EM acceleration algorithm using the vector-ε apply in multi-user detection

Xian Jinlong; Li Jianwu

doi:10.4028/www.scientific.net/AMR.225-226.280

EM acceleration algorithm using the vector-ε apply in multi-user detection

Xian Jinlong^*, Li Jianwu

^*Corresponding author for this work

Henan University of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The EM iterative algorithm is a very general and popular algorithm that commonly used for missing data to find maximum likelihood in recent years, which has the character of stability, flexibility and simlicity. However, the EM algorithm has a great weakness that the convergence speed is slowly; Acceleration of the EM algorithm using the Vector-ε method is proposed in order to solve this problem in this paper. In Multi-user Detection, via this accelerated algorithm, we get a good performance which trends to ML performance and improving the computational efficiency, and compared its speed of convergence with the EM algorithm that Vector-å acceleration algorithm has faster convergence than the standard EM algorithm.

Original language	English
Title of host publication	Advanced Research on Automation, Communication, Architectonics and Materials
Pages	280-283
Number of pages	4
DOIs	https://doi.org/10.4028/www.scientific.net/AMR.225-226.280
Publication status	Published - 2011
Externally published	Yes
Event	2011 International Conference on Automation, Communication, Architectonics and Materials, ACAM2011 - Wuhan, China Duration: 18 Jun 2011 → 19 Jun 2011

Publication series

Name	Advanced Materials Research
Volume	225-226
ISSN (Print)	1022-6680

Conference

Conference	2011 International Conference on Automation, Communication, Architectonics and Materials, ACAM2011
Country/Territory	China
City	Wuhan
Period	18/06/11 → 19/06/11

Keywords

EM iterative algorithm
Multi-user detection
Vector-å algorithm

Access to Document

10.4028/www.scientific.net/AMR.225-226.280

Cite this

@inproceedings{c9cce0876522485ab705141a6b670c93,

title = "EM acceleration algorithm using the vector-ε apply in multi-user detection",

abstract = "The EM iterative algorithm is a very general and popular algorithm that commonly used for missing data to find maximum likelihood in recent years, which has the character of stability, flexibility and simlicity. However, the EM algorithm has a great weakness that the convergence speed is slowly; Acceleration of the EM algorithm using the Vector-ε method is proposed in order to solve this problem in this paper. In Multi-user Detection, via this accelerated algorithm, we get a good performance which trends to ML performance and improving the computational efficiency, and compared its speed of convergence with the EM algorithm that Vector-{\aa} acceleration algorithm has faster convergence than the standard EM algorithm.",

keywords = "EM iterative algorithm, Multi-user detection, Vector-{\aa} algorithm",

author = "Xian Jinlong and Li Jianwu",

year = "2011",

doi = "10.4028/www.scientific.net/AMR.225-226.280",

language = "English",

isbn = "9783037851036",

series = "Advanced Materials Research",

pages = "280--283",

booktitle = "Advanced Research on Automation, Communication, Architectonics and Materials",

note = "2011 International Conference on Automation, Communication, Architectonics and Materials, ACAM2011 ; Conference date: 18-06-2011 Through 19-06-2011",

}

Jinlong, X & Jianwu, L 2011, EM acceleration algorithm using the vector-ε apply in multi-user detection. in Advanced Research on Automation, Communication, Architectonics and Materials. Advanced Materials Research, vol. 225-226, pp. 280-283, 2011 International Conference on Automation, Communication, Architectonics and Materials, ACAM2011, Wuhan, China, 18/06/11. https://doi.org/10.4028/www.scientific.net/AMR.225-226.280

TY - GEN

T1 - EM acceleration algorithm using the vector-ε apply in multi-user detection

AU - Jinlong, Xian

AU - Jianwu, Li

PY - 2011

Y1 - 2011

N2 - The EM iterative algorithm is a very general and popular algorithm that commonly used for missing data to find maximum likelihood in recent years, which has the character of stability, flexibility and simlicity. However, the EM algorithm has a great weakness that the convergence speed is slowly; Acceleration of the EM algorithm using the Vector-ε method is proposed in order to solve this problem in this paper. In Multi-user Detection, via this accelerated algorithm, we get a good performance which trends to ML performance and improving the computational efficiency, and compared its speed of convergence with the EM algorithm that Vector-å acceleration algorithm has faster convergence than the standard EM algorithm.

AB - The EM iterative algorithm is a very general and popular algorithm that commonly used for missing data to find maximum likelihood in recent years, which has the character of stability, flexibility and simlicity. However, the EM algorithm has a great weakness that the convergence speed is slowly; Acceleration of the EM algorithm using the Vector-ε method is proposed in order to solve this problem in this paper. In Multi-user Detection, via this accelerated algorithm, we get a good performance which trends to ML performance and improving the computational efficiency, and compared its speed of convergence with the EM algorithm that Vector-å acceleration algorithm has faster convergence than the standard EM algorithm.

KW - EM iterative algorithm

KW - Multi-user detection

KW - Vector-å algorithm

UR - http://www.scopus.com/inward/record.url?scp=79955885796&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMR.225-226.280

DO - 10.4028/www.scientific.net/AMR.225-226.280

M3 - Conference contribution

AN - SCOPUS:79955885796

SN - 9783037851036

T3 - Advanced Materials Research

SP - 280

EP - 283

BT - Advanced Research on Automation, Communication, Architectonics and Materials

T2 - 2011 International Conference on Automation, Communication, Architectonics and Materials, ACAM2011

Y2 - 18 June 2011 through 19 June 2011

ER -

EM acceleration algorithm using the vector-ε apply in multi-user detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this