Multi-scale descriptions of real-time trends and their impact in pattern recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The author shows how a unifying symbolic representation of process trends leads to a systematic extraction of their temporal features and precise classification of trends. Such classification may proceed in a syntactic, semi-quantitative, or fully quantitative manner, depending on the characteristics of the problem being solved. Furthermore, it is argued that a multi-scale representation of process trends is essential in pattern recognition, and it is shown how the unifying representation of trends allows for the decomposition of signals at various levels of abstraction.

Original languageEnglish (US)
Title of host publicationProceedings of the American Control Conference
PublisherPubl by American Automatic Control Council
Pages2320-2325
Number of pages6
ISBN (Print)0879425652, 9780879425654
DOIs
StatePublished - 1991
EventProceedings of the 1991 American Control Conference - Boston, MA, USA
Duration: Jun 26 1991Jun 28 1991

Publication series

NameProceedings of the American Control Conference
Volume3
ISSN (Print)0743-1619

Other

OtherProceedings of the 1991 American Control Conference
CityBoston, MA, USA
Period6/26/916/28/91

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Multi-scale descriptions of real-time trends and their impact in pattern recognition'. Together they form a unique fingerprint.

  • Cite this

    Stephanopoulos, G. (1991). Multi-scale descriptions of real-time trends and their impact in pattern recognition. In Proceedings of the American Control Conference (pp. 2320-2325). (Proceedings of the American Control Conference; Vol. 3). Publ by American Automatic Control Council. https://doi.org/10.23919/acc.1991.4791819