Clustering and pattern recognition in bioengineering and autonomous systems

Abstract Many artificial intelligence applications are dealing with large amount of data. The essence is to identify and recognize the structure in data and classify them according to similar attributes, features and patterns. Often, these data are fuzzy and do not belong to one cluster only. Presented is a method for optimum partitioning of fuzzy data which uses a concept of n-dimensional Euclidian space to determine the geometric closeness of data. Numeric examples, based on a prototype software, present clustering and pattern recognition algorithms including defuzzification founded on the maximum membership, cluster similarity analysis and classification metrics of the data sets decomposition.