Search for: [Abstrakt = "Support Vector Clustering \(SVC\) is a new method for unsupervised classification. The advantage of this method is that no prior assumptions about the number or the shape of clusters are required. The choice of two parameters\: the soft margin constant and the Gaussian kernel parameter, is crucial to the clustering solutions. In the paper the validation of SVC based on resampling techniques is proposed as a method for a parameter selection. The method was illustrated on benchmark data set from R package cluster Sim."]

Number of results: 1