| 1. |
- He, Zonglong, 1994, et al.
(författare)
-
Experimental Demonstration of Learned Pulse Shaping Filter for Superchannels
- 2022
-
Ingår i: 2022 Optical Fiber Communications Conference and Exhibition, OFC 2022 - Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- We demonstrate a pulse shaping filter enabled by machine learning for spectral superchannels. In contrast to a 1% roll-off root-raised cosine filter, our learned filter reduces the adaptive equalizer length by 47% for the same spectral efficiency.
|
|
| 2. |
- He, Zonglong, 1994, et al.
(författare)
-
Periodicity-Enabled Size Reduction of Symbol Based Predistortion for High-Order QAM
- 2022
-
Ingår i: Journal of Lightwave Technology. - 0733-8724 .- 1558-2213. ; In press
-
Tidskriftsartikel (refereegranskat)abstract
- We experimentally demonstrate a novel size reduction approach for symbol-based look-up table (LUT) digital predistortion (DPD) of the transmitter impairments taking advantage of the periodicity in the pattern-dependent distortions. Compared to other reduced-size LUT schemes, the proposed method can significantly lessen the storage memory requirements with negligible performance penalty for high-order modulation formats. To further alleviate the storage memory restriction, a twice reduced-size LUT scheme is proposed to provide further size reduction. Importantly, given a targeted memory length, we verify the importance of averaging over sufficient occurrences of the patterns to obtain a well-performing LUT. Moreover, it is necessary to evaluate the performance of LUT-based DPD using random data. Finally, we demonstrate a neural network (NN) based nonlinear predistortion technique, which achieves nearly identical performance to the full-size LUT for all employed constellations and is robust against a change of modulation format. The proposed techniques are verified in a back-to-back transmission experiment of 20 Gbaud 64-QAM, 256-QAM, and 1024-QAM signals considering 3 and 5 symbol memory. The performance of the LUT-based DPD is further validated in a noise loading experiment.
|
|
| 3. |
- He, Zonglong, 1994, et al.
(författare)
-
Symbol-Based Supervised Learning Predistortion for Compensating Transmitter Nonlinearity
- 2021
-
Ingår i: 2021 European Conference on Optical Communication, ECOC 2021. - 9781665438681
-
Konferensbidrag (refereegranskat)abstract
- We experimentally demonstrate a symbol-based nonlinear digital predistortion (DPD) technique utilizing supervised learning, which is robust against a change of modulation format. Back-to-back transmission of 30 Gbaud 32, 64 and 256QAM confirms that our scheme significantly outperforms the baseline of arcsine-based predistortion.
|
|
| 4. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Blind Frequency-Domain Equalization Using Vector-Quantized Variational Autoencoders
- 2023
-
Ingår i: 2023 European Conference on Optical Communications, ECOC 2023. ; In press
-
Konferensbidrag (refereegranskat)abstract
- We propose a novel frequency-domain blind equalization scheme for coherent optical communications. The method is shown to achieve similar performance to its recently proposed time-domain counterpart with lower computational complexity, while outperforming the commonly used CMA-based equalizers.
|
|
| 5. |
- Song, Jinxiang, 1995, et al.
(författare)
-
End-to-end Autoencoder for Superchannel Transceivers with Hardware Impairments
- 2021
-
Ingår i: 2021 Optical Fiber Communications Conference and Exhibition, OFC 2021 - Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- We propose an end-to-end learning-based approach for superchannel systems impaired by non-ideal hardware component. Our system achieves up to 60% SER reduction and up to 50% guard band reduction compared with the considered baseline scheme.
