摘要
为提高基于遗传算法的压缩感知重构方法性能,提出一种改进的遗传重构算法.该算法将0-1编码染色体等效为稀疏信号,并以染色体信号的稀疏性为先验条件,提出稀疏交叉、稀疏突变操作,同时引入自适应机制动态调整稀疏操作与传统遗传算子的执行概率,迭代逼近最优重构目标.其重建过程也无需预知原始信号稀疏度且不必进行子空间的跟踪与扩充.仿真结果表明,改进算法对于不同维度信号均能实现快速、精确的重建.
In order to enhance the performance of the reconstruction based on genetic algorithm(RGA) in compressed sensing, an reconstruction based on improved genetic algorithm(RIGA) was proposed. In this algorithm, the 0-1 coded chromosome was equivalent to sparse signal, and the sparsity of chromosome signals was used as a priori condition. The algorithm proposed sparse crossover and mutation operations, at the same time, an adaptive mechanism was introduced to dynamically adjust the execution probability of sparse operations and traditional genetic operators, and then iteratively approached to the optimal reconstruction target. The algorithm need neither to know the sparsity degree of original signal nor to carry out subspace pursuit in reconstruction process. Simulation results show that the proposed algorithm can achieve fast and accurate reconstruction for different dimension signals.
作者
高雷阜
徐部
GAO Leifu;XU Bu(College of Science,Liaoning Technical University,Fuxin 123000,China)
出处
《辽宁工程技术大学学报(自然科学版)》
CAS
北大核心
2018年第4期763-768,共6页
Journal of Liaoning Technical University (Natural Science)
基金
辽宁省教育厅辽宁省高等学校基本科研项目(LJ2017QL031)
辽宁省博士启动基金项目(20170520075)
辽宁省社科规划基金项目(L17BGL004)
关键词
压缩感知
信号重构
遗传算法
稀疏度
子空间跟踪
compressed sensing
signal reconstruction
genetic algorithm
sparsity degree
subspace pursuit