2022
DOI: 10.1109/jphot.2022.3193727
|View full text |Cite
|
Sign up to set email alerts
|

Linear Regression vs. Deep Learning for Signal Quality Monitoring in Coherent Optical Systems

Abstract: Error vector magnitude (EVM) is a metric for assessing the quality of m-ary quadrature amplitude modulation (mQAM) signals. Recently proposed deep learning techniques, e.g., feedforward neural networks (FFNNs) -based EVM estimation scheme leverage fast signal quality monitoring in coherent optical communication systems. Such a scheme estimates EVM from amplitude histograms (AHs) of short signal sequences captured before carrier phase recovery (CPR). In this work, we explore further complexity reduction by prop… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
3

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 27 publications
0
3
0
Order By: Relevance
“…The proposed ANN reports an overall MAE of 0.0432%, indicating a notable improvement in accuracy. When compared to the MAE published by [11,13,19] which varies between 0.06% and 3.7% for various modulation forms, this figure stands out significantly. The measured MAE points to both a significant improvement and a possible breakthrough in coherent optical communications EVM estimation accuracy.…”
Section: Numerical Results and Processing Costmentioning
confidence: 75%
See 1 more Smart Citation
“…The proposed ANN reports an overall MAE of 0.0432%, indicating a notable improvement in accuracy. When compared to the MAE published by [11,13,19] which varies between 0.06% and 3.7% for various modulation forms, this figure stands out significantly. The measured MAE points to both a significant improvement and a possible breakthrough in coherent optical communications EVM estimation accuracy.…”
Section: Numerical Results and Processing Costmentioning
confidence: 75%
“…The structural arrangement of the model is tested and refined for optimum performance. After that, a loss function [18][19][20][21] is employed to quantify the discrepancy between the real reference value and the anticipated output. The derivative of the loss is analyzed so that the influence of each contribution of the weight to the overall loss can be evaluated.…”
Section: Flowchart Of Annmentioning
confidence: 99%
“…Further, the MLP regressor had a better performance on the test/validation sets for the hologram and phase-only image datasets with a fixed EV regression score of 0.00 compared to the CNN and the other machine learning regressors [ 51 ]. The RF regressor had a better performance on the validation set for the concatenated intensity–phase image dataset with a stable EV regression score of 0.01 compared to the CNN and the other regressors [ 52 ]. Therefore, we concluded that both the CNN and the machine learning classifiers and regressors (KNN, MLP, DT, RF, and ET) had a superior performance in both the five-class classification and regression tasks for all three datasets.…”
Section: Discussionmentioning
confidence: 99%