|
|
| 6. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments
- 2022
-
Ingår i: IEEE Journal of Selected Topics in Quantum Electronics. - 1558-4542 .- 1077-260X. ; 28:4
-
Tidskriftsartikel (refereegranskat)abstract
- We propose an AE-based transceiver for a WDM system impaired by hardware imperfections. We design our AE following the architecture of conventional communication systems. This enables to initialize the AE-based transceiver to have similar performance to its conventional counterpart prior to training and improves the training convergence rate. We first train the AE in a single-channel system, and show that it achieves performance improvements by putting energy outside the desired bandwidth, and therefore cannot be used for a WDM system. We then train the AE in a WDM setup. Simulation results show that the proposed AE significantly outperforms the conventional approach. More specifically, it increases the spectral efficiency of the considered system by reducing the guard band by 37% and 50% for a root-raised-cosine filter-based matched filter with 10% and 1% roll-off, respectively. An ablation study indicates that the performance gain can be ascribed to the optimization of the symbol mapper, the pulse-shaping filter, and the symbol demapper. Finally, we use reinforcement learning to learn the pulse-shaping filter under the assumption that the channel model is unknown. Simulation results show that the reinforcement-learning-based algorithm achieves similar performance to the standard supervised end-to-end learning approach assuming perfect channel knowledge.
|
|
| 7. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Over-the-fiber Digital Predistortion Using Reinforcement Learning
- 2021
-
Ingår i: 2021 European Conference on Optical Communication, ECOC 2021. - 9781665438681
-
Konferensbidrag (refereegranskat)abstract
- We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning. Optical back-to-back training of a novel NN-based digital predistorter outperforms arcsine-based predistortion with up to 60% bit-error-rate reduction.
|
|
| 8. |
- Fougstedt, Christoffer, 1990, et al.
(författare)
-
Power-Efficient Time-Domain Dispersion Compensation Using Optimized FIR Filter Implementation
- 2015
-
Ingår i: Signal Processing in Photonics Communications, SPPCom 2015; Boston, MA; United States; 27 June 2015-1 July 2015. - 9781557520005 ; , s. SpT3D.3-
-
Konferensbidrag (refereegranskat)abstract
- We investigate fixed-point aspects and time-domain ASIC implementations of CD compensation. An optimized implementation gives significant power dissipation reduction for short links, with further reduction if pulse shaping is considered.
|
|
| 9. |
- Häger, Christian, 1986, et al.
(författare)
-
A Low-Complexity Detector for Memoryless Polarization-Multiplexed Fiber-Optical Channels
- 2014
-
Ingår i: IEEE Communications Letters. - 1558-2558 .- 1089-7798. ; 18:2, s. 368-371
-
Tidskriftsartikel (refereegranskat)abstract
- A low-complexity detector is introduced for polarization-multiplexed M-ary phase shift keying modulation in a fiber-optical channel impaired by nonlinear phase noise, generalizing a previous result by Lau and Kahn for single-polarization signals. The proposed detector uses phase compensation based on both received signal amplitudes in conjunction with simple straight-line rather than four-dimensional maximum-likelihood decision boundaries.
|
|
| 10. |
- LINDBERG, CHRISTOPHER, 1988, et al.
(författare)
-
Compressed Sensing in Wireless Sensor Networks without Explicit Position Information
- 2017
-
Ingår i: IIEEE Transactions on Signal and Information Processing over Networks. - 2373-776X. ; 3:2, s. 404-415
-
Tidskriftsartikel (refereegranskat)abstract
- Reconstruction in compressed sensing relies on knowledge of a sparsifying transform. In a setting where a sink reconstructs a field based on measurements from a wireless sensor network, this transform is tied to the locations of the individual sensors, which may not be available to the sink during reconstruction. In contrast to previous works, we do not assume that the sink knows the position of each sensor to build up the sparsifying basis. Instead, we propose the use of spatial interpolation based on a predetermined sparsifying transform, followed by random linear projections and ratio consensus using local communication between sensors. For this proposed architecture, we upper bound the reconstruction error induced by spatial interpolation, as well as the reconstruction error induced by distributed compression. These upper bounds are then utilized to analyze the communication cost tradeoff between communication to the sink and sensor-to-sensor communication.
|
|
