A Novel Fingerprint Identification Method Based on Sparse Representation for Transient of AIS Emitter

Based on the sparse representation of transient，a novel method of radio transient fingerprint sparse representation discriminant for emitters in Automatic Identification System is investigated. The algorithm finds a projection preserved sparse representation structure of transient vectors and class label information to project the test vector to the optimal low dimensional discriminable subspace. An objective function is constructed by simultaneously maximizing reconstructed error of inter-class features, and minimizing reconstructed error of intra-class features. The criterion of minimum reconstruction error of sparse representation for test vector is applied to find classification label. Its applications to signals measured through an antenna show promising results for radiometric identification of emitters in Automatic Identification System. Simulations on the data set of the radio transient mathematical model proves the correctness and validity of the proposed method, and the simulation results show that the average correct classification ratio of the proposed method have a huge advantage in comparison with the existing algorithm.