摘要
模拟电路实现低功耗小波变换的首要任务是对小波函数进行有理函数逼近。针对已有的一些小波逼近方法逼近误差大,系统稳定性不够理想等问题,提出一种基于混合蚁群优化算法的小波逼近方法。利用最小均方误差准则,对小波逼近过程进行具有约束的数学建模;针对构造的优化模型,采用混合蚁群算法求解。仿真实验结果表明,该小波逼近方法逼近效果更好,更具优越性。
The primary task of realizing low-power wavelet transform with analog circuit is to approximate the wavelet function with rational function. Some existing wavelet approximation methods have non-ideal approximation error and less stability of the system. So the approximation method of wavelet, based on hybrid ant colony optimization algorithm, was proposed. The mathematical model with constraint conditions was constructed in the procedure of wavelet approximation by the least mean square error criterion. The hybrid ant colony algorithm was utilized to solve the constructed optimization model. The results of simulation indicate that the approximation method of wavelet functions based on hybrid ant colony optimization has better approximation effect and exhibit superior performance.
作者
谢喜云
李宏民
李文
曾靖
Xie Xiyun;Li Hongmin;Li Wen;ZengJing(School of Information and Communication Engineering,Hunan Institute of Science and Technology,Yueyang 414006,Hunan,China;School of Physics and Electronics,Hunan Institute of Science and Technology,Yueyang 414006,Hunan,China)
出处
《计算机应用与软件》
北大核心
2018年第10期252-256,316,共6页
Computer Applications and Software
基金
湖南省2016教育厅科学研究项目(16K037)
湖南省2017科技计划项目(2017SK2164)
湖南省教育厅重点科研项目(14A062)
关键词
小波变换
模拟电路
最小均方
混合蚁群算法
Wavelet transform
Analog circuit
Least mean square
Hybrid ant colony algorithm
