A comparison between decision trees and extension matrixes

Decision trees and extension matrixes are two methodologies for (fuzzy) rule generation. This paper gives an initial study on the comparison between the two methodologies. Their computational complexity and the quality of rule generation are analyzed. The experimental results have shown that the number of generated rules of the heuristic algorithm based on extension matrix is fewer than the decision tree algorithm. Moreover, regarding the testing accuracy (i.e., the generalization capability for unknown cases), experiments have also shown that the extension matrix method is better than the other method.