Abstract

We propose a transfer learning assisted deep neural network (DNN) method for optical-signal-to-noise ratio (OSNR) monitoring and realize fast remodel to response to various system parameters changing, e.g. optical launch power, residual chromatic dispersion (CD) and bit rate. By transferring the hyper-parameters of DNN at the initial stage, we can fast response to the channel variation with fewer training set size and calculations to save consumptions. For feature extraction processing, we use amplitude histograms of received 56-Gb/s QPSK signals as the input for DNN at the initial stage, which shows the root mean squared error (RMSE) of OSNR estimation is less than 0.1 dB with the OSNRs ranging from 5 to 35 dB. Then, we change several system parameters and find superior capabilities of fast remodeling and data resource saving with the proposed method. The required training epochs have about four times reduction, and the required training set size is only one-fifth compared to retraining the network without any accuracy penalty. The DNN assisted by transfer learning can save resources and will be beneficial for real-time application on OSNR estimation.

© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Full Article  |  PDF Article
OSA Recommended Articles
Transfer learning simplified multi-task deep neural network for PDM-64QAM optical performance monitoring

Yijun Cheng, Wenkai Zhang, Songnian Fu, Ming Tang, and Deming Liu
Opt. Express 28(5) 7607-7617 (2020)

Multi-task deep neural network (MT-DNN) enabled optical performance monitoring from directly detected PDM-QAM signals

Yijun Cheng, Songnian Fu, Ming Tang, and Deming Liu
Opt. Express 27(13) 19062-19074 (2019)

Intelligent constellation diagram analyzer using convolutional neural network-based deep learning

Danshi Wang, Min Zhang, Jin Li, Ze Li, Jianqiang Li, Chuang Song, and Xue Chen
Opt. Express 25(15) 17150-17166 (2017)

References

  • View by:
  • |
  • |
  • |

  1. Z. Huang, J. Qiu, Y. Tian, Y. Li, H. Guo, X. Hong, C. Wang, and J. Wu, “A Novel High-Performance OSNR Measurement Technique Based on the Polynomial Fitting Function of Signals,” J. Lightwave Technol. 36(14), 3018–3022 (2018).
    [Crossref]
  2. J. Thrane, J. Wass, M. Piels, J. C. M. Diniz, R. Jones, and D. Zibar, “Machine Learning Techniques for Optical Performance Monitoring From Directly Detected PDM-QAM Signals,” J. Lightwave Technol. 35(4), 868–875 (2017).
    [Crossref]
  3. Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical Performance Monitoring: A Review of Current and Future Technologies,” J. Lightwave Technol. 34(2), 525–543 (2016).
    [Crossref]
  4. F. N. Khan, K. Zhong, X. Zhou, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks,” Opt. Express 25(15), 17767–17776 (2017).
    [Crossref]
  5. C. K. Chan, Optical performance monitoring: advanced techniques for next-generation photonic networks (Academic, 2010).
  6. J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.
  7. L. Lundberg, H. Sunnerud, and P. Johannisson, “In-Band OSNR Monitoring of PM-QPSK Using the Stokes Parameters,” in Optical Fiber Communications Conference (OFC, 2015), paper W4D. 5.
  8. M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
    [Crossref]
  9. F. N. Khan, C. Lu, and A. P. T. Lau, “Optical Performance Monitoring in Fiber-Optic Networks Enabled by Machine Learning Techniques,” in Optical Fiber Communications Conference (OFC, 2018), paper M2F. 3.
  10. T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.
  11. L. Guesmi, A. M. Ragheb, H. Fathallah, and M. Menif, “Experimental Demonstration of Simultaneous Modulation Format/Symbol Rate Identification and Optical Performance Monitoring for Coherent Optical Systems,” J. Lightwave Technol. 36(11), 2230–2239 (2018).
    [Crossref]
  12. D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
    [Crossref]
  13. Z. Wang, A. Yang, P. Guo, and P. He, “OSNR and nonlinear noise power estimation for optical fiber communication systems using LSTM based deep learning technique,” Opt. Express 26(16), 21346–21357 (2018).
    [Crossref]
  14. M. Kang and N. J. Jameson, “Machine Learning: Fundamentals,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 85–109.
  15. M. Kang, “Machine Learning: Diagnostics and Prognostics,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 163–191.
  16. S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010).
    [Crossref]
  17. K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J Big Data 3(1), 9 (2016).
    [Crossref]
  18. W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.
  19. N. M. Nasrabadi, “Pattern recognition and machine learning,” J. Electron. Imaging 16(4), 049901 (2007).
    [Crossref]
  20. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
    [Crossref]
  21. N. D. Lawrence and J. C. Platt, “Learning to learn with the informative vector machine,” in 21th International Conference on Machine learning (ICML, 2004), pp. 65.
  22. E. Bonilla, K. M. Chai, and C. Williams, “Multi-task Gaussian process prediction,” in Advances in Neural Information Processing Systems (NIPS, 2008), pp. 153–160.
  23. A. Schwaighofer, V. Tresp, and K. Yu, “Learning Gaussian process kernels via hierarchical Bayes,” in Advances in Neural Information Processing Systems (NIPS, 2005), pp.1209–1216.
  24. T. Evgeniou and M. Pontil, “Regularized multi–task learning,” in 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2004), pp. 109–117.
  25. J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.
  26. J. Ba and D. Kingma, “Adam: a method for stochastic optimization,” in 3rd International Conference on Learning Representations (ICLR, 2015).
  27. V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in 27th International Conference on Machine Learning (ICML, 2010), pp. 807–814.
  28. S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning (ICML, 2015).
  29. M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

