Knowledge Fusion Patterns for Context Aware Decision Support

Knowledge Fusion Patterns for Context Aware Decision Support

Alexander Smirnov (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia & ITMO University, Russia), Tatiana Levashova (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia) and Nikolay Shilov (St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, Russia)
Copyright: © 2015 |Pages: 13
DOI: 10.4018/978-1-4666-5888-2.ch057
OnDemand PDF Download:
$30.00
List Price: $37.50

Chapter Preview

Top

Background

Based on the analysis of knowledge fusion studies, a number of knowledge fusion processes can be distinguished:

  • 1.

    Intelligent fusion of massive amounts of heterogeneous data / information from a wide range of distributed sources into a form which may be used by systems and humans as the foundation for problem solving and decision making (Scherl & Ulery, 2004; Alun et al., 2001).

  • 2.

    Integration of knowledge from various knowledge sources (KSs) resulting in a completely different type of knowledge or new idea how to solve the problem (Lee, 2007; Grebla, Cenan & Stanca, 2010). Integration of different types of knowledge (domain, procedural, derived, presentation, etc.) resulting in a new knowledge type (Holsapple & Whinston, 1986) and integration of multiple KSs into a new knowledge object (Kuo, Tseng, & Lin, 2003; Gou, Yang, & Chen, 2005) belong to this type of knowledge fusion.

  • 3.

    Combining knowledge from different autonomous KSs in different ways in different scenarios, which results in discovery of new relations between the knowledge from different sources or/and between the entities this knowledge represents (Laskey, Costa & Janssen, 2008; Jonquet et al., 2011).

  • 4.

    Re-configuration of KSs to achieve a new configuration with new capabilities or competencies (Lin & Lo, 2010).

  • 5.

    Knowledge exchange to improve capabilities or competencies through learning, interactions, discussions, and practices (Lin & Lo, 2010).

  • 6.

    Involvement of knowledge from various sources in problem solving, which results in a new knowledge product (Smirnov et al., 2003).

The processes above can produce the following possible knowledge fusion results:

  • A new knowledge object created from data/information (the result of the process 1);

  • A new knowledge type or knowledge product (service, process, technology, etc.) (the result of the process 2);

  • New relations between knowledge objects (the result of the process 3);

  • New capabilities / competencies of a knowledge object (the result of the processes 4 and 5);

  • A new idea how to solve the problem (the result of the process 2); in the informatics terms this result corresponds to a new problem solving method;

  • A solution for the problem (the result of the process 6).

Key Terms in this Chapter

Knowledge Fusion: Knowledge processing resulting in an appearance of new knowledge.

Knowledge Source: A source of data, information, or knowledge, which can be explicitly specified.

Knowledge Fusion Result / Effect: Any new knowledge (new knowledge source, new concept, new property, etc.).

Ontology: Based context model – representation of the situation (context) by means of ontology.

Autonomous Knowledge Source: A knowledge source having no relations to other sources; the changes in the autonomous source do not produce any changes in other sources.

Non-Autonomous Knowledge Source: A knowledge source relating to other sources; any changes in a non-autonomous knowledge source are passed to the related sources and reflected in them.

Context Aware Decision Support System: A system that uses context to provide the decision maker with a set of decisions that can be made in the current situation.

Context: Information about the situation in which decisions are made.

Constraint Satisfaction Problem: A set of variables (class properties in ontology-based representations) and a set of constraints specifying the allowed values for these variables. A solution for a constraint satisfaction problem is a set of feasible solutions (each solution is represented by a set of ontology instances) such as all the values assigned to the variables satisfy all the constraints.

Complete Chapter List

Search this Book:
Reset