Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Low-complexity mitigation of multipath interference in PAM-4 IM/DD systems via recursive filtering.

Optics express·2026
Same author

Interfacial Polarization Engineering in MXene-Polymer Nanofibers for High-Output Triboelectric Nanogenerators.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

5α-Reductase underscores the development of pectoral fin breeding tubercles in zebrafish.

Communications biology·2026
Same author

Integrating fixed and mobile coherent optical access networks for unified broadband services.

Communications engineering·2026
Same author

Integrated photonics enabling ultra-wideband fibre-wireless communication.

Nature·2026
Same author

Interconnected counter-propagating recirculating loops with high-loss loop back path for long-haul integrated sensing and communication in-lab emulation.

Optics letters·2026

Related Experiment Video

Updated: Dec 13, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
09:43

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

10.2K

Cascade recurrent neural network-assisted nonlinear equalization for a 100  Gb/s PAM4 short-reach direct detection

Zhaopeng Xu, Chuanbowen Sun, Tonghui Ji

    Optics Letters
    |August 1, 2020
    PubMed
    Summary

    We developed a new cascade recurrent neural network (RNN) equalizer to combat nonlinear signal distortion in 100 Gb/s pulse amplitude modulation (PAM)4 systems. This advanced equalizer significantly improves performance and reduces training time for short-reach optical links.

    More Related Videos

    Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy
    09:57

    Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy

    Published on: July 25, 2022

    4.4K
    Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS
    12:56

    Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

    Published on: October 17, 2010

    14.0K

    Related Experiment Videos

    Last Updated: Dec 13, 2025

    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
    09:43

    Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

    Published on: March 20, 2017

    10.2K
    Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy
    09:57

    Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy

    Published on: July 25, 2022

    4.4K
    Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS
    12:56

    Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

    Published on: October 17, 2010

    14.0K

    Area of Science:

    • Optical Communications
    • Machine Learning for Signal Processing
    • Nonlinear System Equalization

    Background:

    • Short-reach optical communication systems, such as those using Pulse Amplitude Modulation (PAM)4, face significant nonlinear impairments.
    • These impairments arise from the interplay of linear channel effects, square-law detection, directly modulated laser (DML) frequency chirp, and device nonlinearities.
    • Effective equalization is crucial for maintaining signal integrity and achieving high data rates.

    Purpose of the Study:

    • To propose and experimentally validate a novel cascade Recurrent Neural Network (RNN)-based nonlinear equalizer.
    • To address the significant nonlinear signal distortion in a 100 Gb/s PAM4 short-reach direct detection system.
    • To demonstrate the superiority of the proposed equalizer over existing feedforward and non-cascade neural network (NN) approaches.

    Main Methods:

    • Development of a cascade RNN-based nonlinear equalizer architecture.
    • Experimental demonstration of a 100 Gb/s PAM4 optical link over 15 km of standard single-mode fiber (SSMF).
    • Utilizing a 16 GHz directly modulated laser (DML) in the C-band for signal transmission.

    Main Results:

    • The proposed cascade RNN equalizer significantly outperformed feedforward and non-cascade NN equalizers in mitigating nonlinear impairments.
    • A bit-error rate (BER) below the 7% hard-decision forward error correction (FEC) threshold was achieved for receiver power levels above 5 dBm.
    • The cascade structure of the RNN equalizer reduced training time by half compared to traditional non-cascade NN equalizers.

    Conclusions:

    • The cascade RNN-based equalizer shows great potential for effectively tackling nonlinear signal distortion in high-speed optical communication systems.
    • This novel approach offers improved performance and efficiency for PAM4 direct detection systems.
    • The demonstrated equalization technique is vital for future advancements in optical data transmission.