Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning

N. Dikhaminjia; G. Tsintsadze; Z. Kiguradze; J. He; Mikheil Tsiklauri; James L. Drewniak; A. Chada; B. Mutnury

doi:10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning

N. Dikhaminjia
, G. Tsintsadze
, Z. Kiguradze
, J. He
, Mikheil Tsiklauri
, James L. Drewniak
, A. Chada
, B. Mutnury

Electrical and Computer Engineering

Missouri University of Science and Technology

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

Abstract

The paper elaborates an efficient algorithm for optimization of joint Feed-Forward Equalization (FFE) and Decision Feedback Equalization (DFE) for non-return-to-zero (NRZ) and 4 level pulse amplitude modulation (PAM-4) signals using Bayesian Machine Learning approach previously introduced for NRZ by authors and expanded for PAM-4. A new optimal covariant function and hyper-parameters has been selected for the Bayesian optimization. Cost function for the Bayesian optimization is chosen based on eye height. The proposed method was compared to the conventional Least Mean Square (LMS) method and showed significant improvement. Test cases were performed for several data rates of NRZ and PAM-4 signals with crosstalk and injected jitter. Test results show that the proposed algorithm is the more effective the higher data rates are considered.

Original language	American English
Journal	Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC)
DOIs	https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157
State	Published - Aug 13 2021

Keywords

Bayesian Optimization
Cost Function
Covariant Function
DFE
Equalization
FFE
Joint Optimization
Tap Coefficients

Disciplines

Electromagnetics and Photonics

Access to Document

10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157License: Unspecified

https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

Cite this

Dikhaminjia, N., Tsintsadze, G., Kiguradze, Z., He, J., Tsiklauri, M., Drewniak, J. L., Chada, A., & Mutnury, B. (2021). Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning. Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC). https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

Dikhaminjia, N, Tsintsadze, G, Kiguradze, Z, He, J, Tsiklauri, M, Drewniak, JL, Chada, A & Mutnury, B 2021, 'Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning', Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC). https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

@article{3e3e9fc866de4b26b19dff42ced9df21,

title = "Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning",

abstract = " The paper elaborates an efficient algorithm for optimization of joint Feed-Forward Equalization (FFE) and Decision Feedback Equalization (DFE) for non-return-to-zero (NRZ) and 4 level pulse amplitude modulation (PAM-4) signals using Bayesian Machine Learning approach previously introduced for NRZ by authors and expanded for PAM-4. A new optimal covariant function and hyper-parameters has been selected for the Bayesian optimization. Cost function for the Bayesian optimization is chosen based on eye height. The proposed method was compared to the conventional Least Mean Square (LMS) method and showed significant improvement. Test cases were performed for several data rates of NRZ and PAM-4 signals with crosstalk and injected jitter. Test results show that the proposed algorithm is the more effective the higher data rates are considered.",

keywords = "Bayesian Optimization, Cost Function, Covariant Function, DFE, Equalization, FFE, Joint Optimization, Tap Coefficients",

author = "N. Dikhaminjia and G. Tsintsadze and Z. Kiguradze and J. He and Mikheil Tsiklauri and Drewniak, \{James L.\} and A. Chada and B. Mutnury",

year = "2021",

month = aug,

day = "13",

doi = "10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157",

language = "American English",

journal = "Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC)",

}

TY - JOUR

T1 - Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning

AU - Dikhaminjia, N.

AU - Tsintsadze, G.

AU - Kiguradze, Z.

AU - He, J.

AU - Tsiklauri, Mikheil

AU - Drewniak, James L.

AU - Chada, A.

AU - Mutnury, B.

PY - 2021/8/13

Y1 - 2021/8/13

N2 - The paper elaborates an efficient algorithm for optimization of joint Feed-Forward Equalization (FFE) and Decision Feedback Equalization (DFE) for non-return-to-zero (NRZ) and 4 level pulse amplitude modulation (PAM-4) signals using Bayesian Machine Learning approach previously introduced for NRZ by authors and expanded for PAM-4. A new optimal covariant function and hyper-parameters has been selected for the Bayesian optimization. Cost function for the Bayesian optimization is chosen based on eye height. The proposed method was compared to the conventional Least Mean Square (LMS) method and showed significant improvement. Test cases were performed for several data rates of NRZ and PAM-4 signals with crosstalk and injected jitter. Test results show that the proposed algorithm is the more effective the higher data rates are considered.

AB - The paper elaborates an efficient algorithm for optimization of joint Feed-Forward Equalization (FFE) and Decision Feedback Equalization (DFE) for non-return-to-zero (NRZ) and 4 level pulse amplitude modulation (PAM-4) signals using Bayesian Machine Learning approach previously introduced for NRZ by authors and expanded for PAM-4. A new optimal covariant function and hyper-parameters has been selected for the Bayesian optimization. Cost function for the Bayesian optimization is chosen based on eye height. The proposed method was compared to the conventional Least Mean Square (LMS) method and showed significant improvement. Test cases were performed for several data rates of NRZ and PAM-4 signals with crosstalk and injected jitter. Test results show that the proposed algorithm is the more effective the higher data rates are considered.

KW - Bayesian Optimization

KW - Cost Function

KW - Covariant Function

KW - DFE

KW - Equalization

KW - FFE

KW - Joint Optimization

KW - Tap Coefficients

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/4522

UR - https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

U2 - 10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

DO - 10.1109/EMC/SI/PI/EMCEurope52599.2021.9559157

M3 - Article

JO - Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC)

JF - Proceedings of the 2021 Joint IEEE International Symposium on EMC/SI/PI, and EMC Europe (2021, Raleigh, NC)

ER -

Optimization of Joint Equalization of High-Speed Signals using Bayesian Machine Learning

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this