Variable step-size widely linear complex-valued NLMS algorithm and its performance analysis
| Autor: | Yi Yu, Haiquan Zhao, Long Shi, Xiangping Zeng |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Normalization (statistics)
Mean squared error Rayleigh distribution System identification 020206 networking & telecommunications 02 engineering and technology Least mean squares filter Gradient noise Control and Systems Engineering Signal Processing Convergence (routing) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Electrical and Electronic Engineering Algorithm Software Computer Science::Cryptography and Security Mathematics Variable (mathematics) |
| Zdroj: | Signal Processing. 165:1-6 |
| ISSN: | 0165-1684 |
| DOI: | 10.1016/j.sigpro.2019.06.029 |
| Popis: | The shrinkage widely linear complex-valued least mean square (SWL-CLMS) algorithm with a variable step-size (VSS) overcomes the tradeoff between fast convergence and low steady-state misalignment, but meanwhile suffers from instability for highly correlated input signals because of the gradient noise amplification problem. To obtain a VSS that is also applicable to the case of highly correlated input signals, in this paper, we propose the VSS widely linear complex-valued normalized least mean square (VSS-WL-CNLMS) algorithm, where the VSS is derived by minimizing the mean-square deviation (MSD). Owing to the normalization, the VSS-WL-CNLMS algorithm is convergent in the mean square sense. By using the Rayleigh distribution, we calculate the mean step-size, which is then combined with the approximate uncorrelating transform to analyze the transient and steady-state mean square error (MSE) behaviors. Simulations for system identification scenario show that the proposed VSS-WL-CNLMS algorithm outperforms some well-known techniques and verify the accuracy of the theoretical analysis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect