克隆粒子群算法的镜像层叠滤波器的优化设计  

Optimizing stacked filters with mirrored threshold decomposition using an improved clone selection and PSO algorithm

作　　者：赵春晖[1] 肖晓俊[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《智能系统学报》2008年第2期129-134,共6页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(60672034)

摘　　要：层叠滤波器是一种具有层叠性和阈值分解性的滑动窗非线性数字滤波器.层叠滤波器的优化设计过程关键就是对正布尔函数优化.本文利用了克隆粒子群优化算法的全局寻优能力和免疫系统的免疫信息处理机制,改善了粒子群优化算法摆脱局部极值点的能力,提高了算法进化过程中的收敛速度和精度.仿真实验的结果也表明,该算法在正布尔函数的优化效果得到了显著改善,收敛加快,试验结果表明该算法设计的层叠滤波器具有良好的细节保持能力和去噪声能力,有效地改善了滤波性能.Stack filters are a class of nonlinear digital filters with sliding windows. Their two main properties are threshold decomposition and stacking. Optimal design of these filters requires optimization of a positive Boolean function （PBF）. Optimization of stacked filters using traditional algorithms is easily trapped in a local optimum. To prevent this in recent years the bionic clone selection and PSO algorithms were proposed. The combination of these two algorithms avoids the problem of falling into a local minimum, greatly improving convergence speed and accuracy. Experimental results show that optimally stacked filters effectively suppress noise while retaining details of images and enhancing filtering capability.

关 键 词：镜像阈值分解 正布尔函数(PBF) 层叠滤波器 克隆选择 粒子群 

分 类 号：TN713[电子电信—电路与系统]