Data mining for multi-agent fuzzy decision tree structure and rules

Abstract

A fuzzy logic based expert system has been developed that automatically allocates resources in realtime over many dissimilar platforms. The platforms can be very general, e.g., ships, planes, etc. Potential foes can also be general. The resource manager has been embedded in an electronic game environment. This co-evolutionary game fully automates the data mining problem allowing determination of parameters essential to the resource manager. The game allows the resource manager to learn from human experts or computerized enemies. The game does not determine the structure of fuzzy decision trees. A new data mining algorithm that uses a genetic program, an algorithm that evolves other computer programs, as a data mining function has been developed to solve this problem. It not only determines the fuzzy decision tree structure it also creates fuzzy rules while mining scenario data bases. Finally, experimental results are discussed related to both data mining algorithms.