An incremental knowledge acquisition-based system for critical domains

  • Authors:
  • Francisco Jesús Torralba-Rodríguez;Jesualdo Tomás Fernández-Breis;Rodrigo Martínez-Béjar;Vicente Bixquert Montagud

  • Affiliations:
  • Departamento de Informática y Sistemas, Universidad de Murcia, CP 30100, Spain;Departamento de Informática y Sistemas, Universidad de Murcia, CP 30100, Spain;Departamento de Ingeniería de la Información y las Comunicaciones, Universidad de Murcia, CP 30100, Spain;Servicio de Medicina Intensiva, Hospital Universitario Virgen de la Arrixaca, Carretera Madrid-Cartagena, CP 30120, El Palmar, Murcia, Spain

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.05

Visualization

Abstract

In some real life situations, humans have to make decisions in critical environments. When a human analyzes a situation, (s)he has to decide whether there is a risky situation and what actions have to be performed. It is always desirable to detect these situations in advance, because the solution could be easier and the expert would have more time to make the best decision. An intelligent system may analyze the information, extract conclusions, format and order the causes leading to the severe condition, so becoming the decision-making process less dramatic. Multiple Classification Ripple Down Rules (MCRDR) are a successful intelligent classification technique which has proven its efficiency in several application domains, but it has some limitations to define complex situations. In this work, an extension to MCRDR to cover with complex domains is proposed. The validation of this methodological extension has been done through the development of a prototype for complex medical domains and this is also presented in this paper.