摘要
广义特征分解技术在现代自适应信号处理中占有重要地位.本文提出了一种新的无约束损失函数用于广义特征分解,并且分析了损失函数的特性.通过应用递推最小二乘(RLS)技术来最小化损失函数,得到了用于求解最大广义特征值对应的广义特征向量的自适应算法.并将这种算法应用于CDMA系统中的智能天线波束形成问题.仿真结果表明算法具有快速收敛和动态跟踪能力.
The generalized eigen-decomposition plays important roles in modem adaptive signal processing applications. In this paper, a novel unconstrained cost function for the generalized eigen-deeomposition is presented and the properties of the cost function are analyzed. By applying recursive least-squares technique to minimize the cost function,an adaptive algorithm is proposed for finding the most dominant generalized eigenveetor. The algorithm is also applied for the beamforming of the smart antenna in CDMA systems. The simulation results show the proposed algorithm has fast convergence and dynamic tracking capability.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2005年第7期1258-1261,共4页
Acta Electronica Sinica
基金
国家863计划资助项目(No.2003AA103710)
关键词
广义特征向量
自适应算法
广义特征分解
递推最小二乘
自适应波束形成
generalized eigenvector
adaptive algorithm
generalized eigen-decomposition
recursive least-squares
adaptive beamforming