Knowledge Discovery from Data Streams

ISBN-13: 9781439826119 / Angielski / Twarda / 2010 / 256 str.

JOAO GAMA

Opis

In many modem applications, data are best modeled not as persistent tables but as transient data streams. Traditional methods of knowledge discovery do not work well in dynamic environments, where data continuously flow at high speeds. Presenting current research on knowledge discovery methods for data streams, this book provides a comprehensive introduction to this cutting-edge area of research in data mining and machine learning. Focusing on a variety of data stream mining algorithms, it covers basic streaming methods, exploratory models from data streams, and predictive models.

Spis treści

Knowledge Discovery from Data Streams. Introduction to Data Streams. Change Detection. Maintaining Histograms from Data Streams. Evaluating Streaming Algorithms. Clustering from Data Streams. Frequent Pattern Mining. Decision Trees from Data Streams. Novelty Detection in Data Streams. Ensembles of Classifiers. Time Series Data Streams. Ubiquitous Data Mining. Final Comments. Appendix. Bibliography. Index.

O autorze

João Gama is an associate professor and senior researcher in the Laboratory of Artificial Intelligence and Decision Support (LIAAD) at the University of Porto in Portugal.