Target Attribute Identification Based on Multi-Class SVM and D-S Evidence Theory

Abstract

Concerning for air target attribute identification, an attribute identification method based on the combination of multi-class SVM and D-S evidence theory is proposed. The method constructs several multi-class support vector machine (SVM) classifiers, and generates the basic probability assignment (BPA) by the class-wise probability. Then D-S evidence theory is adopted to make the fusion and decision. Simulation results indicate that the method have a good identification of air target attribute, and prove the rationality and validity. Target attribute identification；Multi-class SVM；BPA；D-S evidence theoryI.