Radar signal sorting method based on support vector clustering and grey correlation degree index

Abstract

Radar signal sorting method based on traditional clustering algorithm takes on a high time complexity and has poor accuracy. Aimed at the problem, a new sorting method is researched based on improved cone cluster labelling (ICCL) method for SVC algorithm and grey correlation degree (GCD) index. The ICCL method relies on approximate coverings both in feature space and data space. By using ICCL the calculation of adjacency matrix is avoided. This method is interpreted in theory and is modified for lower complexity and high accuracy by handling the outliers. And a new cluster validity index, grey correlation degree (GCD) index, is proposed which assesses the compactness and separation of clusters using average grey relational degree. In this paper, the SVC sorting model is constructed to obtain the cluster division firstly with ICCL method. Secondly, grey correlation degree is designed to measure the similarity between clusters, and to verify the clustering validity. Thirdly, the clustering parameters are adjusted adaptively to achieve the best clusters division. Finally, clustering validity sorting experiments of interleaved pulse streams is implemented. The results show that this method can obtain better clustering results.