摘要
提出了一种基于神经网络算法的频谱分析方法,研究了神经网络算法的收敛性,给出了频谱分析的应用实例.研究结果表明,本文提出的频谱分析方法不涉及复数的乘法运算和加法运算,计算精度高,且速度快,便于软件和硬件实现,特别适合于DSP软硬件实现,因而是一种有效的频谱分析方法.
The method of spectrum analysis by using neural network algorithm was presented. The convergence of the neural-network algorithm was studied. Simulation examples of spectrum analysis were given. The results show that the approaches of spectrum analysis presented in this study are not involved in plural multiplication operation and plural addition operation. The high accuracy and fast convergence speed are the features of the method presented in this study. Software and hardware of the approach are easily implemented. It is especially fit for the implementation of software and hardware about DSP. Therefore, the methods of spectrum analysis proposed in this study are effective.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
2007年第2期141-145,共5页
Journal of Infrared and Millimeter Waves
基金
国家自然科学基金(60375001)资助项目
关键词
神经网络
频谱分析
算法
收敛性
neural-network
spectrum analysis
algorithm
convergence
