Extreme learning machine-based receiver for MIMO LED communications

Authors

Dawei Gao, University of WollongongFollow
Qinghua Guo, University of WollongongFollow

RIS ID

139333

Publication Details

D. Gao & Q. Guo, "Extreme learning machine-based receiver for MIMO LED communications," Digital Signal Processing: A Review Journal, vol. 95, pp. 102594-1-102594-6, 2019.

Abstract

This work concerns receiver design for light-emitting diode (LED) multiple input multiple output (MIMO) communications where the LED nonlinearity can severely degrade the performance of communications. We firstly propose an extreme learning machine (ELM) based receiver to jointly handle the LED nonlinearity and cross-LED interference. Then, by taking advantage of the features of the ELM, we propose to use a circulant structure for the input weight matrix and the fast Fourier transform (FFT) for implementation, leading to significant computational complexity reduction. It is demonstrated that, the proposed ELM based receivers can handle the nonlinearity and interference much more effectively compared to conventional techniques, and the low complexity ELM-based receiver with circulant input matrix delivers almost the same performance as the receiver based on the conventional ELM.