favorite326.4 Clustering Performance We conducted experiments on five datasets and Table (2) compares our results with six previous methods (eight different approaches).
favorite1Moreover, to identify more complex relation between input patterns, we also propose GMM to be incorporated to the random forest because it is very robust method for unsupervised data clustering [19, 20].
favorite0However, it is not an easy task to realize acceptable performance parameters for data clustering by applying spectral clustering because some datasets have very high dimensionality and it is difficult to group similar objects using Euclidean Distance metric.
favorite23The proposed algorithm differs from the commonly used spectral clustering methods where the computed distance metric is used to find similarities between data points.
favorite5The Random Forest method has been specifically applied to construct a robust affinity graph that provides information on the underlying structure of data objects used in clustering.