Advertisement
Published in:
2008 | OriginalPaper | Chapter
Knowledge Discovery in a Framework for Modelling with Words
Authors : Zengchang Qin, Jonathan Lawry
Published in: Soft Computing for Knowledge Discovery and Data Mining
Publisher: Springer US
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The learning of transparent models is an important and neglected area of data mining. The data mining community has tended to focus on algorithm accuracy with little emphasis on the knowledge representation framework. However, the transparency of a model will help practitioners greatly in understanding the trends and idea hidden behind the system. In this chapter, a random set based knowledge representation framework for learning linguistic models is introduced. This framework is referred to as label semantics and a number of data mining algorithms are proposed. In this framework, a vague concept is modelled by a probability distribution over a set of appropriate fuzzy labels which is called as mass assignment. The idea of mass assignment provides a probabilistic approach for modelling uncertainty based on pre-defined fuzzy labels.