Title :
An Incremental Formation Method of Influence Diagram Structure
Author :
Ma, Feng ; Liu, Weiyi
Author_Institution :
Sch. of Inf. Sci. & Eng., Yunnan Univ., Kunming, China
Abstract :
As an effective decision tool, influence diagram has been widely used in many fields. However, its traditional building method needs experts or domain knowledge to identify the dependence relationship between variables in original dataset. When data set increased, its corresponding influence diagram might not suitable for it any more. A new influence diagram may need to be built from very beginning according to the traditional building method. An incremental formation method is developed in this paper, which could format the new influence diagram´s structure by adjusting that of the original one. The validity of this method is discussed in theory and illustrated by experiment.
Keywords :
decision diagrams; decision making; knowledge based systems; decision tool; domain knowledge; incremental formation method; influence diagram structure; Bayesian methods; Buildings; Cognition; Learning systems; Presses; Probabilistic logic; Timing; domain knowledge; incremental formation; influence diagram;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
Conference_Location :
Shenzhen, Guangdong
Print_ISBN :
978-1-61284-289-9
DOI :
10.1109/ICICTA.2011.20