko Haram, as well as develop data-driven policies to shape Boko Haram's behavior and reduce attacks by them. This book also identifies conditions that predict sexual violence, suicide bombings and attempted bombings, abduction, arson, looting, and targeting of government officials and security installations. After reducing Boko Haram's history to a spreadsheet containing monthly information about different types of attacks and different circumstances prevailing over a 9 year period, this book introduces Temporal Probabilistic (TP) rules that can be automatically learned from data and are easy to explain to policy makers and security experts. This book additionally reports on over 1 year of forecasts made using the model in order to validate predictive accuracy. It also introduces a policy computation method to rein in Boko Haram's attacks. Applied machine learning researchers, machine learning experts and predictive modeling experts agree that this book is a valuable learning asset. Counter-terrorism experts, national and international security experts, public policy experts and Africa experts will also agree this book is a valuable learning tool.

Welcome to the 6th International Conference on Open Source Systems of the IFIP Working Group 2. 13. This year was the ?rst time this international conf- ence was held in North America. We had a large number of high-quality papers, highlyrelevantpanelsandworkshops, acontinuationofthepopulardoctoralc- sortium, and multiple distinguished invited speakers. The success of OSS 2010 was only possible because an Organizing Committee, a Program Committee, Workshop and Doctoral Committees, and authors of research manuscripts from over 25 countries contributed their time and interest to OSS 2010. In the spirit of the communities we study, you self-organized, volunteered, and contributed to this important research forum studying free, libre, open source software and systems. We thank you Despite our modest success, we have room to improve and grow our conf- ence and community. At OSS 2010 we saw little or no participation from large portions of the world, including Latin America, Africa, China, and India. But opportunitiestoexpandarepossible. InJapan, weseeahotspotofparticipation led by Tetsuo Noda and his colleagues, both with full-paper submissions and a workshopon"OpenSourcePolicyandPromotionofITIndustries inEastAsia. " The location of OSS 2011 in Salvador, Brazil, will hopefully result in signi?cant participation from researchers in Brazil - already a strong user of OSS - and otherSouthAmericancountries. UndertheleadershipofMeganSquire, Publicity Chair, we recruited RegionalPublicity Co-chairscovering Japan (Tetsuo Noda), Africa(SulaymanSowe), the MiddleEastandSouthAsia(FaheenAhmed), R- sia and Eastern Europe (Alexey Khoroshilov), Western Europe (Yeliz Eseryel), UK and Ireland (Andrea Capiluppi), and the Nordic countries (Bj] orn Lundell)."

The present book outlines a new approach to possibilistic clustering in which the sought clustering structure of the set of objects is based directly on the formal definition of fuzzy cluster and the possibilistic memberships are determined directly from the values of the pairwise similarity of objects. The proposed approach can be used for solving different classification problems. Here, some techniques that might be useful at this purpose are outlined, including a methodology for constructing a set of labeled objects for a semi-supervised clustering algorithm, a methodology for reducing analyzed attribute space dimensionality and a methods for asymmetric data processing. Moreover, a technique for constructing a subset of the most appropriate alternatives for a set of weak fuzzy preference relations, which are defined on a universe of alternatives, is described in detail, and a method for rapidly prototyping the Mamdani s fuzzy inference systems is introduced. This book addresses engineers, scientists, professors, students and post-graduate students, who are interested in and work with fuzzy clustering and its applications

The authors focus on the mathematical models and methods that support most data mining applications and solution techniques.

Observational calculi were introduced in the 1960's as a tool of logic of discovery. Formulas of observational calculi correspond to assertions on analysed data. Truthfulness of suitable assertions can lead to acceptance of new scientific hypotheses. The general goal was to automate the process of discovery of scientific knowledge using mathematical logic and statistics. The GUHA method for producing true formulas of observational calculi relevant to the given problem of scientific discovery was developed. Theoretically interesting and practically important results on observational calculi were achieved. Special attention was paid to formulas - couples of Boolean attributes derived from columns of the analysed data matrix. Association rules introduced in the 1990's can be seen as a special case of such formulas. New results on logical calculi and association rules were achieved. They can be seen as a logic of association rules. This can contribute to solving contemporary challenging problems of data mining research and practice. The book covers thoroughly the logic of association rules and puts it into the context of current research in data mining. Examples of applications of theoretical results to real problems are presented. New open problems and challenges are listed. Overall, the book is a valuable source of information for researchers as well as for teachers and students interested in data mining.

This book reports on advanced theories and cutting-edge applications in the field of soft computing. The individual chapters, written by leading researchers, are based on contributions presented during the 4th World Conference on Soft Computing, held May 25-27, 2014, in Berkeley. The book covers a wealth of key topics in soft computing, focusing on both fundamental aspects and applications. The former include fuzzy mathematics, type-2 fuzzy sets, evolutionary-based optimization, aggregation and neural networks, while the latter include soft computing in data analysis, image processing, decision-making, classification, series prediction, economics, control, and modeling. By providing readers with a timely, authoritative view on the field, and by discussing thought-provoking developments and challenges, the book will foster new research directions in the diverse areas of soft computing.

