基于神经网络的智能多用户检测技术在CDMA中的应用  

The Application of Neural Networks-based Intelligent Multiuser Detection Technology to CDMA Systems

作　　者：牛志强[1] 吴新余[1] 

机构地区：[1]南京邮电学院电子工程系,江苏南京210003

出　　处：《南京邮电学院学报》2001年第1期43-47,共5页Journal of Nanjing University of Posts and Telecommunications(Natural Science)

摘　　要：多用户检测技术是第 3代移动通信系统IMT 2 0 0 0中的一项关键技术。求解最优多用户检测器的目标函数的最小值问题可以转化为求解Hopfield神经网络的能量函数的最小值问题。对两种基于神经网络的智能多用户检测器进行性能分析和计算机仿真 ,通过与最佳多用户检测器和传统检测器的比较 ,证实了这两种神经网络检测器都能较好地实现多用户检测的功能 ,因此 。The technique of multiuser detection is one of the key ones in the 3G mobile communication system IMT-2000.It is shown that the problem of minimizing the objective function of the optimal multiuser detector can be translated into minimizing the energy function of Hopfield Neural Networks(HNNs).Two kinds of intelligent multiuser detectors basd on HNNs are proposed in this paper.The performance analysis and computer simulation is performed on both detectors.Compared to that of the optimal multiuser detector and the conventional detector,we testify that two kinds of neural network detectors can realize multiuser detection quite well and they are both feasible methods.

关 键 词：码分多址 多用户检测 HOPFIELD神经网络 IMF-2000 CDMA IMT-2000 移动通信 

分 类 号：TN929.533[电子电信—通信与信息系统]