| Autor: |
Shen-Jie Tang, Yu Tang, Xi-Feng Li, Bo Liu, Dong-Jie Bi, Guo Yi, Xue-Peng Zheng, Li-Biao Peng, Yong-Le Xie |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Journal of Electronic Science and Technology, Vol 21, Iss 3, Pp 100217- (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2666-223X |
| DOI: |
10.1016/j.jnlest.2023.100217 |
| Popis: |
Kernel adaptive filters (KAFs) have sparked substantial attraction for online non-linear learning applications. It is noted that the effectiveness of KAFs is highly reliant on a rational learning criterion. Concerning this, the logarithmic hyperbolic cosine (lncosh) criterion with better robustness and convergence has drawn attention in recent studies. However, existing lncosh loss-based KAFs use the stochastic gradient descent (SGD) for optimization, which lack a trade-off between the convergence speed and accuracy. But recursion-based KAFs can provide more effective filtering performance. Therefore, a Nyström method-based robust sparse kernel recursive least lncosh loss algorithm is derived in this article. Experiments via measures and synthetic data against the non-Gaussian noise confirm the superiority with regard to the robustness, accuracy performance, and computational cost. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
