Aiming at the problem that a large number of array elements are needed for uniform arrays to meet the requirements of direction map,a sparse array pattern synthesis method is proposed in this paper based on the sparse...Aiming at the problem that a large number of array elements are needed for uniform arrays to meet the requirements of direction map,a sparse array pattern synthesis method is proposed in this paper based on the sparse sensing theory.First,the Orthogonal Matching Pursuit(OMP)algorithm and the Exact Augmented Lagrange Multiplier(EALM)algorithm were improved in the sparse sensing theory to obtain a more efficient Orthogonal Multi⁃Matching Pursuit(OMMP)algorithm and the Semi⁃Exact Augmented Lagrange Multiplier(SEALM)algorithm.Then,the two improved algorithms were applied to linear array and planar array pattern syntheses respectively.Results showed that the improved algorithms could achieve the required pattern with very few elements.Numerical simulations verified the effectiveness and superiority of the two synthetic methods.In addition,compared with the existing sparse array synthesis method,the proposed method was more robust and accurate,and could maintain the advantage of easy implementation.展开更多
Sparse representation has been widely used in signal processing,pattern recognition and computer vision etc.Excellent achievements have been made in both theoretical researches and practical applications.However,there...Sparse representation has been widely used in signal processing,pattern recognition and computer vision etc.Excellent achievements have been made in both theoretical researches and practical applications.However,there are two limitations on the application of classification.One is that sufficient training samples are required for each class,and the other is that samples should be uncorrupted.In order to alleviate above problems,a sparse and dense hybrid representation(SDR)framework has been proposed,where the training dictionary is decomposed into a class-specific dictionary and a non-class-specific dictionary.SDR putsℓ1 constraint on the coefficients of class-specific dictionary.Nevertheless,it over-emphasizes the sparsity and overlooks the correlation information in class-specific dictionary,which may lead to poor classification results.To overcome this disadvantage,an adaptive sparse and dense hybrid representation with non-convex optimization(ASDR-NO)is proposed in this paper.The trace norm is adopted in class-specific dictionary,which is different from general approaches.By doing so,the dictionary structure becomes adaptive and the representation ability of the dictionary will be improved.Meanwhile,a non-convex surrogate is used to approximate the rank function in dictionary decomposition in order to avoid a suboptimal solution of the original rank minimization,which can be solved by iteratively reweighted nuclear norm(IRNN)algorithm.Extensive experiments conducted on benchmark data sets have verified the effectiveness and advancement of the proposed algorithm compared with the state-of-the-art sparse representation methods.展开更多
基金Sponsored by the National Natural Science Foundation of China(Grant No.U1813222)the Tianjin Natural Science Foundation(Grant No.18JCYBJC16500)+1 种基金the Hebei Province Natural Science Foundation(Grant No.E2016202341)the Research Project on Graduate Training in Hebei University of Technology(Grant No.201801Y006).
文摘Aiming at the problem that a large number of array elements are needed for uniform arrays to meet the requirements of direction map,a sparse array pattern synthesis method is proposed in this paper based on the sparse sensing theory.First,the Orthogonal Matching Pursuit(OMP)algorithm and the Exact Augmented Lagrange Multiplier(EALM)algorithm were improved in the sparse sensing theory to obtain a more efficient Orthogonal Multi⁃Matching Pursuit(OMMP)algorithm and the Semi⁃Exact Augmented Lagrange Multiplier(SEALM)algorithm.Then,the two improved algorithms were applied to linear array and planar array pattern syntheses respectively.Results showed that the improved algorithms could achieve the required pattern with very few elements.Numerical simulations verified the effectiveness and superiority of the two synthetic methods.In addition,compared with the existing sparse array synthesis method,the proposed method was more robust and accurate,and could maintain the advantage of easy implementation.
基金The work described in this paper was partially supported by the National Natural Science Foundation of China(Grant Nos.61673249,61703252)the Union Fund of National Natural Science Foundation of China(U1805263)the Research Project Supported by Shanxi Scholarship Council of China(2016-004).
文摘Sparse representation has been widely used in signal processing,pattern recognition and computer vision etc.Excellent achievements have been made in both theoretical researches and practical applications.However,there are two limitations on the application of classification.One is that sufficient training samples are required for each class,and the other is that samples should be uncorrupted.In order to alleviate above problems,a sparse and dense hybrid representation(SDR)framework has been proposed,where the training dictionary is decomposed into a class-specific dictionary and a non-class-specific dictionary.SDR putsℓ1 constraint on the coefficients of class-specific dictionary.Nevertheless,it over-emphasizes the sparsity and overlooks the correlation information in class-specific dictionary,which may lead to poor classification results.To overcome this disadvantage,an adaptive sparse and dense hybrid representation with non-convex optimization(ASDR-NO)is proposed in this paper.The trace norm is adopted in class-specific dictionary,which is different from general approaches.By doing so,the dictionary structure becomes adaptive and the representation ability of the dictionary will be improved.Meanwhile,a non-convex surrogate is used to approximate the rank function in dictionary decomposition in order to avoid a suboptimal solution of the original rank minimization,which can be solved by iteratively reweighted nuclear norm(IRNN)algorithm.Extensive experiments conducted on benchmark data sets have verified the effectiveness and advancement of the proposed algorithm compared with the state-of-the-art sparse representation methods.