Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Event mining : algorithms and applications
Li T., Chapman & Hall/CRC, Boca Raton, FL, 2016. 332 pp. Type: Book (978-1-466568-57-0)
Date Reviewed: May 11 2017

A very interesting and well-structured survey work, Event mining: algorithms and applications succeeds in presenting a thorough overview of the most important characteristics of the field of event processing. It is a unique and first-of-its-kind work, putting together prominent aspects and applications of event detection, interpretation, and use. Further, the book is very well balanced with respect to the selected content, size, and structure of each chapter. Each chapter uses a fairly identical table of contents and presents a thorough survey of the state-of-the-art approaches to handle each topic. This offers to the reader a detailed and succinct overview of the topic of interest, addressing various solutions of the problems that each chapter tackles. As a result, the book is packed with descriptions of methods to automatically extract, process, and interpret knowledge from events, defined as “real-world occurrences” that “typically involve changes of system states” and “are naturally temporal,” “often stored as logs.” It also abounds with technical details and thorough explanations about the operational aspects of the presented methods. This makes the book very good reading for scholars and practitioners in the event processing and system management areas.

Each of the book’s three parts is dedicated to a specific area: (1) “Event Generation and System Monitoring”; (2) “Pattern Discovery and Summarization”; and (3) “Applications.” Following an introductory chapter, the first part has two chapters dedicated to log interpretation. The second part contains three chapters dedicated to important aspects of event processing, such as event pattern mining, mining time lags, and log event summarization. The third part describes two applications based on event mining, one in the field of system management and the other in the field of social media using Twitter streams.

The two chapters of Part 1 are dedicated to methods to transform the heterogeneous and disparate log data into a uniform, structured canonical format that allows analytics over entire system behavior. The first chapter covers log event data integration, whereas the second chapter depicts event detection and interpretation as a component of system monitoring software. The two chapters discuss state-of-the-art approaches in a detailed technical manner and consequently present the technical contribution of each chapter by describing the proposed approach to log data integration and events detection and interpretation for automatic system monitoring.

The three chapters of Part 2 are concerned with processing, interpretation, and data analytics of event occurrences in logs. The first chapter turns to methods for discovering temporal patterns in big datasets. It discusses the different categories of event patterns and presents the data mining techniques suitable for discovering and handling them. It also outlines use case scenarios of system management applications where these approaches would be employed. The second chapter addresses a very important problem in predictive analytics and system analysis--mining time lags--including the interpretation of time sequences, and more precisely the detection and processing of time lags in temporal chains of events. This topic, being of crucial importance for the surveillance of system behavior, root-cause detection, fault-error-failure evidence, future behavior prediction, and trend analysis, has been studied in order to design methods for discovering time lags. The third chapter covers log event summarization.

The two chapters of Part 3 show two applications of event mining. The first chapter of Part 3 treats the problem of diagnostics in system operation to enable optimal system management. It offers several data-driven approaches that use event detection and interpretation to assist human administrators in diagnosing system behavior. The next chapter leaves the realm of system management and discusses a framework for social event summarization based on processing text from Twitter streams and detecting events in them. This chapter also outlines several approaches and methods that provide solutions to the difficult problem of event summarization from text.

With a very clean and distilled presentation; a very rich collection of references, figures, and examples; a very clear purpose and objectives; and a really detailed technical account about each of the selected topics, this book should be recommended to everyone who is technically savvy, is research and innovation oriented, and deals with logs or other event-rich media on a daily basis.

The single chapters are designed to stand alone, so experts, scholars, and engineers interested in attacking any of the topics covered by the book can turn to the corresponding chapter without considering the whole book.

Reviewer:  Mariana Damova Review #: CR145276 (1707-0423)
Bookmark and Share
  Featured Reviewer  
 
Data Mining (H.2.8 ... )
 
 
Content Analysis And Indexing (H.3.1 )
 
 
Knowledge Representation Formalisms And Methods (I.2.4 )
 
Would you recommend this review?
yes
no
Other reviews under "Data Mining": Date
Feature selection and effective classifiers
Deogun J. (ed), Choubey S., Raghavan V. (ed), Sever H. (ed) Journal of the American Society for Information Science 49(5): 423-434, 1998. Type: Article
May 1 1999
Rule induction with extension matrices
Wu X. (ed) Journal of the American Society for Information Science 49(5): 435-454, 1998. Type: Article
Jul 1 1998
Predictive data mining
Weiss S., Indurkhya N., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998. Type: Book (9781558604032)
Feb 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy