基于支持向量机的非线性多用户检测

Support vector machine for nonlinear multi-user detection

基于支持向量机的非线性多用户检测器具有利用较少训练数据检测CDMA通信系统信号、性能稳定的优点。由于通信系统中的多径干扰和信道的非线性,尤其在非高斯噪声的环境下,线性的检测器已经不再适用。本文将支持向量机应用于非线性多用户检测中,从仿真结果来看,基于支持向量机的非线性多用户检测性能接近于最佳检测器且优于线性检测器。

Support Vector Machine （SVM） is proposed as a nonlinear Multi - User Detector（MUD） trom a relatively small training data block to detect CDMA signals. Because of the steady capability, it is used in MUD, then it is improved in the complexity and rate of operation. Because of the multiple access interference and the nonlinearity of channel, the performance of linear detector will be degraded substantially. Especially in the case of non- gaussian noise environment. SVM which is a nonlinear method is proposed to implement the multiuser detector. As the simulation results show, the performance of SVM MUD is very close to the optimal detector and prior to the linear MUD.