A novel blind multiuser detection algorithm based on support vector machines
Yan Zhu, Limin Xiao, Shidong Zhou, Jing Wang · 2005
We propose a novel method based on support vector machines (SVM) for blind multiuser detection. Compared with existing methods, this algorithm has the feature of shorter iterative length and higher robustness. Simulation results show that in a high SNR situation, our method has better BER performance than the normal minimum mean square error (MMSE) algorithm, such as Kalman (Zhang, X.-D. and Wei, W., IEEE Trans. Sig. Process., vol.50. p.87-95, 2002.).