"This paper proposes a fuzzy clustering model for probability density functions (PDFs) using
the two-objective genetic algorithm. In this model, the L1-distance is used to evaluate the
similarity of PDFs, and new two indexes that relate to the similarity of PDFs and clusters
are proposed as the objective functions of genetic algorithm. Moreover, the operators for
crossover, mutation, and selection are also updated to improve the quality of fuzzy clustering
according to the corrected rand, the partition entropy, and the partition coefficients. By combining
these improvements, we have an effective automatic fuzzy clustering algorithm for
PDFs that can determine the appropriate number of clusters, the elements in each cluster, and
the probability belonging to clusters of each element. The proposed model is tested through
experiments using the established Matlab procedure, and it is also applied effectively to
image data. These experiments demonstrate the superiority of the proposed model compared
to other models"