新型Lagrange神经网络盲多用户检测

A New Blind Multi-user Detection Based on Lagrange Neural Network

码分多址系统中,多用户检测是消除多址干扰(MAI)和远近效应(FNE)的关键技术。基于最小输出能量准则,将盲多用户检测转化为约束优化问题,利用Lagrange函数将约束问题转化为无约束问题,再利用神经网络的动态特性对其进行求解。仿真表明,该算法误码率低、抗远近效应强。

In the CDMA wireless communications system,multi-user detection is a key technique erasi.ng multi-access interference （MAI） and near-far effect （NFE）. The new detection in this paper is based on min output energy. Firstly,blind multi-user detection is transformed into constraint optimum problem. Secondly, constraint problem is transformed into unconstrained problem by Lagrange function. Then, the dynamic characters of neural network are used in solving procedure of unconstrained problem. Theoretical analysis and numerical simulation indicate that the proposed algorithm has such merits as low bit error rate,strong farnear-resistance.