一种基于非参数似然比准则的ICA盲检测算法

ICA blind detection algorithm based on nonparametric likelihood ratio criterion

为抑制CDMA系统中的多址干扰,提出一种基于非参数似然比准则的ICA盲检测算法.该算法直接由观测信号样本出发,使用核函数估计分离信号的概率密度函数,并结合梯度下降法和似然比准则进行目标用户的信号检测.计算机仿真及与其他算法的比较表明,该算法抑制多址干扰的能力介于FastICA检测和最小均方误差(MMSE)检测之间.

To suppress muhiuser access interference in CDMA system , an independent component analysis （ICA） blind detection algorithm based on nonparametric likelihood ratio criterion was developed. The proposed algorithm is completely blind to the .sources and has the ability to separate the mixed sources simuhaneously. The signal of desired user is detected by using kernel function to estimate probability density function and combining gradient descent algorithm with likelihood ratio criterion. Computer simulation and comparing with other algorithms show that the proposed algorithm provides interference suppression ability between FastlCA detection and minimum mean square error （ MMSE）.