Sign in
Nodes Selection Criteria for Fuzzy Cognitive Maps Designed to Model Time Series
Conference proceeding

Nodes Selection Criteria for Fuzzy Cognitive Maps Designed to Model Time Series

Wladyslaw Homenda, Agnieszka Jastrzebska and Witold Pedrycz
INTELLIGENT SYSTEMS'2014, VOL 2: TOOLS, ARCHITECTURES, SYSTEMS, APPLICATIONS, Vol.323, pp.859-870
Advances in Intelligent Systems and Computing
01/01/2015

Abstract

Computer Science Computer Science, Artificial Intelligence Robotics Science & Technology Technology
The article introduces three concepts' rejection/selection criteria for Fuzzy Cognitive Map-based method of time series modeling and prediction. Proposed criteria are named entropy index, membership index and global distance index. Concepts' selection strategies facilitate Fuzzy Cognitive Map design procedure. Proposed criteria allow to simplify, otherwise very complex models, and achieve a reasonable balance between complexity and accuracy.

Metrics

1 Record Views

Details