Training set forming for SVM algorithm with use of the fuzzy clustering algorithms ensemble on base of cluster tags vectors similarity matrices

摘要

The objects classification problem with application of SVM algorithm is considered. The ways of training set formation for the SVM-algorithm, realizing various versions of classification decisions accounting, received with application of fuzzy clustering algorithms, are analyzed. Use possibility of fuzzy clustering algorithms ensemble on the base of the cluster tags vectors similarity matrices for the training set forming is shown.