Abstract
We show an adaptive deep-learning algorithm that recovers the distorted broadband signals of defective microwave photonic (MWP) receiving systems. With data-driven supervised training, the adopted neural network automatically learns the end-to-end distortion effects of the photonic analog links and recovers the received signals in the digital domain. Through changing the training data sets and retraining the same neural network, this algorithm can be applied in various MWP receiving systems. Two MWP receiving systems are set up for experimentally demonstrating the capability of broadband signal recovery. Results show that the neural network can reduce the signal distortion (measured with mean square error) by ${\sim}{18}\;{\rm dB}$. Moreover, visualization analysis indicates that the proposed algorithm is potentially adaptive to more MWP receiving systems and applications. The noise robustness of this algorithm is also verified so that it is applicable in noisy situations. The proposed algorithm improves the performance of MWP receiving systems through appending a deep learning digital processor whose deployment is low cost.
© 2021 Optical Society of America
Full Article | PDF ArticleMore Like This
Fei Jiang, Zhenhai Zhang, Zixiao Lu, Honglang Li, Yahui Tian, Yixin Zhang, and Xuping Zhang
Opt. Express 29(21) 33467-33480 (2021)
Alejandro Escobar Pérez, David Zabala-Blanco, Cesar A. Azurdia Meza, Neil Guerrero González, and Jhon J. Granada Torres
Appl. Opt. 60(28) 8939-8948 (2021)
Hui Chen, Wenqing Niu, Yiheng Zhao, Junwen Zhang, Nan Chi, and Ziwei Li
Opt. Express 29(14) 21773-21782 (2021)