Novel artificial intelligent techniques via AFS theory: Feature selection, concept categorization and characteristic description

Artificial intelligence is the study of how computer systems can simulate intelligent processes such as learning, reasoning, and understanding symbolic information in context. Axiomatic Fuzzy Set (AFS) theory, in which fuzzy sets (membership functions) and their logic operations are determined by a consistent algorithm according to the distributions of original data and the semantics of the fuzzy concepts, is applied to study some new techniques of feature selection, concept categorization and characteristic description; problems often encountered in artificial intelligence area such as machine learning and pattern recognition. These techniques developed under the framework of AFS theory in this paper are more simple and more interpretable than the conventional methods, since they imitate the human recognition process. In order to evaluate the effectiveness of the feature selection, the concept categorization and the characteristic description, these new techniques are applied to fuzzy clustering problems. Several benchmark data sets are used for this purpose. Clustering accuracies are comparable with or superior to the conventional algorithms such as FCM, k-means, and the new algorithm such as single point iterative weighted fuzzy C-means clustering algorithm.