High Performance Discovery in Time Series: Techniques and Case Studies

✍ Scribed by Dennis Shasha, Yunyue Zhu

• Publisher: Springer
• Year: 2004
• Tongue: English
• Leaves: 195
• Series: Monographs in Computer Science
• Category: Library

✦ Synopsis

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.

✦ Table of Contents

Front Matter....Pages i-xv
Front Matter....Pages 1-1
Time Series Preliminaries....Pages 3-7
Data Reduction and Transformation Techniques....Pages 9-71
Indexing Methods....Pages 73-85
Flexible Similarity Search....Pages 87-100
Front Matter....Pages 101-101
StatStream....Pages 103-126
Query by Humming....Pages 127-150
Elastic Burst Detection....Pages 151-173
A Call to Exploration....Pages 175-175
Back Matter....Pages 177-190

✦ Subjects

Models and Principles; Information Storage and Retrieval; Algorithm Analysis and Problem Complexity; Computing Methodologies; Performance and Reliability; Math Applications in Computer Science