摘要
针对传统算法在处理传感器网络的大规模信号时,运算复杂度显著增大,性能急剧下降的问题,提出了启发式同步自适应迭代阈值重构算法。采用启发式差错控制函数选择代价最少的方向逐行同步收缩逼近最优解,并结合由自适应递减幂指数参数所确定的非线性阈值函数,进一步判断修正重构信号。仿真结果表明,启发式同步自适应迭代阈值重构算法以更少的测量值和迭代次数重构信号,其信噪比提高了60 dB。
In consideration of the issues of the high computation complexity and the weakness performance of traditional algorithm for very large-scale problems in sensor networks,this paper proposed a new method.Hierarchical simultaneous adaptive iterative threshold algorithm allowed reconstructing the optimal sparse signals simultaneously by processing row by row of the compressed signals along the least cost direction.Moreover,with the nonlinearly thresholding function,it was able to fix the reconstruction signals.The extensive experimental results confirm the validity and high performance of the HSAIT algorithm with fewer numbers of measures and iterative,and the signal to noise ratio improves to 60dB.
出处
《计算机应用研究》
CSCD
北大核心
2012年第11期4232-4234,共3页
Application Research of Computers
基金
国家自然科学基金资助项目(60872064)
关键词
传感器网络
分布式压缩传感
迭代阈值
非线性函数
重构
sensor networks
distributed compressive sensing
iterative threshold
nonlinearly function
reconstruction
