Coherent chaotic optical communication of 30 Gb/s over 340-km fiber transmission via deep learning.

Chaotic optical communication has attracted much attention as a hardware encryption method in the physical layer. Limited by the requirements of chaotic hardware synchronization, fiber transmission impairments are restrictedly compensated in the optical domain. There has been little experimental demonstration of high-speed and long-distance chaotic optical communication systems.

Effect of ADC parameters on neural network based chaotic optical communication.

The performance of traditional chaotic optical communications depends on the matching parameters of the chaotic transmitter and receiver. The chaotic receiver based on the neural network (NN) can solve the dependence on matching parameters, but the analog-to-digital converter (ADC) has an effect on the decryption performance. In this paper, the effects of sampling rate and digitalizing bit for ADC on NN-based chaotic optical communication systems with different feedback strengths at different bit rates are numerically studied.

32 Gb/s chaotic optical communications by deep-learning-based chaos synchronization.

Chaotic optical communications were originally proposed to provide high-level physical layer security for optical communications. Limited by the difficulty of chaos synchronization, there has been little experimental demonstration of high-speed chaotic optical communications, and point to multipoint chaotic optical networking is hard to implement. Here, we propose a method to overcome the current limitations.

Reservoir computing system with double optoelectronic feedback loops.

Reservoir computing (RC) by supervised training, a bio-inspired paradigm, is gaining popularity for processing time-dependent data. Compared to conventional recurrent neural networks, RC is facilely implemented by available hardware and overcomes some obstacles in training period, such as slow convergence and local optimum. In this paper, we propose and characterize a novel reservoir computing system based on a semiconductor laser with double optoelectronic feedback loops.

Chaotic optical communications over 100-km fiber transmission at 30-Gb/s bit rate.

For the first time, to the best of our knowledge, we experimentally demonstrate a successful 30-Gb/s signal transmission of a duobinary message hidden in a chaotic optical carrier over 100-km fiber. Thanks to the duobinary modulation format with high spectral efficiency, the 30-Gb/s signal can be encrypted by a 10-GHz-wide chaotic carrier. A digital signal processing technique can be used to convert duobinary data into binary data on the receiver side.