High Performance Discovery in Time Series: Techniques and Case Studies
-41 %

High Performance Discovery in Time Series: Techniques and Case Studies

Unser bisheriger Preis:ORGPRICE: 149,79 €

Jetzt 88,31 €*

Alle Preise inkl. MwSt.|Versandkostenfrei
ISBN-13:
9780387008578
Erscheinungsdatum:
01.06.2004
Seiten:
190
Autor:
New York University
Gewicht:
436 g
Format:
244x162x14 mm
Serie:
Monographs in Computer Science
Sprache:
Englisch
Beschreibung:

This monograph is a technical survey of concepts and techniques for describing and analyzing large-scale time-series data streams. Some topics covered are algorithms for query by humming, gamma-ray burst detection, pairs trading, and density detection. Included are self-contained descriptions of wavelets, fast Fourier transforms, and sketches as they apply to time-series analysis. Detailed applications are built on a solid scientific basis.
This book presents concepts and techniques for describing and analyzing large-scale time-series data streams, which, for example, is critical for complex real-world data in telecommunications, bioinformatics, and finance databases. The work aims at efficient discovery in time series, rather than at prediction, and presents rapid-discovery techniques for finding portions of time series with many events (i.e., gamma-ray scatterings) and finding closely related time series (i.e., highly correlated price histories or musical melodies). Database and online Web Services researchers and professionals will appreciate the book's algorithmic contributions, as well as its practical aspects and many case studies. Graduate students studying databases or interested in massive time-series data will find the book an essential resource.
I--REVIEW OF TECHNIQUES: * Time series preliminaries * Data reduction and transformation techniques * Indexing methods * Flexible similarity search II--CASE STUDIES: * StatStream * Query by humming * Elastic burst detection * A call to exploration * Answers to questions * References * Index

Kunden Rezensionen

Zu diesem Artikel ist noch keine Rezension vorhanden.
Helfen sie anderen Besuchern und verfassen Sie selbst eine Rezension.

Google Plus
Powered by Inooga