High Performance Discovery In Time Series Techniques and Case Studies [Paperback]

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.

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.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

From the relÌ