Data justify; MARGIN: 0in 0in 0pt; unicode-bidi: embed; DIRECTION: ltr" First step of this processing is the data clustering. Many clustering methods have been proposed till now in which almost all of them estimation of the number of clusters is an important issue. In this thesis we propose a new method in order to estimate the number of clusters. This method is based on rough sets theory and data discretization. Our proposed method has not only the ability to estimate the number of clusters but also determining initial centers of clusters. We used hierarchical and k-means clustering algorithm in order to achieve the goal of putting data in proper clusters. In the second step we also propose an algorithm based on support vector machine (SVM) and relevance vector machine (RVM) for justify; MARGIN: 0in 0in 0pt; unicode-bidi: embed; DIRECTION: ltr" Keywords: Radar Emitter Identification, Rough Sets Theory, Discretization, Support Vector Machines, Relevance Vector Machines.
