Deinterleaving technology of radar emitter signals based on clustering
Taowei Chen · Journal of Circuits and Systems · 2011
Clustering algorithm based on intra-pulse features is an important approach to realize deinterleaving of radar emitter signals.In this paper,a novel algorithm based on wavelet transform domain filtering is proposed to deinterleave radar emitter signals.The energy entropy from approximation coefficients of wavelet transform and the other energy entropy from inner-scale correlations denoise of detail coefficients are used as deinterleaving feature vector.And grey relational analysis,introduced to measure the degree of similarity between feature vector sets,is used to sort different radar emitter signals.Computer simulation results and clustering of 10 different radar signals show that the feature vectors have good performance of noise-resistance when SNR is 0dB.Moreover,compared with FCM clustering algorithm,the hierarchical clustering algorithm based on grey relational analysis has higher accuracy of clustering.