Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter

Ching Wei Peng; David W.U. Chan; Chi Wai Chow; Tun Yao Hung; Yin He Jian; Yeyu Tong; Pin Cheng Kuo; Guan Hong Chen; Yang Liu; Chien Hung Yeh; Hon Ki Tsang

doi:10.1016/j.optcom.2022.129067

Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter

Ching Wei Peng, David W.U. Chan, Chi Wai Chow^*, Tun Yao Hung, Yin He Jian, Yeyu Tong, Pin Cheng Kuo, Guan Hong Chen, Yang Liu, Chien Hung Yeh, Hon Ki Tsang^*

^*Corresponding author for this work

Department of Photonics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

We propose and experimentally illustrate the use of Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction (IFE) to recover 4-level pulse amplitude modulation (PAM4) data transmitted from a silicon micro-ring modulator (SiMRM) operated at 160 Gbit/s. Pre-hard-decision (HD) forward error correction (FEC) requirement (i.e. bit-error-rate, BER < 3.8 × 10⁻³) is achieved in the 160 Gbit/s PAM4 signal produced using a 47-GHz bandwidth SiMRM after 1 km single-mode-fiber (SMF) transmission.

Original language	English
Article number	129067
Journal	Optics Communications
Volume	529
DOIs	https://doi.org/10.1016/j.optcom.2022.129067
State	Published - 15 Feb 2023

Keywords

Deep learning
Fiber optical communication
Machine learning
Silicon photonics

Access to Document

10.1016/j.optcom.2022.129067

Cite this

Peng, C. W., Chan, D. W. U., Chow, C. W., Hung, T. Y., Jian, Y. H., Tong, Y., Kuo, P. C., Chen, G. H., Liu, Y., Yeh, C. H., & Tsang, H. K. (2023). Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter. Optics Communications, 529, Article 129067. https://doi.org/10.1016/j.optcom.2022.129067

@article{abd227dfea564589924611e1fc78cca4,

title = "Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter",

abstract = "We propose and experimentally illustrate the use of Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction (IFE) to recover 4-level pulse amplitude modulation (PAM4) data transmitted from a silicon micro-ring modulator (SiMRM) operated at 160 Gbit/s. Pre-hard-decision (HD) forward error correction (FEC) requirement (i.e. bit-error-rate, BER < 3.8 × 10−3) is achieved in the 160 Gbit/s PAM4 signal produced using a 47-GHz bandwidth SiMRM after 1 km single-mode-fiber (SMF) transmission.",

keywords = "Deep learning, Fiber optical communication, Machine learning, Silicon photonics",

author = "Peng, {Ching Wei} and Chan, {David W.U.} and Chow, {Chi Wai} and Hung, {Tun Yao} and Jian, {Yin He} and Yeyu Tong and Kuo, {Pin Cheng} and Chen, {Guan Hong} and Yang Liu and Yeh, {Chien Hung} and Tsang, {Hon Ki}",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2023",

month = feb,

day = "15",

doi = "10.1016/j.optcom.2022.129067",

language = "English",

volume = "529",

journal = "Optics Communications",

issn = "0030-4018",

publisher = "Elsevier",

}

TY - JOUR

T1 - Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter

AU - Peng, Ching Wei

AU - Chan, David W.U.

AU - Chow, Chi Wai

AU - Hung, Tun Yao

AU - Jian, Yin He

AU - Tong, Yeyu

AU - Kuo, Pin Cheng

AU - Chen, Guan Hong

AU - Liu, Yang

AU - Yeh, Chien Hung

AU - Tsang, Hon Ki

PY - 2023/2/15

Y1 - 2023/2/15

N2 - We propose and experimentally illustrate the use of Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction (IFE) to recover 4-level pulse amplitude modulation (PAM4) data transmitted from a silicon micro-ring modulator (SiMRM) operated at 160 Gbit/s. Pre-hard-decision (HD) forward error correction (FEC) requirement (i.e. bit-error-rate, BER < 3.8 × 10−3) is achieved in the 160 Gbit/s PAM4 signal produced using a 47-GHz bandwidth SiMRM after 1 km single-mode-fiber (SMF) transmission.

AB - We propose and experimentally illustrate the use of Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction (IFE) to recover 4-level pulse amplitude modulation (PAM4) data transmitted from a silicon micro-ring modulator (SiMRM) operated at 160 Gbit/s. Pre-hard-decision (HD) forward error correction (FEC) requirement (i.e. bit-error-rate, BER < 3.8 × 10−3) is achieved in the 160 Gbit/s PAM4 signal produced using a 47-GHz bandwidth SiMRM after 1 km single-mode-fiber (SMF) transmission.

KW - Deep learning

KW - Fiber optical communication

KW - Machine learning

KW - Silicon photonics

UR - http://www.scopus.com/inward/record.url?scp=85141334987&partnerID=8YFLogxK

U2 - 10.1016/j.optcom.2022.129067

DO - 10.1016/j.optcom.2022.129067

M3 - Article

AN - SCOPUS:85141334987

SN - 0030-4018

VL - 529

JO - Optics Communications

JF - Optics Communications

M1 - 129067

ER -

Long Short Term Memory Neural Network (LSTMNN) and inter-symbol feature extraction for 160 Gbit/s PAM4 from silicon micro-ring transmitter

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this