Cover Story: Hu F C, Holguin-Lerma J A, Mao Y, Zou P, Shen C et al. Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode. Opto-Electron Adv 3, 200009 (2020). 

Group-Ⅲ-nitride superluminescent diodes (SLDs) are emerging as light sources for white lighting and visible light communications (VLCs) owning to their droop-free, low speckle noise, and large modulation bandwidth properties. However, the investigation on SLD-based VLC system together with some advanced signal processing algorithms is insufficient. Recently, Professor Nan Chi from Fudan University and Professor Boon S. Ooi from King Abdullah University of Science and Technology reported the first implementation of a novel memory-polynomial-aided neural network (MPANN) post-equalizer for carrierless amplitude and phase (CAP)-based visible light communication (VLC), together with the first use of CAP modulation on a GaN-based SLD. They implemented the MPANN-aided CAP modulation to achieve a high-speed communication link of 2.95 Gbps with a blue SLD. Here, the MPANN used as a robust and efficient post-equalization filter of CAP shows unprecedented advantages over conventional filters by mitigating the linear and nonlinear damage of the VLC channel with a better performance and lower complexity. Moreover, this proof-of-concept investigation lays the foundation for further implementing SLDs in efficient VLC systems, smart lighting, and SLD-Light-fidelity. It is believed that the newsworthy results in the present work appeal to the scientific communities interested in edge-emitting devices, optical communications, and deep-learning photonics.