Karhunen - Loeve Transformation in Radar Signal Features Processing

One of the most difficult tasks in the radar signal processing is an optimal features extraction and classification. The multifunction radar systems can not be classified and precisely recognized by most of new and modern Electronic Support Measure and Electronic Intelligence devices in the real time. It is directly combined with a possibility of measurement radar features. The number of radar features is sometimes measured a bit much and more often a few. This paper provides an overview of the new methods of measurement emitter signal features parameters and their transformation. This paper presents some aspects of radar signal features processing using Karhunen-Loeve ´a expansion as a feature selection and classification transform.