Evolutionary fuzzy c-means clustering algorithm

In this paper, a new approach to fuzzy clustering is introduced. This approach, which is based on the application of an evolutionary strategy to the fuzzy c-means clustering algorithm, utilizes the relationship between the various definitions of distance and structures implied in each given data set. As soon as a particular definition of distance is chosen, a particular structure in the data set is implied. Therefore, the search for a structure in given data can be viewed as a search for an appropriate definition of distance. We describe an evolutionary algorithm for determining the "best" distance for given data, where the criterion of goodness is defined in terms of the performance of the fuzzy c-means clustering method. We discuss relevant theoretical aspects as well as experimental results that characterize the utility of the proposed algorithm.<>