New York University Courant Inst. Mathematical Sciences – författare
Visar alla böcker från författaren New York University Courant Inst. Mathematical Sciences. Handla med fri frakt och snabb leverans.
2 produkter
2 produkter
1 055 kr
Skickas inom 10-15 vardagar
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 yield scientific discoveries, medical diagnoses, and certainly 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 histories, or musical melodies). Such real-time streaming data analysis is critical for complex real-world data in telecommunications, bioinformatics, and finance databases.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 database and online web services researchers and professionals, as well as an ideal resource for graduates.
1 103 kr
Skickas inom 10-15 vardagar
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.