Title :
A New EM Acceleration Algorithm for Multi-user Detection
Author :
Jinlong, Xian ; Jianwu, Li ; Yang, Yang
Author_Institution :
Henan Univ. of Technol., Zhengzhou, China
Abstract :
The EM iterative algorithm is commonly used in recent years for missing data, which has the character of easy and popular applicability. But the EM algorithm has a fatal weakness that is slow convergence speed, base on that a new EM acceleration algorithm Quasi-Newton EM is proposed in order to solve this problem. In non-Gaussian noise simulation numerical is carried out, the results show that the proposed algorithm has a good performance, comparing with EM algorithm, and the convergence speed is better than standard EM algorithm.
Keywords :
Newton method; convergence; expectation-maximisation algorithm; multiuser detection; convergence speed; expectation maximization acceleration algorithm; expectation maximization iterative algorithm; multiuser detection; nonGaussian noise simulation; quasi-Newton expectation maximization; Acceleration; Convergence; Iterative methods; Maximum likelihood estimation; Multiuser detection; Noise; Signal processing algorithms; EM; MUD; Non-Gaussian noise; Quasi-Newton;
Conference_Titel :
Measuring Technology and Mechatronics Automation (ICMTMA), 2011 Third International Conference on
Conference_Location :
Shangshai
Print_ISBN :
978-1-4244-9010-3
DOI :
10.1109/ICMTMA.2011.43