2018 (3)

2017 (3)

2016 (2)

2015 (1)

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
[Crossref]

2014 (1)

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
[Crossref]

2010 (1)

S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010).
[Crossref]

2007 (1)

N. M. Nasrabadi, “Pattern recognition and machine learning,” J. Electron. Imaging 16(4), 049901 (2007).
[Crossref]

Abadi, M.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Al-Arashi, W. H.

Aono, Y.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Ba, J.

J. Ba and D. Kingma, “Adam: a method for stochastic optimization,” in 3rd International Conference on Learning Representations (ICLR, 2015).

Barham, P.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Bengio, Y.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
[Crossref]

Bonilla, E.

E. Bonilla, K. M. Chai, and C. Williams, “Multi-task Gaussian process prediction,” in Advances in Neural Information Processing Systems (NIPS, 2008), pp. 153–160.

Chai, K. M.

E. Bonilla, K. M. Chai, and C. Williams, “Multi-task Gaussian process prediction,” in Advances in Neural Information Processing Systems (NIPS, 2008), pp. 153–160.

Chan, C. K.

C. K. Chan, Optical performance monitoring: advanced techniques for next-generation photonic networks (Academic, 2010).

Chen, J.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Chen, X.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Chen, Z.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Cui, Y.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Davis, A.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Dean, J.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Diniz, J. C. M.

Dong, Z.

Evgeniou, T.

T. Evgeniou and M. Pontil, “Regularized multi–task learning,” in 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2004), pp. 109–117.

Fan, W.

J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.

Faruk, M. S.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
[Crossref]

Fathallah, H.

Fu, M.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Gao, J.

J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.

Guesmi, L.

Guo, H.

Guo, P.

Han, J.

J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.

He, P.

Hinton, G.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
[Crossref]

Hinton, G. E.

V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in 27th International Conference on Machine Learning (ICML, 2010), pp. 807–814.

Hong, X.

Hoshida, T.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Huang, Y.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Huang, Z.

Ioffe, S.

S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning (ICML, 2015).

Ip, E.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Jameson, N. J.

M. Kang and N. J. Jameson, “Machine Learning: Fundamentals,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 85–109.

Jiang, J.

J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.

Johannisson, P.

L. Lundberg, H. Sunnerud, and P. Johannisson, “In-Band OSNR Monitoring of PM-QPSK Using the Stokes Parameters,” in Optical Fiber Communications Conference (OFC, 2015), paper W4D. 5.

Jones, R.

Kang, M.

M. Kang, “Machine Learning: Diagnostics and Prognostics,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 163–191.

M. Kang and N. J. Jameson, “Machine Learning: Fundamentals,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 85–109.

Khan, F. N.

Khoshgoftaar, T. M.

K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J Big Data 3(1), 9 (2016).
[Crossref]

Kikuchi, K.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
[Crossref]

Kilper, D. C.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Kingma, D.

J. Ba and D. Kingma, “Adam: a method for stochastic optimization,” in 3rd International Conference on Learning Representations (ICLR, 2015).

Kudlur, M.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

Lai, J.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Lau, A. P. T.

Lawrence, N. D.

N. D. Lawrence and J. C. Platt, “Learning to learn with the informative vector machine,” in 21th International Conference on Machine learning (ICML, 2004), pp. 65.

