出版社：Japan Society for Fuzzy Theory and Intelligent Informatics
摘要：By the former clustering algorithms, it is difficult to obtain a good clustering results for the data which is not able to be separated on linear classification boundary. The square of norms between data is used as dissimilarity so that those algorithms regard the classification boundary as linear. In this paper, the new hierarchical algorithm is proposed using kernel functions. The kernel functions are useful into the field of classification and give the value of the inner product of two vectors in a high-dimensional feature space by a mapping which one-to-one corresponds to the kernel function. The mapping is not explicit so that the value of the inner product of the feature space can be easily calculated on dimension of the original pattern space. By introducing the kernel functions, the proposed algorithm can separate the data on nonlinear classification boundary. Moreover, the availability of proposed algorithm is discussed through some numerical examples.
关键词：hierarchical clustering ; kernel function ; pattern recognition
