Adaptive Stream Mining

This book is a significant contribution to the subject of mining time-changing data streams and addresses the design of learning algorithms for this purpose. It introduces new contributions on several different aspects of the problem, identifying research opportunities and increasing the scope for applications. It also includes an in-depth study of stream mining and a theoretical analysis of proposed methods and algorithms. The first section is concerned with the use of an adaptive sliding window algorithm (ADWIN). Since this has rigorous performance guarantees, using it in place of counters or accumulators, it offers the possibility of extending such guarantees to learning and mining algorithms not initially designed for drifting data. Testing with several methods, including Naïve Bayes, clustering, decision trees and ensemble methods, is discussed as well. The second part of the book describes a formal study of connected acyclic graphs, or 'trees', from the point of view of closure-based mining, presenting efficient algorithms for subtree testing and for mining ordered and unordered frequent closed trees. Lastly, a general methodology to identify closed patterns in a data stream is outlined. This is applied to develop an incremental method, a sliding-window based method, and a method that mines closed trees adaptively from data streams. These are used to introduce classification methods for tree data streams.

A hands-on approach to tasks and techniques in data stream mining and real-time analytics, with examples in MOA, a popular freely available open-source software framework. Today many information sources—including sensor networks, financial markets, social networks, and healthcare monitoring—are so-called data streams, arriving sequentially and at high speed. Analysis must take place in real time, with partial data and without the capacity to store the entire data set. This book presents algorithms and techniques used in data stream mining and real-time analytics. Taking a hands-on approach, the book demonstrates the techniques using MOA (Massive Online Analysis), a popular, freely available open-source software framework, allowing readers to try out the techniques after reading the explanations. The book first offers a brief introduction to the topic, covering big data mining, basic methodologies for mining data streams, and a simple example of MOA. More detailed discussions follow, with chapters on sketching techniques, change, classification, ensemble methods, regression, clustering, and frequent pattern mining. Most of these chapters include exercises, an MOA-based lab session, or both. Finally, the book discusses the MOA software, covering the MOA graphical user interface, the command line, use of its API, and the development of new methods within MOA. The book will be an essential reference for readers who want to use data stream mining as a tool, researchers in innovation or data stream mining, and programmers who want to create new algorithms for MOA.

This book constitutes the refereed proceedings of the 8th Pacific-Asia Conference on Knowledge Discovery and Data mining, PAKDD 2004, held in Sydney, Australia in May 2004. The 50 revised full papers and 31 revised short papers presented were carefully reviewed and selected from a total of 238 submissions. The papers are organized in topical sections on classification; clustering; association rules; novel algorithms; event mining, anomaly detection, and intrusion detection; ensemble learning; Bayesian network and graph mining; text mining; multimedia mining; text mining and Web mining; statistical methods, sequential data mining, and time series mining; and biomedical data mining.

The First Asian Conference on Machine Learning (ACML 2009) was held at Nanjing, China during November 2–4, 2009.This was the ?rst edition of a series of annual conferences which aim to provide a leading international forum for researchers in machine learning and related ?elds to share their new ideas and research ?ndings. This year we received 113 submissions from 18 countries and regions in Asia, Australasia, Europe and North America. The submissions went through a r- orous double-blind reviewing process. Most submissions received four reviews, a few submissions received ?ve reviews, while only several submissions received three reviews. Each submission was handled by an Area Chair who coordinated discussions among reviewers and made recommendation on the submission. The Program Committee Chairs examined the reviews and meta-reviews to further guarantee the reliability and integrity of the reviewing process. Twenty-nine - pers were selected after this process. To ensure that important revisions required by reviewers were incorporated into the ?nal accepted papers, and to allow submissions which would have - tential after a careful revision, this year we launched a “revision double-check” process. In short, the above-mentioned 29 papers were conditionally accepted, and the authors were requested to incorporate the “important-and-must”re- sionssummarizedbyareachairsbasedonreviewers’comments.Therevised?nal version and the revision list of each conditionally accepted paper was examined by the Area Chair and Program Committee Chairs. Papers that failed to pass the examination were ?nally rejected.

This book presents a unique approach to stream data mining. Unlike the vast majority of previous approaches, which are largely based on heuristics, it highlights methods and algorithms that are mathematically justified. First, it describes how to adapt static decision trees to accommodate data streams; in this regard, new splitting criteria are developed to guarantee that they are asymptotically equivalent to the classical batch tree. Moreover, new decision trees are designed, leading to the original concept of hybrid trees. In turn, nonparametric techniques based on Parzen kernels and orthogonal series are employed to address concept drift in the problem of non-stationary regressions and classification in a time-varying environment. Lastly, an extremely challenging problem that involves designing ensembles and automatically choosing their sizes is described and solved. Given its scope, the book is intended for a professional audience of researchers and practitioners who deal with stream data, e.g. in telecommunication, banking, and sensor networks.

Searching Multimedia Databases by Content bridges the gap between the database and signal processing communities by providing the necessary background information for the reader and presenting it along with the intuition and mechanics of the best existing tools in each area. The first half of Searching Multimedia Databases by Content reviews the most successful database access methods, in increasing complexity, reaching up to spatial access methods and text retrieval. In all cases, the emphasis is on practical approaches that have been incorporated in commercial systems, or that seem very promising. The second half of the book uses the above access methods to achieve fast searching in a database of signals. A general methodology is presented, which suggests extracting a few good features from each multimedia object, thus mapping objects into points in a metric space. Finally, the book concludes by presenting some recent successful applications of the methodology on time series and color images. Searching Multimedia Databases by Content is targeted towards researchers and developers of multimedia systems. The book can also serve as a textbook for a graduate course on multimedia searching, covering both access methods as well as the basics of signal processing.

Since the beginning of the Internet age and the increased use of ubiquitous computing devices, the large volume and continuous flow of distributed data have imposed new constraints on the design of learning algorithms. Exploring how to extract knowledge structures from evolving and time-changing data, Knowledge Discovery from Data Streams presents

This comprehensive reference consists of 18 chapters from prominent researchers in the field. Each chapter is self-contained, and synthesizes one aspect of frequent pattern mining. An emphasis is placed on simplifying the content, so that students and practitioners can benefit from the book. Each chapter contains a survey describing key research on the topic, a case study and future directions. Key topics include: Pattern Growth Methods, Frequent Pattern Mining in Data Streams, Mining Graph Patterns, Big Data Frequent Pattern Mining, Algorithms for Data Clustering and more. Advanced-level students in computer science, researchers and practitioners from industry will find this book an invaluable reference.