Zekun Niu

Research Direction：Development of Intelligent Optical Fiber Simulation Platform Based on Python
PhD candidate (2018 - present)

E-mail: zekunniu@sjtu.edu.cn

A 2020 Ph.D student in the Department of Electronics, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University. During the undergraduate period, he served as the head of the college's grade meeting and the head of the learning department of the college's student union. He was responsible for organizing many academic activities such as ACM competitions and mobile game development competitions. The current research is based on deep learning to study the compensation and performance optimization technology of optical fiber nonlinearity, using AI as the starting point, combined with professional knowledge in optical communication, to design and optimize the optical transmission system to improve the communication performance limit. Based on the Python language, the first version of the IFTS platform was designed and developed, realizing a complete optical communication algorithm library, integrating optical communication algorithms and AI algorithms, and providing effective support for efficient and intelligent scientific computing in the field of optical communication.

paper:

[1] Z. Niu, H. Yang, H. Zhao, C. Dai, W. Hu and L. Yi, "End-to-End Deep Learning for Long-haul Fiber Transmission Using Differentiable Surrogate Channel," in Journal of Lightwave Technology, 2022.

[2] H. Yang, Z. Niu, et al., "Fast and Accurate Optical Fiber Channel Modeling Using Generative Adversarial Network," in Journal of Lightwave Technology, vol. 39, no. 5, pp. 1322-1333, 1 March1, 2021.

[3] H. Yang, Z. Niu, et al., "Fast and Accurate Waveform Modeling of Long-Haul Multi-Channel Optical Fiber Transmission Using a Hybrid Model-Data Driven Scheme," in Journal of Lightwave Technology, 2022.

[4] H. Yang, H. Zhao, Z. Niu, et al., "Low-complexity full-field ultrafast nonlinear dynamics prediction by a convolutional feature separation modeling method," in Optics Express, 2022.

[5] N. Zhang H. Yang, Z. Niu, et al., "Transformer-Based Long Distance Fiber Channel Modeling for Optical OFDM Systems," in Journal of Lightwave Technology, 2022.

patent:

[1] Lilin Yi, Hang Yang, Zekun Niu, End-to-end modeling method and system based on data-driven optical fiber communication experimental system, CN202211281083.7

[2] Lilin Yi, Hang Yang, Zekun Niu, Fast and accurate modeling method and system for distributed optical fiber channel based on feature decoupling, CN202111478750.6

[3] Lilin Yi, Zekun Niu, Hang Yang, End-to-end optimization method and system based on differentiable auxiliary channels, CN202111405475.5

[4] Lilin Yi, Zekun Niu, Chenhao Dai, Yang Hang, Method and system for calculating mutual information of optical fiber communication transmission system based on deep learning, CN202210540923.0

[5] Lilin Yi, Zekun Niu, Jiaxi Liang, Geometric and probability joint constellation shaping method and system based on mutual information estimation, CN202210010298.9

[6] Lilin Yi, Jiaxi Liang, Zekun Niu, Physical layer security method and system based on mutual information estimation neural network, CN202111574717.3

No data