This book has a collection of articles written by Big Data experts to describe some of the cutting-edge methods and applications from their respective areas of interest, and provides the reader with a detailed overview of the field of Big Data Analytics as it is practiced today. The chapters cover technical aspects of key areas that generate and use Big Data such as management and finance; medicine and healthcare; genome, cytome and microbiome; graphs and networks; Internet of Things; Big Data standards; bench-marking of systems; and others. In addition to different applications, key algorithmic approaches such as graph partitioning, clustering and finite mixture modelling of high-dimensional data are also covered. The varied collection of themes in this volume introduces the reader to the richness of the emerging field of Big Data Analytics.

This book explores the concepts of data mining and data warehousing, a promising and flourishing frontier in database systems, and presents a broad, yet in-depth overview of the field of data mining. Data mining is a multidisciplinary field, drawing work from areas including database technology, artificial intelligence, machine learning, neural networks, statistics, pattern recognition, knowledge based systems, knowledge acquisition, information retrieval, high performance computing and data visualization.

This edited collection discusses the emerging topics in statistical modeling for biomedical research. Leading experts in the frontiers of biostatistics and biomedical research discuss the statistical procedures, useful methods, and their novel applications in biostatistics research. Interdisciplinary in scope, the volume as a whole reflects the latest advances in statistical modeling in biomedical research, identifies impactful new directions, and seeks to drive the field forward. It also fosters the interaction of scholars in the arena, offering great opportunities to stimulate further collaborations. This book will appeal to industry data scientists and statisticians, researchers, and graduate students in biostatistics and biomedical science. It covers topics in: Next generation sequence data analysis Deep learning, precision medicine, and their applications Large scale data analysis and its applications Biomedical research and modeling Survival analysis with complex data structure and its applications.

Given its effective techniques and theories from various sources and fields, data science is playing a vital role in transportation research and the consequences of the inevitable switch to electronic vehicles. This fundamental insight provides a step towards the solution of this important challenge. Data Science and Simulation in Transportation Research highlights entirely new and detailed spatial-temporal micro-simulation methodologies for human mobility and the emerging dynamics of our society. Bringing together novel ideas grounded in big data from various data mining and transportation science sources, this book is an essential tool for professionals, students, and researchers in the fields of transportation research and data mining.

This book focuses on new and emerging data mining solutions that offer a greater level of transparency than existing solutions. Transparent data mining solutions with desirable properties (e.g. effective, fully automatic, scalable) are covered in the book. Experimental findings of transparent solutions are tailored to different domain experts, and experimental metrics for evaluating algorithmic transparency are presented. The book also discusses societal effects of black box vs. transparent approaches to data mining, as well as real-world use cases for these approaches.As algorithms increasingly support different aspects of modern life, a greater level of transparency is sorely needed, not least because discrimination and biases have to be avoided. With contributions from domain experts, this book provides an overview of an emerging area of data mining that has profound societal consequences, and provides the technical background to for readers to contribute to the field or to put existing approaches to practical use.

This book discusses the challenges facing current research in knowledge discovery and data mining posed by the huge volumes of complex data now gathered in various real-world applications (e.g., business process monitoring, cybersecurity, medicine, language processing, and remote sensing). The book consists of 14 chapters covering the latest research by the authors and the research centers they represent. It illustrates techniques and algorithms that have recently been developed to preserve the richness of the data and allow us to efficiently and effectively identify the complex information it contains. Presenting the latest developments in complex pattern mining, this book is a valuable reference resource for data science researchers and professionals in academia and industry.

The present text aims at helping the reader to maximize the reuse of information. Topics covered include tools and services for creating simple, rich, and reusable knowledge representations to explore strategies for integrating this knowledge into legacy systems. The reuse and integration are essential concepts that must be enforced to avoid duplicating the effort and reinventing the wheel each time in the same field. This problem is investigated from different perspectives. in organizations, high volumes of data from different sources form a big threat for filtering out the information for effective decision making. the reader will be informed of the most recent advances in information reuse and integration.

This proceedings volume introduces recent work on the storage, retrieval and visualization of spatial Big Data, data-intensive geospatial computing and related data quality issues. Further, it addresses traditional topics such as multi-scale spatial data representations, knowledge discovery, space-time modeling, and geological applications. Spatial analysis and data mining are increasingly facing the challenges of Big Data as more and more types of crowd sourcing spatial data are used in GIScience, such as movement trajectories, cellular phone calls, and social networks. In order to effectively manage these massive data collections, new methods and algorithms are called for. The book highlights state-of-the-art advances in the handling and application of spatial data, especially spatial Big Data, offering a cutting-edge reference guide for graduate students, researchers and practitioners in the field of GIScience.