An improved normalized BP based decoding algorithm for LDPC codes

Haigang Zhang, Dongfeng Yuan, Cheng Xiang Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

A uniformly most powerful (UMP) belief propagation (BP) based algorithm is referred to as a simplified version of a BP algorithm with reduced complexity but performance loss for low density parity check (LDPC) codes. To compensate the performance loss, the normalized BP based algorithm was proposed, where the normalization factor was derived by mean ratio or by minimizing the mean square error. In this paper, an improved novel normalized BP based algorithm is proposed. The normalization uses multiplicative factor instead of divisional factor. The novel scheme shows better performance than the existing normalized BP based algorithms while keeping the same implementation complexity. The simulation is done for two kinds of LDPC codes: random constructed codes and finite geometry codes. At high signal-to-noise ratio (SNR) region, the proposed scheme can achieve even better performance than BP algorithm for short length random constructed LDPC codes.

Original languageEnglish
Title of host publicationIET 2nd International Conference on Wireless, Mobile and Multimedia Networks, ICWMMN 2008
Pages223-226
Number of pages4
Edition545 CP
DOIs
Publication statusPublished - 2008
EventIET 2nd International Conference on Wireless, Mobile and Multimedia Networks, ICWMMN 2008 - Beijing, China
Duration: 12 Oct 200815 Oct 2008

Conference

ConferenceIET 2nd International Conference on Wireless, Mobile and Multimedia Networks, ICWMMN 2008
CountryChina
CityBeijing
Period12/10/0815/10/08

Keywords

  • BP algorithm
  • LDPC codes
  • Normalized BP

Fingerprint Dive into the research topics of 'An improved normalized BP based decoding algorithm for LDPC codes'. Together they form a unique fingerprint.

Cite this