Overview and Goals Data arriving in time order (a data stream) arises in fields ranging from physics to finance to medicine to music, just to name a few. Often the data comes from sensors (in physics and medicine for example) whose data rates continue to improve dramati cally as sensor technology improves. Further, the number of sensors is increasing, so correlating data between sensors becomes ever more critical in orderto distill knowl edge from the data. On-line response is desirable in many applications (e.g., to aim a telescope at a burst of activity in a galaxy or to perform magnetic resonance-based real-time surgery). These factors - data size, bursts, correlation, and fast response motivate this book. Our goal is to help you design fast, scalable algorithms for the analysis of single or multiple time series. Not only will you find useful techniques and systems built from simple primi tives, but creative readers will find many other applications of these primitives and may see how to create new ones of their own. Our goal, then, is to help research mathematicians and computer scientists find new algorithms and to help working scientists and financial mathematicians design better, faster software.
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 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.
