Li Event Mining

Theory, Algorithms, and Applications
Erscheinungsjahr 2015
ISBN: 978-1-4665-6859-4
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 332 Seiten

Reihe: Chapman & Hall/CRC Data Mining and Knowledge Discovery Series

This book presents a variety of approaches and applications for using data mining and machine learning techniques in the context of event mining. It offers an introductory overview on recent developments and discusses the challenges and common tasks that need to be addressed in practical applications. The book extensively covers complex event processing, event mining and summarization, and applications in ITIL event management, intelligent cloud management, health care, and smart homes.

Zielgruppe

Researchers, practitioners, and graduate students interested in event mining, data mining, and machine learning.

Autoren/Hrsg.

Li, Tao

Fachgebiete

• Wirtschaftswissenschaften Betriebswirtschaft Wirtschaftsmathematik und -statistik
• Mathematik | Informatik EDV | Informatik Informatik Theoretische Informatik
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Data Mining
• Wirtschaftswissenschaften Volkswirtschaftslehre Volkswirtschaftslehre Allgemein Wirtschaftsstatistik, Demographie

Inhaltsverzeichnis

Introduction

Tao Li
Data-Driven System Management

Overview of the Book

Content of the Book

Conclusion

Event Generation and System Monitoring

Event Generation: From Logs to Events

Liang Tang and Tao Li
Chapter Overview

Log Parser

Log Message Classification

Log Message Clustering

Tree Structure-Based Clustering

Message Signature-Based Event Generation

Summary

Optimizing System Monitoring Configurations

Liang Tang and Tao Li
Chapter Overview

Automatic Monitoring

Eliminating False Positive

Eliminating False Negative

Evaluation

Summary

Pattern Discovery and Summarization

Event Pattern Mining

Chunqiu Zeng and Tao Li
Introduction

Sequential Pattern

Fully Dependent Pattern

Partially Periodic Dependent Pattern

Mutually Dependent Pattern

T-Pattern

Frequent Episode

Event Burst

Rare Event

Correlated Pattern between Time Series and Event

A Case Study

Conclusion

Mining Time Lags

Chunqiu Zeng, Liang Tang, and Tao Li
Introduction

Nonparametric Method

Parametric Method

Empirical Studies

Summary

Log Event Summarization

Yexi Jiang and Tao Li
Introduction

Summarizing with Frequency Changing

Summarizing with Temporal Dynamics

Facilitating the Summarization Tasks

Summary

Applications

Data-Driven Applications in System Management

Wubai Zhou, Chunqiu Zeng, Liang Tang, and Tao Li
System Diagnosis

Searching Similar Sequential Textual Event Segments

Hierarchical Multi-Label Ticket Classification

Tickets Resolution Recommendation

Summary

Social Media Event Summarization Using Twitter Streams

Chao Shen and Tao Li
Introduction

Problem Formulation

Tweet Context Analysis

Sub-Event Detection Methods

Multi-Tweet Summarization

Experiments

Conclusion and Future Work

A Glossary appears at the end of each chapter.