LeCun, Y.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
[Crossref]

Li, J.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Li, S.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Li, Y.

Li, Z.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Lu, C.

Lundberg, L.

L. Lundberg, H. Sunnerud, and P. Johannisson, “In-Band OSNR Monitoring of PM-QPSK Using the Stokes Parameters,” in Optical Fiber Communications Conference (OFC, 2015), paper W4D. 5.

Menif, M.

Mo, W.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Mori, Y.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
[Crossref]

Morikawa, H.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Nair, V.

V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in 27th International Conference on Machine Learning (ICML, 2010), pp. 807–814.

Nasrabadi, N. M.

N. M. Nasrabadi, “Pattern recognition and machine learning,” J. Electron. Imaging 16(4), 049901 (2007).
[Crossref]

Pan, S. J.

S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010).
[Crossref]

Piels, M.

Platt, J. C.

N. D. Lawrence and J. C. Platt, “Learning to learn with the informative vector machine,” in 21th International Conference on Machine learning (ICML, 2004), pp. 65.

Pontil, M.

T. Evgeniou and M. Pontil, “Regularized multi–task learning,” in 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2004), pp. 109–117.

Qiu, J.

Ragheb, A. M.

Rasmussen, J. C.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Schwaighofer, A.

A. Schwaighofer, V. Tresp, and K. Yu, “Learning Gaussian process kernels via hierarchical Bayes,” in Advances in Neural Information Processing Systems (NIPS, 2005), pp.1209–1216.

Sui, Q.

Sunnerud, H.

L. Lundberg, H. Sunnerud, and P. Johannisson, “In-Band OSNR Monitoring of PM-QPSK Using the Stokes Parameters,” in Optical Fiber Communications Conference (OFC, 2015), paper W4D. 5.

Suzuki, M.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Szegedy, C.

S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning (ICML, 2015).

Tajima, T.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Tang, R.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Tang, X.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Tanimura, T.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Thrane, J.

Tian, Y.

Tresp, V.

A. Schwaighofer, V. Tresp, and K. Yu, “Learning Gaussian process kernels via hierarchical Bayes,” in Advances in Neural Information Processing Systems (NIPS, 2005), pp.1209–1216.

Wang, C.

Wang, D.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J Big Data 3(1), 9 (2016).
[Crossref]

Wang, Z.

Wass, J.

Weiss, K.

K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J Big Data 3(1), 9 (2016).
[Crossref]

Williams, C.

E. Bonilla, K. M. Chai, and C. Williams, “Multi-task Gaussian process prediction,” in Advances in Neural Information Processing Systems (NIPS, 2008), pp. 153–160.

Wu, B.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Wu, J.

Yang, A.

Yang, Q.

S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010).
[Crossref]

Yu, C.

Yu, K.

A. Schwaighofer, V. Tresp, and K. Yu, “Learning Gaussian process kernels via hierarchical Bayes,” in Advances in Neural Information Processing Systems (NIPS, 2005), pp.1209–1216.

Zhang, H.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Zhang, M.

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

Zhang, S.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

Zhao, W.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Zhao, X.

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

Zhong, K.

Zhou, X.

Zibar, D.

IEEE Photonics J. (1)

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 1–9 (2014).
[Crossref]

IEEE Photonics Technol. Lett. (1)

D. Wang, M. Zhang, Z. Li, J. Li, M. Fu, Y. Cui, and X. Chen, “Modulation format recognition and OSNR estimation using CNN-based deep learning,” IEEE Photonics Technol. Lett. 29(19), 1667–1670 (2017).
[Crossref]

IEEE Trans. Knowl. Data Eng. (1)

S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010).
[Crossref]

J Big Data (1)

K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J Big Data 3(1), 9 (2016).
[Crossref]

J. Electron. Imaging (1)

N. M. Nasrabadi, “Pattern recognition and machine learning,” J. Electron. Imaging 16(4), 049901 (2007).
[Crossref]

J. Lightwave Technol. (4)

Nature (1)

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 521(7553), 436–444 (2015).
[Crossref]

Opt. Express (2)

Other (17)

M. Kang and N. J. Jameson, “Machine Learning: Fundamentals,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 85–109.

M. Kang, “Machine Learning: Diagnostics and Prognostics,” Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (Wiley, 2018), pp. 163–191.

