.png){kind=icon}
.png){kind=icon}
Return
Kernel Principal Component Analysis Derived Sparse Structure for RKHS Post-Distorter
.png){kind=icon}
PRE
AI
DOI：10.1109/lsp.2026.3716163.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In depressing nonlinear distortion for visible light communications, reproducing kernel Hilbert space (RKHS) post-distortion has been proved to be effective, but the computational complexity grows dramatically with the dictionary size. Aiming at this problem, we propose a new RKHS post-distortion scheme by employing the kernel principal component analysis to project Gram matrix to accomplish dimension reduction. After achieving sparsification, we adopt adaptive signal processing algorithm to find the weight. Numerical results show that the proposed post-distortion is efficient in tracing the sparse structure, which can surpass conventional sparsifications in the detecting performance with the same dictionary size.
Keywords:
Visible light communication
kernel principal component analysis
reproducing kernel Hilbert space
post-distortion