### Abstract

In this paper, we investigate the optimal variable step-size approach for the transform-domain least-mean-square (TDLMS) algorithm to achieve fast convergence speed and low steady-state misadjustment. By minimizing the mean-square deviation (MSD) between the filter weight vector and the true vector, we derive and approximate the optimal variable step-size for the TDLMS algorithm given autoregressive (AR) process as input signals. The resulted variable step-size has simple formulation and easily-setting parameters. Computer simulation is demonstrated in the framework of adaptive system modeling with a fourth-order AR input process. The overall performance are observed superior to the existing popular variable step-size approaches of the TDLMS algorithm.

Original language | English (US) |
---|---|

Title of host publication | Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 |

Pages | 968-971 |

Number of pages | 4 |

DOIs | |

State | Published - Aug 19 2013 |

Event | 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 - Melbourne, VIC, Australia Duration: Jun 19 2013 → Jun 21 2013 |

### Publication series

Name | Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 |
---|

### Other

Other | 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013 |
---|---|

Country | Australia |

City | Melbourne, VIC |

Period | 6/19/13 → 6/21/13 |

### Fingerprint

### ASJC Scopus subject areas

- Electrical and Electronic Engineering

### Cite this

*Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013*(pp. 968-971). [6566507] (Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013). https://doi.org/10.1109/ICIEA.2013.6566507

**A variable step-size transform-domain LMS algorithm based on minimum mean-square deviation for autoregressive process.** / Zhao, Shengkui; Jones, Douglas L; Man, Zhihong; Khoo, Suiyang.

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

*Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013.*, 6566507, Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013, pp. 968-971, 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013, Melbourne, VIC, Australia, 6/19/13. https://doi.org/10.1109/ICIEA.2013.6566507

}

TY - GEN

T1 - A variable step-size transform-domain LMS algorithm based on minimum mean-square deviation for autoregressive process

AU - Zhao, Shengkui

AU - Jones, Douglas L

AU - Man, Zhihong

AU - Khoo, Suiyang

PY - 2013/8/19

Y1 - 2013/8/19

N2 - In this paper, we investigate the optimal variable step-size approach for the transform-domain least-mean-square (TDLMS) algorithm to achieve fast convergence speed and low steady-state misadjustment. By minimizing the mean-square deviation (MSD) between the filter weight vector and the true vector, we derive and approximate the optimal variable step-size for the TDLMS algorithm given autoregressive (AR) process as input signals. The resulted variable step-size has simple formulation and easily-setting parameters. Computer simulation is demonstrated in the framework of adaptive system modeling with a fourth-order AR input process. The overall performance are observed superior to the existing popular variable step-size approaches of the TDLMS algorithm.

AB - In this paper, we investigate the optimal variable step-size approach for the transform-domain least-mean-square (TDLMS) algorithm to achieve fast convergence speed and low steady-state misadjustment. By minimizing the mean-square deviation (MSD) between the filter weight vector and the true vector, we derive and approximate the optimal variable step-size for the TDLMS algorithm given autoregressive (AR) process as input signals. The resulted variable step-size has simple formulation and easily-setting parameters. Computer simulation is demonstrated in the framework of adaptive system modeling with a fourth-order AR input process. The overall performance are observed superior to the existing popular variable step-size approaches of the TDLMS algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84881434800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881434800&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2013.6566507

DO - 10.1109/ICIEA.2013.6566507

M3 - Conference contribution

AN - SCOPUS:84881434800

SN - 9781467363211

T3 - Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013

SP - 968

EP - 971

BT - Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications, ICIEA 2013

ER -