Neuro-fuzzy, Fuzzy Decision Tree and Association Rule Based Methods for Fuzzy Cognitive Map Grading Process

This work focuses on the formalization of a Fuzzy Cognitive Map based decision support system using fuzzy If-Then rules (extracted from data) accompanied with the available experts’ knowledge. The proposed approach is applied to build a Fuzzy Cognitive Map (FCM) grading tool, an advanced FCM-based model used for prediction. The FCM is a modeling methodology based on exploiting knowledge and experience. It can handle uncertainty and can be constructed by experts’ knowledge and the proposed fuzzy rules. The performance of FCMs is known to be sensitive to the initial weight setting and architecture. This shortcoming can be alleviated and the FCM model can be enhanced if a fuzzy rule base (IF-THEN rules) is available. The paper reports a successful attempt to combine FCMs with neuron-fuzzy, fuzzy decision tree and association rule based methods. These methods extract the available knowledge from data in the form of fuzzy rules and insert them into the FCM grading tool used for decision making tasks. This rule base could be derived by association rules, neuron-fuzzy approaches and knowledge extraction methods in general. In this research work, our scope is to introduce a new framework for decision making tasks and the proposed methodology is implemented in a well-known benchmark medical problem with real clinical data.