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.

Describes how to discover groups of time series highly correlated with one another and how to make existing series fast and efficient for such purposes as scientific discovery, medical diagnosis, and profit in the business world

Klappentext
Time-series datadata arriving in time order, or a data streamcan 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 seriesfrom a collection of time seriesto 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 analyzinglarge-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.

Inhalt
1 Time Series Preliminaries.- 2 Data Reduction and Transformation Techniques.- 3 Indexing Methods.- 4 Flexible Similarity Search.- 5 StatStream.- 6 Query by Humming.- 7 Elastic Burst Detection.- 8 A Call to Exploration.- A Answers to the Questions.- A.2 Chapter 2.- A.3 Chapter 3.- A.4 Chapter 4.- A.5 Chapter 5.- A.6 Chapter 6.- A.7 Chapter 7.- References.