A new classification scheme using artificial immune systems learning for fuzzy cognitive mapping

In this paper, an intelligent approach based on artificial immune systems (AIS) is proposed to perform the task of classification using fuzzy cognitive map learning. Fuzzy cognitive map is an approach to knowledge representation and inference including learning capabilities; it emphasizes the connections of concepts as basic units for storing knowledge, and the structure that represents the significance of system. One of the most useful aspects of the FCM is its prediction capability as a classification tool. Little research has been done on pattern classification using FCM approach. The proposed artificial immune algorithm inspired by theoretical immunology and observed immune functions, principles and models, was considered to learn FCM network providing a category after classification. Consequently, the proposed method provides an FCM learning methodology for pattern recognition. The proposed algorithm is implemented in a previous autism classification problem, as well as in some benchmark machine learning datasets to show its functionality.