摘要
研究基于匹配追踪方法实现的信号稀疏分解算法。通过对信号稀疏分解中使用的过完备原子库的结构特性分析,找到中心位置,构造时频原子库,利用二分法控制中心位置参数,将信号快速稀疏分解,应用于基于中心位置参数的改进贪婪匹配追踪算法。该算法与匹配追踪相比,计算速度大约提高了36倍,降低了计算复杂度,提高了稀疏分解的精度。通过对仿真数据的处理验证了所提方法的可行性和有效性。
After the study of Matching Pursuit(MP)based signal sparse decomposition,analysis of structural property of the over-complete atom dictionary used in signal sparse decomposition is made,this paper creates frequency atom dictionary after seeking out centric position,dichotomy control of positional parameter based signal sparse decomposition algorithm is presented,applying to improved MP algorithm based on centric position parameter.The calculating speed of the algorithm in this paper increase by about 36 times compared with MP algorithm.This algorithm can reduce the computation complexity and improve the precision of sparse decomposition.Finally the simulation data processing verified that the proposed algorithm is effective and corrective.
出处
《空军工程大学学报（自然科学版）》
CSCD
北大核心
2013年第5期89-91,共3页
Journal of Air Force Engineering University(Natural Science Edition)
基金
陕西省自然科学基金资助项目(2011JM8031)
关键词
压缩感知
稀疏分解
冗余字典
MP算法
二分法
compressed sensing
sparse decomposition
redundant dictionary
MP algorithm
dichotomy
