Abstract
Radio Frequency Identification technologies have been widely used in various domain. They allowed experts to automatically record on-line data of everyday life at a rapid rate. Consequently, in order to extract knowledge, these data should be treated rigorously. Among these treatments, we cite the classification that is paramount. Generally, for this purpose several classification' technologies exists. Particularly, Support Vector Machine has been applied to several domains to improve results efficiency. But, with the changes and the evolution of event streams and to support such changes, the SVM technique evolution is seen in many researches. The goal of this paper is to present an overview of different works related to SVM evolution, then we propose a comparative study between those works. As a result we obtain a taxonomy which shows in details support vector machine types and correlations between different types.