Proceedings ArticleDOI
Computational-Complexity Comparison of Artificial Neural Network and Volterra Series Transfer Function for Optical Nonlinearity Compensation with Time- and Frequency-Domain Dispersion Equalization
Takeru Kyono,Yuta Otsuka,Yuta Fukumoto,Shotaro Owaki,Moriya Nakamura +4 more
- pp 8535153
Reads0
Chats0
TLDR
The results show that the ANN involved lower computational complexity than the VSTF when additional time-domain nonlinear processing is required.Abstract:
We evaluated the number of complex multiplications in an ANN and a VSTF for optical nonlinearity compensation. The results show that the ANN involved lower computational complexity than the VSTF when additional time-domain nonlinear processing is required.read more
Citations
More filters
Journal ArticleDOI
A Simple Joint Modulation Format Identification and OSNR Monitoring Scheme for IMDD OOFDM Transceivers Using K-Nearest Neighbor Algorithm
Zhang Qianwu,Hai Zhou,Yuntong Jiang,Bingyao Cao,Yingchun Li,Yingxiong Song,Jian Chen,Junjie Zhang,Min Wang +8 more
TL;DR: Experimental results show that five common quadrature amplitude modulation (QAM) modulation formats can be identified and system OSNR monitoring can be achieved and the average prediction mean square error is similar to that using an artificial neural network.
Journal ArticleDOI
IM/DD mode division multiplexing transmission enabled by machine learning-based linear and nonlinear MIMO equalization
TL;DR: Two mode division multiplexing transmission systems through few-mode fiber by using two degenerate LP11 modes in high speed and low cost optical interconnection scenarios are demonstrated and two novel MIMO equalizers based on machine learning are proposed and utilized to eliminate the impairments.
Journal ArticleDOI
Deep Neural Network Based Chromatic Dispersion Estimation With Ultra-Low Sampling Rate for Optical Fiber Communication Systems
TL;DR: A novel CD estimation method based on the deep neural network (DNN) with ultra-low sampling rate is proposed for the optical fiber transmission systems and shows great potential for the cost-effective under-sampled systems.
Proceedings ArticleDOI
Overfitting of ANN-based Nonlinear Equalizer for Multilevel Signals in Optical Communication Systems
TL;DR: The results show that Gray coding works to relax the condition which causes the overfitting of ANN-based nonlinear equalizer for multilevel optical signals generated by PRBS.
Proceedings ArticleDOI
Polarization Tracking and Optical Nonlinearity Compensation Using Artificial Neural Networks
TL;DR: A novel polarization-tracking scheme using an artificial neural network (ANN), which can compensate nonlinear waveform distortion at the same time, is proposed, comparing with FIR filters.
Related Papers (5)
Equalization of optical nonlinear waveform distortion using neural-network based digital signal processing
Shotaro Owaki,Moriya Nakamura +1 more
An Intelligent Calculation Method of Volterra Time-Domain Kernel Based on Time-Delay Artificial Neural Network
Kaiyang Zhong,Lerui Chen +1 more