Effective representation of physiological dynamics by fuzzy rough set: a review
Fecha
Director
Enlace al recurso
DOI
ORCID
Google Scholar
Cvlac
gruplac
Descripción Dominio:
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Santo Tomás. Seccional Bucaramanga
Compartir
Resumen
Los sistemas biomédicos de última generación registran en intervalos cortos de tiempo la dinámica fisiológica mediante grandes bases de datos. La interpretación adecuada de la información difícilmente puede hacerse por la experticia de un sólo médico, por lo tanto la toma de decisiones se basa sólo en algunas variables seleccionadas. La representación efectiva de variables fisiológicas mediante fuzzy rough set tipo 1 puede ser aplicada para caracterizar y extraer la información relevante de la dinámica fisiológica; sin embargo, estas técnicas poseen el problema de la complejidad de sus algoritmos y alto costo computacional; por lo tanto, se requiere aplicar técnicas de fuzzy rough set tipo 2, asociadas a métodos axiomáticos a través de operadores de aproximación difusa baja y alta como conceptos primitivos para generar un sistema de reducción de dimensiones con tendencia a la disminución de costo computacional en aplicaciones de ingeniería biomédica. En este artículo se presenta la revisión del estado del arte sobre representación efectiva de dinámicas fisiológicas mediante fuzzy rough set, con el fin de determinar la capacidad que poseen este tipo de técnicas para ser incluidas en procedimientos automáticos de toma de decisiones que apoyen el concepto clínico de un especialista.
The latest generation of biomedical systems record at short time intervals the physiological dynamic in large databases. The correct interpretation of the information is difficult to obtain by the expertise of a single physician, so the decision is based only on some selected variables. Effective representation of physiological variables by fuzzy Rough Set type 1 can be applied to characterize and extract relevant information from physiological dynamics, however the disadvantages of these techniques are the complexity of their algorithms and the high computational cost, therefore it is necessary to apply fuzzy rough set type 2 techniques , associated with axiomatic methods through low and high diffuse approximation operators as primitive concepts for generating a dimension reduction system with a tendency to lower computational cost in biomedical engineering applications. This article reviews the state of the art of effective representation of physiological dynamics using fuzzy rough set, in order to determine the ability of these techniques to be included in automatic decision making procedures that support the clinical opinion of a specialist.
The latest generation of biomedical systems record at short time intervals the physiological dynamic in large databases. The correct interpretation of the information is difficult to obtain by the expertise of a single physician, so the decision is based only on some selected variables. Effective representation of physiological variables by fuzzy Rough Set type 1 can be applied to characterize and extract relevant information from physiological dynamics, however the disadvantages of these techniques are the complexity of their algorithms and the high computational cost, therefore it is necessary to apply fuzzy rough set type 2 techniques , associated with axiomatic methods through low and high diffuse approximation operators as primitive concepts for generating a dimension reduction system with a tendency to lower computational cost in biomedical engineering applications. This article reviews the state of the art of effective representation of physiological dynamics using fuzzy rough set, in order to determine the ability of these techniques to be included in automatic decision making procedures that support the clinical opinion of a specialist.
Abstract
Idioma
Palabras clave
Fuzzy/rough sets, Physiological dynamics, Dimensionality reduction, Intrinsic representation, Feature extraction/selection, Conjuntos difusos/aproximados, Dinámica fisiológica, Reducción de dimensiones, Representación efectiva, Extracción/selección de características
Citación
Colecciones
Licencia Creative Commons
Copyright (c) 2011 ITECKNE