A framework for fuzzy rule-based cognitive maps
Khan, M.S. and Khor, S.W. (2004) A framework for fuzzy rule-based cognitive maps. In: Zhang, C., Guesgen, H.W. and Yeap, W-K, (eds.) PRICAI 2004: Trends in Artificial Intelligence. Volume 3157 Lecture Notes in Computer Science. Springer, pp. 454-463.
*Subscription may be required
Fuzzy Cognitive Maps (FCM), as defined originally, are limited in their capacity to model real-world scenarios, due to the rather simple representation of causal relationships between interrelated concepts. They can model a world that has only monotonic cause-effect relationships. Unlike this traditional FCM, which uses a linear function to represent the strength of relationship between two concepts, and a non-linear transfer function, to update the value of a concept during simulation, the FCM proposed by us uses fuzzy rules based on membership functions, and an aggregation operator respectively to serve these two purposes. This allows representation of non-monotonic causality, which is typical of many scenarios.
|Publication Type:||Book Chapter|
|Murdoch Affiliation:||School of Information Technology|
|Item Control Page|