Decomposing a signal based upon redundan dictionaries is a new method for data representation on sig- nal processing. It approximates a signal with an overcom- plete system instead of an orthonormal basis to provide a...Decomposing a signal based upon redundan dictionaries is a new method for data representation on sig- nal processing. It approximates a signal with an overcom- plete system instead of an orthonormal basis to provide a sufficient choice for adaptive sparse decompositions. Re- placing the original data with a sparse approximation can result in not only a higher compression ratio, but also greater flexibility in capturing the inherent structure of the natura signals with the redundancy of dictionaries. This paper gives an overview of a series of recent results in this field, and deals with the relationship between sparsity of signal de- composition and incoherence of dictionaries with BP and MP algorithms. The current and future challenges of the dic- tionary construction are discussed.展开更多
在多孔隙含水层中地面磁共振(surface nuclear magnetic resonance,SNMR)信号呈现多弛豫衰减特性,常规盲源分离方法和单指数拟合方法引起信号严重失真和信息缺失等问题.本文提出了基于稀疏表示的随机噪声背景下多弛豫SNMR信号的提取方法...在多孔隙含水层中地面磁共振(surface nuclear magnetic resonance,SNMR)信号呈现多弛豫衰减特性,常规盲源分离方法和单指数拟合方法引起信号严重失真和信息缺失等问题.本文提出了基于稀疏表示的随机噪声背景下多弛豫SNMR信号的提取方法.根据SNMR信号的衰减特征,设计了精确刻画SNMR信号且与随机噪声不相关的离散衰减余弦冗余字典.其次,针对多弛豫SNMR信号稀疏度未知的问题,通过设置合理的残差比阈值控制迭代次数,改进了广义正交匹配追踪(generalized orthogonal matching pursuit,gOMP)算法,使得该方法应用于SNMR信号的提取时,具有更好的自适应性和普适性.再次,鉴于SNMR测量数据为多次独立重复采集的结果,提出了基于数据流的SNMR信号提取策略,在提高算法鲁棒性的同时,保证了信号提取结果的唯一性.最后,通过仿真和实测数据证明了基于gOMP算法的稀疏表示方法可以显著地提升多弛豫SNMR信号的提取质量,降低随机噪声对含水层反演结果的影响,提高SNMR探测能力.展开更多
基金This work was supported in part by the National Committee for Nationalities,China Scholarship Council and Education Department of China.
文摘Decomposing a signal based upon redundan dictionaries is a new method for data representation on sig- nal processing. It approximates a signal with an overcom- plete system instead of an orthonormal basis to provide a sufficient choice for adaptive sparse decompositions. Re- placing the original data with a sparse approximation can result in not only a higher compression ratio, but also greater flexibility in capturing the inherent structure of the natura signals with the redundancy of dictionaries. This paper gives an overview of a series of recent results in this field, and deals with the relationship between sparsity of signal de- composition and incoherence of dictionaries with BP and MP algorithms. The current and future challenges of the dic- tionary construction are discussed.