C. K. Chan, Optical performance monitoring: advanced techniques for next-generation photonic networks (Academic, 2010).

J. Lai, R. Tang, B. Wu, S. Li, X. Zhao, X. Tang, W. Zhao, and H. Zhang, “Research on optical performance monitoring (OPM) in coherent transmission system,” in Asia Communications and Photonics Conference (ACP, 2016), paper AS2B.2.

L. Lundberg, H. Sunnerud, and P. Johannisson, “In-Band OSNR Monitoring of PM-QPSK Using the Stokes Parameters,” in Optical Fiber Communications Conference (OFC, 2015), paper W4D. 5.

N. D. Lawrence and J. C. Platt, “Learning to learn with the informative vector machine,” in 21th International Conference on Machine learning (ICML, 2004), pp. 65.

E. Bonilla, K. M. Chai, and C. Williams, “Multi-task Gaussian process prediction,” in Advances in Neural Information Processing Systems (NIPS, 2008), pp. 153–160.

A. Schwaighofer, V. Tresp, and K. Yu, “Learning Gaussian process kernels via hierarchical Bayes,” in Advances in Neural Information Processing Systems (NIPS, 2005), pp.1209–1216.

T. Evgeniou and M. Pontil, “Regularized multi–task learning,” in 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2004), pp. 109–117.

J. Gao, W. Fan, J. Jiang, and J. Han, “Knowledge transfer via multiple model local structure mapping,” in 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2008), pp. 283–291.

J. Ba and D. Kingma, “Adam: a method for stochastic optimization,” in 3rd International Conference on Learning Representations (ICLR, 2015).

V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in 27th International Conference on Machine Learning (ICML, 2010), pp. 807–814.

S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning (ICML, 2015).

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, and M. Kudlur, “TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI, 2016), pp. 265–283.

W. Mo, Y. Huang, S. Zhang, E. Ip, D. C. Kilper, Y. Aono, and T. Tajima, “ANN-Based Transfer Learning for QoT Prediction in Real-Time Mixed Line-Rate Systems,” in Optical Fiber Communications Conference (OFC, 2018), paper W4F.3.

F. N. Khan, C. Lu, and A. P. T. Lau, “Optical Performance Monitoring in Fiber-Optic Networks Enabled by Machine Learning Techniques,” in Optical Fiber Communications Conference (OFC, 2018), paper M2F. 3.

T. Tanimura, T. Hoshida, J. C. Rasmussen, M. Suzuki, and H. Morikawa, “OSNR monitoring by deep neural networks trained with asynchronously sampled data,” in OptoElectronics and Communications Conference (OECC, 2016), pp. 1–3.

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (7)

Fig. 1.
Fig. 1. The schematic diagram of (a) the deep neural network, (b) transfer learning assisted DNN method for OSNR estimation.
Fig. 2.
Fig. 2. System block diagram of transfer learning assisted DNN for coherent optical transmission system. DACs: digital to analogue converters, LD: laser diode.
Fig. 3.
Fig. 3. The AHs of QPSK signal for two different OSNRs: 12 dB (first row) and 20 dB (second row), three different CDs: 100 ps/nm (first column), 300 ps/nm (second column) and 500 ps/nm (third column).
Fig. 4.
Fig. 4. The results of DNN based monitoring for (a) actual OSNR vs. estimated OSNR, (b) the RMSE of each estimated OSNR in the simulation and (c) actual OSNR vs. estimated OSNR, (d) the RMSE of each estimated OSNR in the experiment.
Fig. 5.
Fig. 5. Transfer learning vs. retraining for simulation signals at various different launch powers with a same training set size of 10%. (a) The RMSE of estimated OSNR, (b) The required epochs for training process.
Fig. 6.
Fig. 6. The experimental comparison on the convergence speed for transfer learning (15% of training set size) and retraining (75% of training set size). (a) Epochs vs. different residual CDs, (b) The training process when the target domain is at the CD of 100 ps/nm.
Fig. 7.
Fig. 7. The RMSE of transfer learning vs. retraining at different training set sizes.

Tables (2)

Tables Icon

Table 1. Parameter settings of source domain and target domain.

Tables Icon

Table 2. The performance comparison between transfer learning and retraining scheme.

Equations (2)

Equations on this page are rendered with MathJax. Learn more.

w S = w 0 + v S  and  w T = w 0 + v T ,
m i n w 0 , v t , b J T ( w 0 , v t ) = 1 2 × t { S , T } i = 1 N [ y i f ( x i ; w 0 , v t ) ] 2 + c o n s t .

Metrics