A hierarchical pattern matching procedure for signal abstraction

Authors:
A. Otero;P. Félix;S. Fraga;S. Barro;F. Palacios
Affiliations:
Dpto. de Electrónica e Computación, Universidade de Santiago de Compostela, Santiago de Compostela, Spain;Dpto. de Electrónica e Computación, Universidade de Santiago de Compostela, Santiago de Compostela, Spain;Dpto. de Electrónica e Computación, Universidade de Santiago de Compostela, Santiago de Compostela, Spain;Dpto. de Electrónica e Computación, Universidade de Santiago de Compostela, Santiago de Compostela, Spain;Hospital Universitario de Getafe, Madrid, Spain
Venue:
CAEPIA'05 Proceedings of the 11th Spanish association conference on Current Topics in Artificial Intelligence
Year:
2005

Citing 2
Cited 1

Constraint Processing

Constraint Processing
Fuzzy constraint networks for signal pattern recognition

Artificial Intelligence - Special issue: Fuzzy set and possibility theory-based methods in artificial intelligence

A structural knowledge-based proposal for the identification and characterization of apnoea episodes

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Multivariable Fuzzy Temporal Profile model enables human experts to project their knowledge of a signal pattern, described over a set of parameters, into a computable description. Here it is endowed with a hierarchical capability through the definition of algorithms that recognize a set of findings over a signal, and aggregate them into a set of abstraction levels. We also present a heuristics that takes advantage of the continuity properties of real signals to allow the matching process to meet real time requirements, even over high frequency signals.