High Performance Discovery in Time Series: Techniques and Case Studies

ISBN-13: 9781441918420 / Angielski / Miękka / 2011 / 190 str.

New York University

Opis

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.

Recenzje

From the reviews:

"The goal of the book is to show how to design fast scalable algorithms for the analysis of time series when much data must be analyzed. ... A linear time filter is constructed in such a way that no burst will be missed and nearly all false positives are eliminated. ... the book aims at efficient discovery in time series and presents practical algorithms for this task." (Jiri Andel, Mathematical Reviews, 2005)

 

Spis treści

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

Blurb

 

Time-series data—data arriving in time order, or a data stream—can be found in fields such as physics, finance, music, networking, and medical instrumentation. Designing fast, scalable algorithms for analyzing single or multiple time series can lead to scientific discoveries, medical diagnoses, and perhaps profits.

High Performance Discovery in Time Series 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 and return histories, or musical melodies). A typical time-series technique may compute a "consensus" time series—from a collection of time series—to use regression analysis for predicting future time points. By contrast, this book aims at efficient discovery in time series, rather than prediction, and its novelty lies in its algorithmic contributions and its simple, practical algorithms and case studies. It presumes familiarity with only basic calculus and some linear algebra.

Topics and Features:

*Presents efficient algorithms for discovering unusual bursts of activity in large time-series databases

* Describes the mathematics and algorithms for finding correlation relationships between thousands or millions of time series across fixed or moving windows

*Demonstrates strong, relevant applications built on a solid scientific basis

*Outlines how readers can adapt the techniques for their own needs and goals

*Describes algorithms for query by humming, gamma-ray burst detection, pairs trading, and density detection

*Offers self-contained descriptions of wavelets, fast Fourier transforms, and sketches as they apply to time-series analysis

This new monograph provides a technical survey of concepts and techniques for describing and analyzing large-scale time-series data streams. It offers essential coverage of the topic for computer scientists, physicists, medical researchers, financial mathematicians, musicologists, and researchers and professionals who must analyze massive time series. In addition, it can serve as an ideal text/reference for graduate students in many data-rich disciplines.