同步CDMA系统中一种支持向量机的多用户检测器

Multiuser Detector Based on Support Vector Machine for Synchronous DS-CDMA Systems

支持向量机是一种建立在结构风险最小化原理之上的新的分类方法,与一些神经网络方法相比较他能更好地解决小样本问题。将支持向量机应用于同步信道多用户检测中,为研究CDMA多用户检测提供了一条新的途径,仿真结果表明其误码性能优于MMSE,逼近于单用户接收机。

Support Vector Machine（SVM） is a novel classification method based on the principle of structural risk minimization,it can solve small sample learning problems better in comparison with some methods of neural network. That SVM is applied to muhiuser detection for synchronous DS- CDMA opened a new way for realizing muhiuser detection in CDMA. The simulation results show that the performance of error code is better than MMSE,can closely match that of the single user receiver.