摘要
传统稀疏分解算法正交匹配追踪(OMP)算法里采用内积最大值来寻找最优原子,该方法容易陷入局部最优,为了弥补这一缺点,采用了新的算法:A*OMP算法,该算法使用A*搜索(即最佳优先搜索技术)寻找最优原子,该搜索方式寻找的最优原子具有全局最优性。实验表明相比传统OMP算法而言,该算法有效地提高了信号的重构精度。
In the traditional sparse decomposition algorithm——orthognal matching pursuit（OMP）algorithm,maximum inner product is used to find the optimal atom.The method is easy to fall into local optimization,in order to make up the shortcoming,a new algorithm is proposed in this paper：A＊OMP algorithm,the algorithm uses A＊search（the best first search technology）to find the optimal atom,the optimal atom searched by using the search way has global optimality.Experiments show that the algorithm effectively improves the reconstruction accuracy of signal compared with the traditional OMP algorithms.
出处
《舰船电子对抗》
2015年第1期65-69,共5页
Shipboard Electronic Countermeasure
关键词
稀疏分解
正交匹配追踪算法
雷达信号
sparse decomposition
orthogonal matching pursuit algorithm
radar signal
