Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods

Bobi Shi; Yixuan Zhao; Hanzhi Ma; Thong Nguyen; Er Ping Li; Andreas C. Cangellaris; Jose Schutt-Aine

doi:10.1109/EDAPS53774.2021.9656986

Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods

Bobi Shi, Yixuan Zhao, Hanzhi Ma, Thong Nguyen, Er Ping Li, Andreas C. Cangellaris, Jose Schutt-Aine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this work, a direct surrogate model from channel geometry to decision feedback equalization taps is constructed by four different machine learning methods, namely Polynomial Regression, Feed-forward Neural Network, Support Vector Regression, and Polynomial Chaos. They will be used to replace computational heavy simulations done by electromagnetic solver and channel simulation. Overall, all methods can offer 1% relative error rate of the prediction in this numerical example.

Original language	English (US)
Title of host publication	2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665466134
DOIs	https://doi.org/10.1109/EDAPS53774.2021.9656986
State	Published - 2021
Event	2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021 - Urbana, United States Duration: Dec 13 2021 → Dec 15 2021

Publication series

Name	IEEE Electrical Design of Advanced Packaging and Systems Symposium
Volume	2021-December
ISSN (Print)	2151-1225
ISSN (Electronic)	2151-1233

Conference

Conference	2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021
Country/Territory	United States
City	Urbana
Period	12/13/21 → 12/15/21

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering
Automotive Engineering
General Computer Science

Online availability

10.1109/EDAPS53774.2021.9656986

Library availability

Discover UIUC Full Text

Cite this

Shi, B., Zhao, Y., Ma, H., Nguyen, T., Li, E. P., Cangellaris, A. C., & Schutt-Aine, J. (2021). Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods. In 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021 (IEEE Electrical Design of Advanced Packaging and Systems Symposium; Vol. 2021-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EDAPS53774.2021.9656986

Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods. / Shi, Bobi; Zhao, Yixuan; Ma, Hanzhi et al.
2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (IEEE Electrical Design of Advanced Packaging and Systems Symposium; Vol. 2021-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shi, B, Zhao, Y, Ma, H, Nguyen, T, Li, EP, Cangellaris, AC & Schutt-Aine, J 2021, Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods. in 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021. IEEE Electrical Design of Advanced Packaging and Systems Symposium, vol. 2021-December, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021, Urbana, United States, 12/13/21. https://doi.org/10.1109/EDAPS53774.2021.9656986

Shi B, Zhao Y, Ma H, Nguyen T, Li EP, Cangellaris AC et al. Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods. In 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (IEEE Electrical Design of Advanced Packaging and Systems Symposium). doi: 10.1109/EDAPS53774.2021.9656986

@inproceedings{531c06c84ed140628aeeeefc0dc4663e,

title = "Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods",

abstract = "In this work, a direct surrogate model from channel geometry to decision feedback equalization taps is constructed by four different machine learning methods, namely Polynomial Regression, Feed-forward Neural Network, Support Vector Regression, and Polynomial Chaos. They will be used to replace computational heavy simulations done by electromagnetic solver and channel simulation. Overall, all methods can offer 1% relative error rate of the prediction in this numerical example.",

author = "Bobi Shi and Yixuan Zhao and Hanzhi Ma and Thong Nguyen and Li, {Er Ping} and Cangellaris, {Andreas C.} and Jose Schutt-Aine",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021 ; Conference date: 13-12-2021 Through 15-12-2021",

year = "2021",

doi = "10.1109/EDAPS53774.2021.9656986",

language = "English (US)",

series = "IEEE Electrical Design of Advanced Packaging and Systems Symposium",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021",

address = "United States",

}

TY - GEN

T1 - Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods

AU - Shi, Bobi

AU - Zhao, Yixuan

AU - Ma, Hanzhi

AU - Nguyen, Thong

AU - Li, Er Ping

AU - Cangellaris, Andreas C.

AU - Schutt-Aine, Jose

PY - 2021

Y1 - 2021

N2 - In this work, a direct surrogate model from channel geometry to decision feedback equalization taps is constructed by four different machine learning methods, namely Polynomial Regression, Feed-forward Neural Network, Support Vector Regression, and Polynomial Chaos. They will be used to replace computational heavy simulations done by electromagnetic solver and channel simulation. Overall, all methods can offer 1% relative error rate of the prediction in this numerical example.

AB - In this work, a direct surrogate model from channel geometry to decision feedback equalization taps is constructed by four different machine learning methods, namely Polynomial Regression, Feed-forward Neural Network, Support Vector Regression, and Polynomial Chaos. They will be used to replace computational heavy simulations done by electromagnetic solver and channel simulation. Overall, all methods can offer 1% relative error rate of the prediction in this numerical example.

UR - http://www.scopus.com/inward/record.url?scp=85124125484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85124125484&partnerID=8YFLogxK

U2 - 10.1109/EDAPS53774.2021.9656986

DO - 10.1109/EDAPS53774.2021.9656986

M3 - Conference contribution

AN - SCOPUS:85124125484

T3 - IEEE Electrical Design of Advanced Packaging and Systems Symposium

BT - 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Electrical Design of Advanced Packaging and Systems, EDAPS 2021

Y2 - 13 December 2021 through 15 December 2021

ER -

Decision Feedback Equalizer (DFE) Taps Estimation with Machine Learning Methods

Abstract

Publication series

Conference

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this